Machine learning device, insulation state diagnosing device, machine learning method, machine learning program, insulation state diagnosing method, and insulation state diagnosing program

Abstract

To provide a machine learning device capable of diagnosing the insulation state of a winding without stopping a canned motor pump.SOLUTION: A machine learning device 4 generates a learning model 6 used in an insulation state diagnosing device 5 for diagnosing the insulation state of a winding 31 of a stator 23 used in a canned motor pump 2. The machine learning device 4 accepts, as input data, the data of voltage and current values supplied a motor unit 20, the data of temperature of the winding 31 of the stator 23 or a temperature, temperature difference or pressure having a correlation with the foregoing, and the data of inflow temperature and flow rate of a handling liquid in a pump unit 10 that is unprocessed data or at least partly preprocessed data, and inputs training data including at least these input data to the learning model 6, thereby making the learning model to learn a correlation relationship between the input data and diagnosis information on the insulation state of the winding.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a machine learning device, an insulation condition diagnosis device, a machine learning method, a machine learning program, an insulation condition diagnosis method, and an insulation condition diagnosis program suitable for diagnosing the insulation condition of the windings of the motor section of a canned motor pump having a motor section and a pump section. [Background technology]

[0002] In a canned motor pump, the rotor of the motor section that drives the pump section is housed in a can that is filled with the pump liquid, and the stator of the motor section is disposed around the outer periphery of the can and housed in a motor housing that functions as a case. In such canned motor pumps, the motor output is set based on the allowable temperature of the stator coil. That is, the rotor of a canned motor pump is cooled quickly because it is surrounded by the liquid being pumped. For this reason, heat is generated mainly on the stator side in canned motor pumps, with the coil ends being the hottest. For this reason, conventionally, the motor output and liquid temperature have been regulated so that the temperature of the coil ends does not exceed the allowable temperature. In addition, canned motor pumps generally guide a portion of the liquid being pumped into a can in which the rotor is disposed, to lubricate and cool the bearings, and also to absorb heat from the motor section (rotor, etc.) before returning the liquid to the pump section.

[0003] However, canned motor pumps are often used in plants that handle high-temperature liquids. Therefore, when high-temperature liquid is introduced into the can, the windings of the motor section reach a temperature higher than the temperature of the liquid, and are easily exposed to high temperatures that exceed the allowable range of the heat-resistant insulation. For this reason, there is a concern that the insulation of the windings of the motor section of a canned motor pump will deteriorate if it is used for a long period of time in a high-temperature environment. When the insulation of the windings deteriorates, they need to be replaced, but because the stator is sealed between the can and the motor housing, replacing the stator windings requires disassembly of the sealed motor section, etc. Since such disassembly work requires a lot of cost and man-hours, it is necessary to properly judge the lifespan of the windings, i.e., the insulation condition of the windings.

[0004] Therefore, in the past, in order to diagnose deterioration of the windings, the canned motor pump was stopped and the insulation resistance and inter-terminal resistance of the windings were measured periodically, and these were compared with normal values ​​and past measured values ​​to perform trend management of the insulation condition (see Patent Document 1). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2010-256348 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in order to perform trend management of the insulation condition of the windings, it is necessary to stop the canned motor pump and measure the resistance values ​​(insulation resistance, terminal-to-terminal resistance), and it is difficult to frequently stop the canned motor pump while the plant is operating.

[0007] The present invention has been made in consideration of the above-mentioned circumstances, and has as its main objective the provision of a machine learning device, an insulation condition diagnosis device, a machine learning method, a machine learning program, an insulation condition diagnosis method, and an insulation condition diagnosis program that enable diagnosing the insulation condition of a winding without stopping a canned motor pump. [Means for solving the problem]

[0008] According to an embodiment of the present invention, a machine learning device The pump has a motor section and a pump section driven by the motor section, the motor unit includes a rotor rotatable about a shaft, a stator facing the rotor with a gap therebetween, and a cylindrical can that defines a rotor chamber for accommodating the rotor on the inside and a stator chamber for accommodating the stator together with a motor housing on the outside, A machine learning device that generates a learning model to be used in an insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump that circulates a part of a pumped liquid in the pump section to the rotor chamber, the machine learning device comprising: a learning data acquisition unit which receives as input data unprocessed data or data at least partially preprocessed, the data being data on voltage values ​​and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on temperatures, temperature differences or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid, and acquires a plurality of sets of learning data including at least this input data; a machine learning unit that inputs the learning data into the learning model to cause the learning model to learn a correlation between the input data and diagnostic information about the insulation state of the winding; A trained model storage unit that stores the learning model trained by the machine learning unit; The present invention is characterized by the following.

[0009] Moreover, the insulation condition diagnosis device according to one embodiment of the present invention comprises: An insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump, using a learning model generated by the above machine learning device, comprising: an input data acquisition unit that acquires input data including unprocessed data or data that has been at least partially preprocessed, such as data on voltage values ​​and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on temperatures, temperature differences, or pressures correlated therewith, and data on the inlet temperature and flow rate of the handled liquid; An inference unit inputs the input data acquired by the input data acquisition unit into the learning model and infers diagnostic information of an insulation state of the stator winding.

[0010] In addition, a machine learning method according to an embodiment of the present invention includes: The pump has a motor section and a pump section driven by the motor section, the motor unit includes a rotor rotatable about a shaft, a stator facing the rotor with a gap therebetween, and a cylindrical can that defines a rotor chamber for accommodating the rotor on the inside and a stator chamber for accommodating the stator together with a motor housing on the outside, A machine learning method for learning a learning model used in an insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump that circulates a part of a pumped liquid in the pump section to the rotor chamber, comprising: a learning data acquisition step of acquiring a plurality of sets of learning data including at least the input data, the input data being unprocessed data or data that has been at least partially preprocessed, the input data being data on voltage and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on temperatures, temperature differences or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid; a machine learning process for inputting the learning data into the learning model to cause the learning model to learn a correlation between the input data and diagnostic information on the insulation state of the winding; The method further includes a trained model storage step of storing the learned model trained by the machine learning step in a trained model storage unit.

[0011] In addition, the machine learning program according to an embodiment of the present invention is The computer is caused to execute each step of the machine learning method.

[0012] Further, the insulation condition diagnosis method according to one embodiment of the present invention includes the steps of: An insulation condition diagnosis method for diagnosing an insulation condition of a winding of the stator used in the canned motor pump by using a learning model generated by the machine learning device, comprising: an input data acquisition step of acquiring input data including data on voltage and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on a temperature, temperature difference or pressure correlated therewith, and data on the inlet temperature and flow rate of the treated liquid, the input data including unprocessed data or data that has been at least partially preprocessed; an inference step of inputting the input data acquired by the input data acquisition step into the learning model and inferring diagnostic information on an insulation state of the stator winding; An insulation condition diagnosis method comprising:

[0013] In addition, an insulation state diagnosis program according to an embodiment of the present invention includes: The method causes a computer to execute each step of the insulation condition diagnosis method. Effect of the Invention

[0014] According to the present invention, it is possible to provide a machine learning device, an insulation condition diagnosis device, a machine learning method, a machine learning program, an insulation condition diagnosis method, and an insulation condition diagnosis program that enable diagnosis of the insulation condition of a winding without stopping a canned motor pump. [Brief description of the drawings]

[0015] [Figure 1] 1 is a schematic diagram showing an insulation condition diagnosis device applied to a canned motor pump; [Diagram 2] FIG. 2 is a cross-sectional view showing an example of a canned motor pump. [Diagram 3] FIG. 1 is a block diagram illustrating an example of a machine learning device. [Figure 4] 4 is a flowchart showing an example of a machine learning method performed by the machine learning device according to the first embodiment. [Diagram 5] FIG. 1 is a block diagram showing an example of an insulation state diagnosis device. [Figure 6] 4 is a flowchart showing an example of an insulation state diagnosis method by the insulation state diagnosis device according to the first embodiment. [Figure 7]FIG. 4 is a cross-sectional view showing another example of a canned motor pump. [Figure 8] FIG. 8(a) is a block diagram showing an example of a machine learning device applied to the canned motor pump shown in FIG. 7, and FIG. 8(b) is a block diagram showing an example of an insulation condition diagnosis device applied to the canned motor pump shown in FIG. 7. [Figure 9] 10 is a flowchart showing an example of a machine learning method performed by the machine learning device according to the second embodiment. [Figure 10] 10 is a flowchart showing an example of an insulation state diagnosis method by the insulation state diagnosis device according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. (First embodiment) 1 is a schematic diagram showing an insulation condition diagnosis system 1 applied to a canned motor pump. As an example of the canned motor pump 2 used here, a horizontal canned motor pump in which the motor axis direction is approximately horizontal is given, but the present invention is not limited to the horizontal type and can also be applied to a vertical canned motor pump in which the motor axis direction is approximately vertical.

[0017] First, the outline of the canned motor pump 2 will be described with reference to FIG. 2 is a cross-sectional view showing an example of the configuration of the canned motor pump 2 according to this embodiment. The X direction shown in the drawing is the motor axial direction, the right side in the drawing is the front, and the left side in the drawing is the rear.

[0018] In FIG. 2, the canned motor pump 2 has a pump section 10 having the configuration of a centrifugal pump, and a motor section 20 that drives this pump section 10, and the pump section 10 and the motor section 20 are coaxially coupled by a shaft 21 of a motor 24 which will be described later.

[0019] The pump section 10 has an impeller 11 and a pump casing 13 that forms a pump chamber 12 that houses the impeller 11. The impeller 11 is coupled to the front end of a shaft 21 of a motor 24. Note that, in this embodiment, the pump section 10 is described as being configured as a centrifugal pump, but the present invention is not limited to this, and the pump section 10 may be configured as a turbo pump such as a mixed flow pump or an axial flow pump.

[0020] The motor section 20 has a motor 24 including a rotor 22 fixed around the shaft 21 and rotating integrally with the shaft, and an annular stator 23 arranged to surround the rotor 22 at a predetermined distance, and a motor housing 25 that accommodates the motor 24.

[0021] Stator 23 has a stator core 30 having teeth arranged in the circumferential direction on its substantially cylindrical inner peripheral surface, and a winding (coil) 31 formed by winding a conductor around the teeth of stator core 30. An end of the conductor of winding 31 is guided into a terminal box 32 extending radially outward from an outer cylinder 41 of motor housing 25, and is connected to a terminal (not shown) provided in terminal box 32.

[0022] A cylindrical can 33 is disposed inside the stator core 30 but outside the rotor 22, i.e., between the rotor 22 and the stator 23. The can 33 is fixed in contact with the inner circumferential surface of the stator core 30, i.e., the tip surfaces of the teeth, and is disposed with a fixed gap between it and the outer circumferential surface of the rotor 22.

[0023] A cylindrical outer cylinder (stator band) 41 that houses the motor is provided along the outer circumferential surface of the stator core 30. The can 33 and the outer cylinder 41 are arranged concentrically, and are formed to have approximately the same length in the axial direction X. Annular plate-shaped end bells 42, 43 are arranged on both ends of the can 33 and the outer cylinder 41, respectively, and these end bells 42, 43 close the cylindrical space formed between the can 33 and the outer cylinder 41. The end bell 42 on the pump section 10 side is connected to the pump casing 13 by bolts. A bearing holder 44 that closes the space inside the can 33 is connected to the end bell 43 on the opposite side to the pump section 10 by bolts.

[0024] The outer cylinder 41, the end bells 42, 43 at both ends, and the bearing holder 44 form a motor housing 25 that accommodates the motor 24. Further, the can 33 , the pump portion 10 , and the bearing holder 44 form a rotor chamber 50 inside the can 33 , which accommodates the rotor 22 . Furthermore, a stator chamber 45 that houses the stator 23 is formed by a cylindrical space defined by the outer cylinder 41, the can 33, and the end bells 42, 43 at both ends. The stator chamber 45 has the stator core 30 disposed in a substantially central portion in the axial direction, and has annular coil end housing portions 45a, 45b that house the coil ends 31a, 31b at the front and rear of the stator core 30 in the axial direction. In addition, a cylindrical backup sleeve 34 (34a, 34b) for preventing the can 33 from being deformed is attached to the outer circumferential surface of the can 33 facing the coil end accommodating portions 45a, 45b.

[0025] Shaft 21, to which rotor 22 is integrally fixed, is supported at both ends by bearings 51, 52. Bearing 51 on the pump section 10 side is held by bearing portion 53 extending from bearing holder 44 fixed to end bell 42 behind pump casing 13 of pump section 10. Bearing 52 on the opposite side to pump section 10 is held by bearing portion 54 extending from bearing holder 46 fixed to end bell 43. These bearings 51, 52 are constituted by plain bearings positioned in bearing portions 53, 54.

[0026] The canned motor pump 2 is fixed to a support base 56 by legs 55 fixed to the end bells 42, 43.

[0027] The bearing holder 44 fixed to the back of the pump casing 13 of the pump section 10 is formed with an introduction passage 14 for introducing the handled liquid into the can 33. Also, the shaft 21 is formed with a central hole 15 along its entire length along its axis. A part of the handled liquid discharged by the impeller 11 becomes an internal circulating liquid circulating in the can 33 as shown by the arrow in FIG. 2. That is, the handled liquid flows around the back of the impeller 11 and is introduced into the can 33 (rotor chamber 50) through the introduction passage 14. The handled liquid introduced into the can 33 (rotor chamber 50) lubricates and cools the bearings 51 and 52 and cools the motor section 20 (rotor 22, etc.), and then enters the central hole 15 formed in the shaft from the rear end of the shaft 21. The handled liquid is then returned to the suction side of the pump section 10 through the central hole 15 and is discharged into the vortex chamber by the impeller 11.

[0028] For the canned motor pump 2 having the above-mentioned configuration, an insulation condition diagnosis system 1 is provided that diagnoses the insulation condition of the windings 31 of the stator 23. As shown in FIG. 1, this insulation condition diagnosis system 1 includes a measurement device 3, a machine learning device 4, and an insulation condition diagnosis device 5.

[0029] The measuring device 3 is installed in the canned motor pump 2 or in an appropriate location around it to measure physical quantities and state quantities of each part. In the learning phase, the measuring device 3 is connected to the machine learning device 4 and used to measure data for learning, and in the inference phase, the measuring device 3 is connected to the insulation condition diagnosis device 5 and used to measure data for diagnosis. Here, the measurement device 3 used in the learning phase and the measurement device used in the inference phase may be the same or different, and includes a motor voltage / current sensor 101, a winding heat generation state measurement sensor 102, and a handled liquid measurement sensor 103.

[0030] The motor voltage / current sensor 101 measures the motor voltage and current values ​​supplied to the motor section 20, and is attached, for example, to a power line connecting the motor 24 and the motor control device 26, and measures the voltage and current values ​​supplied from the motor control device 26 to the motor 24. Note that the motor voltage / current sensor 101 may be provided inside the motor section 20 or inside the motor control device 26. Moreover, the motor voltage / current sensor 101 may measure the voltage / current values ​​of each of the three phases.

[0031] The winding heat generation state measuring sensor 102 directly or indirectly measures the temperature of the windings 31 of the motor 24 (stator 23). That is, the winding heat generation state measuring sensor 102 measures the temperature of the windings or data of a temperature, a temperature difference, or a pressure correlated therewith. When the temperature of the winding 31 is measured directly, a thermocouple is attached to the hottest part of the winding 31, for example, the coil ends 31a and 31b, to measure the temperature. Alternatively, a thermocouple may be attached to the winding 31 inside the stator core 30 to measure the winding temperature. When the temperature of winding 31 is measured indirectly, a thermocouple may be attached to backup sleeves 34a, 34b, end bells 42, 43, or bearing holders 44, 46, which are affected by radiant heat from winding 31 or the state (amount, temperature) of the internal circulating fluid, and the surface temperatures of these locations may be measured. Here, an example has been described in which the winding heat generation state measurement sensor 102 detects temperature using a thermocouple, but other contact-type sensors such as a thermistor or resistance temperature detector, or a non-contact-type sensor such as an infrared sensor may also be used. In addition, in order to indirectly measure the temperature of the winding 31, the pressure P1 in the stator chamber 45 may be measured.

[0032] The handled liquid measurement sensor 103 is composed of, for example, an inflow temperature sensor 103 a and a flow rate sensor 103 b provided in the inflow pipe 60 connected to the inflow port 13 a of the pump casing 13 . The inflow temperature sensor 103a measures the temperature of the handled liquid flowing into the pump section 10, and for example, measures the fluid temperature in the inflow pipe 60 by a piping temperature sensor that uses a resistance temperature detector as the temperature detection element. Meanwhile, the flow rate sensor 103b measures the inflow rate of the handled liquid flowing into the pump section 10, and various types of sensors such as ultrasonic, electromagnetic, Karman vortex, impeller, float, thermal, and differential pressure types are available.

[0033] The measuring device 3 is configured to measure physical quantities and state quantities of each part, and output the measured values ​​to the machine learning device 4 or the insulation state diagnosis device 5. The measured values ​​measured by this measuring device 3 may be pinpoint measured values ​​measured at a predetermined timing, a group of discrete time-dependent measured values ​​measured at predetermined measurement intervals over a predetermined period of time, or continuous measured values ​​measured over a predetermined period of time.

[0034] The machine learning device 4 operates as a main part of the learning phase, and generates, by machine learning, a learning model 6 used when diagnosing the insulation state of the windings 31. Either "supervised learning" or "unsupervised learning" can be adopted as the machine learning, and the first embodiment adopts "supervised learning", while the second embodiment adopts "unsupervised learning".

[0035] The insulation condition diagnosis device 5 operates as the main body of the inference phase, and diagnoses (infers) the insulation condition of the windings 31 from the measurement values ​​measured by the measurement device 3, using the trained learning model 6 generated by the machine learning device 4.

[0036] (Machine learning device) The machine learning device 4 is configured by a general-purpose or dedicated computer. This computer may be a stationary computer or a portable computer, and may also be a client computer, a server computer, or a cloud computer. 3, the machine learning device 4 includes a control unit 111, an operation unit 112, a display unit 113, a communication unit 114, a media input / output unit 115, a RAM 116, a storage unit 117, a bus 118, etc. The various units of the machine learning device 4 are connected to each other via the bus 118.

[0037] The control unit 111 is composed of a calculation processing device (a processor such as a CPU, MPU, or DSP), and controls the operation of each part of the machine learning device 4 by reading and executing programs loaded into RAM 116 and performing various calculation processes. The control unit 111 may have multiple processors, and the various processes of the present embodiment may be executed by the multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

[0038] The operation unit 112 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The display unit 113 is configured, for example, by a liquid crystal display, an organic EL display, electronic paper, a projector, or the like, and functions as an output unit. The operation unit 112 and the display unit 113 may be integrally configured, such as a touch panel display.

[0039] The communication unit 114 is connected to the measurement device 3 via the network 7, and functions as a communication interface for transmitting and receiving various data (measurement data, etc.).

[0040] The media input / output unit 115 is composed of, for example, a DVD drive, a CD drive, a USB port, etc., and reads and writes data from and to media (non-transitory storage media) such as DVDs, CDs, and USBs.

[0041] The RAM 116 is configured from a volatile memory (DRAM, SRAM, etc.) that stores various data and programs and functions as a main memory.

[0042] The storage unit 117 is configured with a storage device such as an HDD or SSD, and stores various data required for executing the operating system and programs.

[0043] The program may be stored in the storage unit 117 instead of the RAM 116. The program may be recorded on a medium in an installable file format or an executable file format, and provided to the machine learning device 4 via the media input / output unit 115. The program may also be provided to the machine learning device 4 by downloading it via the network 7 through the communication unit 114.

[0044] The control unit 111 functions as a learning data acquisition unit 121 and a machine learning unit 122 by executing a machine learning program (not shown).

[0045] The memory unit 117 includes a learning data memory unit 123 that functions as a database for storing multiple sets of learning data acquired by the learning data acquisition unit 121, and a trained model memory unit 124 that functions as a database for storing a trained learning model 6 that has been subjected to machine learning. In this embodiment, the learning data storage unit 123 and the trained model storage unit 124 are provided in a single storage device, but they may be configured as separate storage devices.

[0046] The learning data acquisition unit 121 functions as an interface unit that acquires learning data including at least input data via the communication unit 114 and the network 7, or via the media input / output unit 115. The learning data acquisition unit 121 also acquires learning data by accepting an input operation by an operator via the operation unit 112. The input data included in the learning data is acquired by attaching each sensor (motor voltage / current sensor 101, winding heat generation state measuring sensor 102, handled liquid measuring sensor 103) as a measuring device 3 to each part of a canned motor pump 2 as a testing machine, and connecting this measuring device 3 to the machine learning device 4 via a network 7. In addition, the output data included in the learning data can be automatically acquired in association with the input data if the insulation state of the winding at the time of acquiring the input data can be identified using image analysis or the like, but it may also be acquired by operating the operation unit 112 in association with each input data.

[0047] In addition, in the case where the learning data is acquired separately and stored in an external device, the learning data acquisition unit 121 may acquire the learning data via the media input / output unit 115, or via the communication unit 114 and the network 7.

[0048] In addition, when collecting learning data from the canned motor pump 2 as a testing machine, it is preferable to use a pump having the same configuration as the actual machine for diagnosing the insulation condition of the windings as the canned motor pump 2 as the testing machine, but if it is recognized that the measurement data is not dependent on the model, a similar canned motor pump may be used, or a test device that simulates a canned motor pump may be used.

[0049] The learning data storage unit 123 is a database that stores a plurality of sets of learning data acquired by the learning data acquisition unit 121 . Therefore, the learning data stored in the learning data memory unit 123 is input data actually measured by the measurement device 3, output data input from the operation unit 112, or pre-existing learning data collected in advance that has been loaded.

[0050] The trained model storage unit 124 is a database that stores the trained learning model 6 generated by the machine learning unit 122. The trained model 6 stored in the trained model storage unit 124 is provided to the insulation condition diagnosis device 5 via an arbitrary communication network or storage medium.

[0051] The machine learning unit 122 performs machine learning using the learning data stored in the learning data storage unit 123. The machine learning unit 122 sequentially inputs a plurality of sets of learning data to the learning model 6, thereby causing the learning model 6 to learn the correlation between the input data included in the learning data and the insulation information of the winding, thereby generating a trained model. There are various methods for generating a trained model, but as a specific method of supervised learning by the machine learning unit 122, for example, a neural network may be adopted.

[0052] Here, the learning data includes, as input data, at least data on the voltage and current values ​​supplied to the motor unit 20 (motor 24), data on the temperature of the windings 31 of the stator 23 or data on the temperature, temperature difference or pressure correlated thereto, and data on the inlet temperature and flow rate of the handled liquid. The input data may include other data as well, in which case it is preferable to include data that can be collected without stopping the canned motor pump and that is correlated with the insulation state of the windings.

[0053] Also, here, an example is shown in which raw data (unprocessed data) is used as input data, such as data on the voltage and current values ​​supplied to the motor unit 20 (motor 24), data on the temperature of the windings 31 of the stator 23 or data on the temperature, temperature difference or pressure correlated therewith, and data on the inlet temperature and flow rate of the handled liquid; however, this is not limited to this, and the input data may be data in which at least a portion of the data has been preprocessed (the input data acquired by the learning data acquisition unit 121 and the input data stored in the learning data memory unit 123 may be data in which at least a portion of the data has been preprocessed). Data preprocessing includes, for example, removal of outlier points and data standardization. It also includes processes commonly performed in machine learning, such as type conversion, missing value processing (removal, interpolation), and scaling. Preprocessing may also include at least one filtering process for input data to meet a predetermined criterion.

[0054] In the case of "supervised learning," the learning data further includes, as output data (teacher data) associated with the input data, diagnostic information representing the insulation state of the windings at the time the input data was acquired, for example, diagnostic information representing which of a plurality of states the insulation state is in.

[0055] Here, the diagnostic information is information that evaluates the insulation state of the winding 31 (information that evaluates a phenomenon that determines insulation deterioration), and is, for example, (1) Information on whether or not the handled liquid is attached to the entire winding 31 (because chemical liquids and conductive liquids are often used as the handled liquid, if the can 33 is broken and the handled liquid flows into the stator chamber 45, the handled liquid will adhere to the winding 31 and induce insulation deterioration), (2) Information obtained by diagnosis based on the presence or absence of burnt / discolored winding 31, i.e., information obtained by judging the presence or absence of the phenomenon of the coil bundle being burnt in a circular shape or the coil bundle at the inlet (lead port) of winding 31 (if the winding 31 is scratched, the coil bundle will heat up and burn in a circular shape, and if a large surge voltage is applied to the supplied voltage, this will damage the winding 31 at the power inlet (lead wire side), causing the coil bundle at the winding inlet to burn), (3) Information determined from the presence or absence of voltage imbalance or the presence or absence of one-phase burnout caused by voltage imbalance (a phenomenon that can occur due to a power supply abnormality); (4) Information determined from the degree of discoloration of the entire winding 31 and the presence or absence of signs of heating (phenomenon that may occur due to overheating); etc.

[0056] When diagnosing the insulation state of the winding 31 as to whether there is an abnormality, the diagnostic information is configured as information indicating whether the insulation state is normal or abnormal. In this case, the diagnostic information may be defined as "0" when the insulation state of the winding is normal, and as "1" when the insulation state of the winding is abnormal. Furthermore, the abnormality regarding the insulation of the winding 31 may be classified into a plurality of levels according to the degree of insulation deterioration (degree of abnormality). In this case, the diagnostic information may be expressed as a multi-value, with "0" indicating that the insulation state is normal, "1" indicating that the degree of insulation deterioration is a low level abnormality, and "2" indicating that the degree of insulation deterioration is a high level abnormality. In addition, abnormalities may not only be subsequent abnormalities that are discovered at the time of diagnosis, but may also include signs of abnormalities that are within the acceptable range and are judged to be normal at the time of diagnosis, but that predict the occurrence of an abnormality in the future.

[0057] Here, we will explain the correlation between the input data included in the learning data (motor voltage and current data, winding temperature or temperature, temperature difference or pressure data correlated therewith, and inlet temperature and flow rate data of the handled liquid) and the diagnostic information on the insulation condition of the windings.

[0058] The voltage and current values ​​supplied to the motor section 20 are applied to the motor 24 from the motor control device 26 when the motor section 20 is driven to rotate, and vary according to the output of the motor 24 .

[0059] (Correlation between applied voltage and insulation state) The applied voltage value is necessary as basic information for performing various causal analyses: for example, if the voltage imbalance (imbalance of three-phase voltage) increases, the current imbalance increases accordingly, resulting in the phenomenon of only one phase burning out. Also, by measuring the voltage waveform, it is possible to check for the presence or absence of harmonic noise or surge voltage, which are factors that can cause burning out. Thus, the applied voltage can be used to monitor or predict insulation degradation.

[0060] (Correlation between current value and insulation state) The motor current is supplied from the motor control device 26 to the windings 31 of the motor section 20 when the motor is driven at a predetermined rotation speed, and therefore varies depending on the insulation state of the windings 31. For example, if the insulation of the winding 31 deteriorates excessively, the winding resistance increases and the heat generated by the motor increases. In other words, if the insulation resistance increases due to the deterioration of the winding insulation, the winding overheats, causing a phenomenon such as a layer short circuit that is thermally damaged. In addition, if there is an imbalance in the voltage values ​​between the phases of a three-phase power supply, a phenomenon occurs in which a large amount of current flows concentratedly in only one phase, causing that phase to burn out and the winding to turn black. Although the relationship between the voltage unbalance rate and the current of each phase differs depending on the number of poles and output, it has been confirmed that even if a slight voltage unbalance rate occurs, the current of each phase differs greatly. Therefore, motor current values ​​can be used to monitor or predict insulation degradation as well as coil burnout.

[0061] (Correlation between winding temperature or related temperature, temperature difference or pressure data and insulation condition) Deterioration of the winding insulation is mainly due to thermal degradation. That is, the heat generated by the winding causes the insulation to deteriorate, break down, and burn. Overheating of the winding also causes the entire winding to burn and discolor. Heat generated by the motor 24 is mainly generated in the windings 31, so monitoring the windings directly is the most preferable method for monitoring the insulation state of the windings. Moreover, the coil end housing portion, which is an enclosed space, is a portion where heat generated from the coil ends tends to be trapped and is difficult to dissipate, so the coil ends have the highest temperature among all the windings. Therefore, the temperature of the windings, particularly the temperature of the coil ends (T1: temperature of the coil end farthest from the pump, or T2: temperature of the coil end arranged on the pump side), or the temperature of the windings 31 wound around the teeth inside the stator core 30 (T3) can be used to monitor or predict the insulation state of the windings.

[0062] In addition, since the winding 31 is fixed to the stator core 30, the winding and the stator are directly thermally affected by each other. Furthermore, the heat generated in the winding 31 is transferred as radiant heat to the backup sleeves 34a, 34b, the end bells 42, 43, the bearing holders 44, 46, etc., and the surface temperatures of these vary according to the temperature of the winding 31. In this embodiment in which there is an internal circulating fluid (when there is a flow of the internal circulating fluid in the can 33 as shown by the arrows in FIG. 2), these surface temperatures also vary according to the state (amount, temperature) of the internal circulating fluid. Therefore, these temperatures that are correlated with the temperature of the windings (T4, T5: temperatures of the backup sleeves 34a, 34b, T6, T7: temperatures of the end bells 42, 43, T8, T9: temperatures of the bearing holders 44, 46) can also be used to monitor or predict the insulation state of the windings.

[0063] Furthermore, pressure P1 in stator chamber 45 (coil end accommodating portions 45a, 45b) increases with an increase in temperature of winding 31. Moreover, as winding 31 burns, organic matter gasifies, which makes it easier for the pressure in stator chamber 45 (coil end accommodating portions 45a, 45b) to increase. For this reason, if the correlation between the temperature of winding 31 and the pressure in stator chamber 45 is accurate within an acceptable range, the pressure in stator chamber 45 can also be used to monitor or predict the insulation state of the winding. In addition, by also measuring the pressure P2 in the rotor chamber 50 and monitoring the difference (ΔP) between this and the pressure P1 in the stator chamber 45, it is possible to detect a break in the can 33 (P1=P2), and by extension, a malfunction of the motor.

[0064] In this way, in order to monitor or predict the insulation state of the windings, any one of the following may be used: winding temperature; a temperature correlated with the winding temperature (e.g., the temperature of the stator core, the temperature of the stator chamber, the surface temperatures of the backup sleeves 34a, 34b, or the surface temperatures of the end bells 42, 43); a temperature difference (e.g., the temperature difference of the windings of each phase, the difference (Δt) between the temperature of each phase of the winding and the temperature of the handling liquid, or the difference (T5-T4) between the temperatures T4, T5 of the front and rear backup sleeves 34a, 34b) or a pressure correlated with the winding temperature (e.g., the pressure in the stator chamber 45); however, more than one may be used as necessary. In this embodiment, a case in which any one of the following is used will be described.

[0065] (Correlation between the inlet temperature and flow rate data of the handled liquid and the insulation condition) In the canned motor pump 2, the can 33 is in contact with the inner peripheral surface of the stator core 30, so the temperature of the stator 23 is predominantly affected by the temperature of the handled liquid. That is, heat transfer occurs between the stator 23 and the handled liquid via the can 33, which is thin and has high thermal conductivity, so the temperature of the stator 23 is significantly affected by the inflow temperature and flow rate of the handled liquid. For example, when the temperature of the handled liquid increases, the temperature of the stator core 30 also increases, and the windings 31 become even more self-heated and reach a higher temperature than the handled liquid. For this reason, in the canned motor pump 2, which often handles high-temperature handled liquid, the windings 31 are easily exposed to high-temperature atmospheres that are prone to insulation deterioration. Thus, the flow rate and temperature of the handled liquid are important in monitoring or predicting the insulation condition, since they are the base temperatures for evaluating the insulation condition of the windings.

[0066] The data on motor voltage and current, the temperature of windings 31 of motor section 20 or data on temperatures, temperature differences or pressures correlated therewith, and the inlet temperature and flow rate of the handled liquid have effects on the insulation state as described above, but the insulation state of the windings changes in a complex manner as a result of the overall interaction of these data. For this reason, it is difficult to properly judge the insulation state by judging the above data individually, and in order to properly judge the insulation state of the windings, which changes in a complex manner, it is necessary to take the above data into consideration in its entirety.

[0067] Also, as shown in FIG. 2, even in a canned motor pump 2 in which the motor section 20 is not equipped with a cooling device, the heat generated in the windings 31 of the motor section 20 is released to the atmosphere via the motor housing 25 (outer tube 41, end bells 42, 43 at both ends, and bearing holder 44), and if the temperature becomes higher than that of the handled liquid, it is also released to the handled liquid via the can 33. However, if there are no significant changes in the operating conditions of the canned motor pump 2 used in the plant and the heat dissipation conditions are stable, the heat balance of the canned motor pump can be captured simply, and by using data collected at a specific time under specific conditions (data on the voltage and current values ​​supplied to the motor section 20, data on the temperature of the stator winding or temperatures, temperature differences or pressures correlated therewith, and data on the inlet temperature and flow rate of the handled liquid) as input data for learning data, it is possible to grasp the trend in the insulation condition of the winding 31.

[0068] On the other hand, when the data on the voltage and current values ​​supplied to the motor section 20, the temperature of the windings 31 of the stator 23 or data on the temperature, temperature difference or pressure correlated therewith, and the inflow temperature and flow rate of the handled liquid fluctuate frequently, and the amount of heat dissipated into the atmosphere also fluctuates considerably due to fluctuations in atmospheric temperature, and it is considered that these have a complex effect on the insulation state of the windings 31, then pinpointing the input data (input data at a specified timing) will result in poor correlation accuracy, and in such cases it is advisable to use time-dependent data over a specified period of time for each input data of the learning data. That is, data on the voltage and current values ​​supplied to the motor unit during a predetermined period, data on the temperature of the stator winding or a temperature, temperature difference, or pressure correlated therewith during a predetermined period, and data on the inflow temperature and flow rate of the handled liquid during a predetermined period may be used as input data. In the case of "supervised learning," the insulation state of the winding over time during a predetermined period may also be used as output data (supervised data) associated with the input data.

[0069] Here, the input data and output data for a given period of time are composed of a plurality of measurement values ​​measured by each sensor at a plurality of measurement points within the given period of time. For example, each measurement data is measured at a given sampling period within the given period of time, associated with the measurement time, and composed as sequence data arranged in chronological order.

[0070] (Machine learning methods) When the machine learning device 4 performs "supervised learning" as machine learning, it forms a learning model using, for example, a neural network model. This neural network model is a well-known model, and learns the correlation between the input data and the output data by inputting input data included in the learning data to an input layer and comparing the output data output from the output layer as the inference result with the output data (supervisor data) included in the learning data.

[0071] First, as a preparation for having the machine learning device 4 perform machine learning, the learning data acquisition unit 121 acquires a desired number of learning data and stores the acquired multiple sets of learning data in the learning data storage unit 123. The number of learning data prepared here is appropriately set in consideration of the inference accuracy required for the learning model 6.

[0072] Various methods can be used to acquire the learning data. For example, when an abnormality occurs in the insulation state of the windings 31, or when a symptom of an abnormality is recognized, the measurement value at that time or for a predetermined period before and after that time is acquired from each sensor by the measuring device 3. Also, in association with the acquired measurement value, a diagnosis result (in this case, an abnormality occurs or a symptom of an abnormality is recognized, so the output data is "1") is input from the operation unit 112, and in this way, one set of learning data (input data and output data) is prepared, and this is repeated to prepare multiple sets of learning data.

[0073] Since insulation deterioration may occur over a long period of time or may occur all at once, when the occurrence of an abnormality or a symptom of an abnormality is difficult to detect, learning data may be acquired by intentionally causing an abnormal insulation state. In addition, multiple sets of input data and output data in a normal state where no abnormality has occurred in the insulation state are also prepared as learning data.

[0074] Furthermore, to start machine learning, a pre-learning learning model 6 composed of a neural network model is prepared. The input layer of this learning model 6 is associated with data on motor voltage and current values ​​as input data contained in the learning data, data on the temperature of the stator windings 31 or a temperature, temperature difference, or pressure correlated therewith, and data on the inflow temperature and flow rate of the handled liquid, while the output layer is associated with diagnostic information (insulation state) as output data contained in the learning data. After the above-mentioned preparations, the machine learning unit 122 performs, for example, a series of processes in the flowchart shown in FIG. 4 to generate a trained model. In step S100, the machine learning unit 122 acquires one set of learning data from the multiple sets of learning data stored in the learning data storage unit 123. The learning data may be acquired in a predetermined order or randomly.

[0075] Next, in step S110, the machine learning unit 122 performs supervised machine learning. That is, the machine learning unit 122 inputs input data included in the acquired set of learning data to the prepared learning model, outputs an inference result, compares this inference result with output data (teacher data) included in the learning data acquired in step S100, and performs machine learning using a known neural network method. In this way, the machine learning unit 122 causes the learning model 6 to learn the correlation between the input data and the output data (diagnosis information on the insulation state of the winding).

[0076] Thereafter, using this learning model under learning, the above-mentioned operations are performed on the remaining prepared learning data, and learning is continued in the machine learning unit 122. At this time, the machine learning unit 122 determines whether or not to continue machine learning based on the error between the output data and the teacher data, the number of learning attempts, or the remaining amount of unlearned learning data stored in the learning data storage unit 123 (step S120).

[0077] That is, if the machine learning unit 122 determines in step S120 to continue machine learning (YES), it performs steps S100 to S110 on the learning model 6 being trained using untrained learning data. On the other hand, if the machine learning unit 122 determines in step S120 not to continue machine learning (NO), it stores the generated trained learning model 6 in the trained model storage unit 124 in step S130 and ends the machine learning.

[0078] (Effects of the Machine Learning Device and Machine Learning Method According to the First Embodiment) According to the machine learning device 4 and machine learning method of the above-described first embodiment, it is possible to provide a learning model 6 that can accurately infer (diagnose) diagnostic information for the insulation state of the windings 31 from data on the voltage and current values ​​supplied to the motor section 20, data on the temperature of the windings 31 of the stator 23 or a temperature, temperature difference or pressure correlated therewith, and data on the inflow temperature and flow rate of the handled liquid.

[0079] (Insulation condition diagnostic device) Next, an insulation state diagnosis device 5 that infers (diagnoses) the insulation state of the winding 31 using a trained learning model 6 generated using the above-mentioned technique will be described. The insulation condition diagnostic device 5 is configured with a general-purpose or dedicated computer. This computer may be a stationary computer or a portable computer, and may also be a client computer, a server computer, or a cloud computer. Furthermore, the insulation state diagnosis device 5 may be incorporated in the motor control device 26 or in a higher-level management device of the motor control device 26. Furthermore, the computer constituting the insulation state diagnosis device 5 may be the same as or different from the computer constituting the machine learning device 4.

[0080] 5, the insulation condition diagnosis device 5 includes a control unit 131, an operation unit 132, a display unit 133, a communication unit 134, a media input / output unit 135, a RAM 136, a storage unit 137, and a bus 138. The components of the insulation condition diagnosis device 5 are connected to each other via the bus 138.

[0081] The control unit 131 is composed of an arithmetic processing device (a processor such as a CPU, MPU, or DSP), and controls the operation of each part of the insulation condition diagnosis device 5 by reading and executing programs loaded into the RAM 136 and performing various arithmetic processing. The control unit 131 may have multiple processors, and the various processes of the present embodiment may be executed by the multiple processors. In this case, the multiple processors may be involved in a common process, or the multiple processors may independently execute different processes in parallel.

[0082] The operation unit 132 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The display unit 133 is configured, for example, by a liquid crystal display, an organic EL display, electronic paper, a projector, or the like, and functions as an output unit. The operation unit 132 and the display unit 133 may be integrally configured, such as a touch panel display.

[0083] The communication unit 134 is connected to the measurement device 3 via the network 7, and functions as a communication interface for transmitting and receiving various data (measurement data, etc.).

[0084] The media input / output unit 135 is composed of, for example, a DVD drive, a CD drive, a USB port, etc., and reads and writes data from and to media (non-transitory storage media) such as DVDs, CDs, and USBs.

[0085] The RAM 136 is configured from a volatile memory (DRAM, SRAM, etc.) that stores various data and programs and functions as a main memory.

[0086] The storage unit 137 is configured with a storage device such as an HDD or SSD, and stores various data required for executing the operating system and programs.

[0087] The program may be stored in the storage unit 137 instead of the RAM 136. The program may be recorded on a medium in an installable file format or an executable file format, and provided to the insulation condition diagnosis device 5 via the media input / output unit 135. The program may also be provided to the insulation condition diagnosis device 5 by downloading it via the communication unit 134 over the network 7.

[0088] The control unit 131 functions as an input data acquisition unit 141, an inference unit 142, and an output processing unit 143 by executing an insulation state diagnosis program (not shown). The storage unit 137 also includes a trained model storage unit 144 that functions as a database for storing the trained learning model 6 that has been machine-learned.

[0089] The input data acquisition unit 141 is an interface unit that is connected to the measuring devices 3 (motor voltage / current sensor 101, winding heat generation state measurement sensor 102, handled liquid measurement sensor 103) provided in the actual canned motor pump 2 via the communication unit 134 and the network 7, and acquires input data based on the measured values ​​measured by the measuring devices 3 (motor voltage and current data at a specified timing, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated thereto, and data on the inflow temperature and flow rate of the handled liquid, or motor voltage and current data for a specified period, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated thereto, and data on the inflow temperature and flow rate of the handled liquid).

[0090] In this example, the input data is shown to be raw data (unprocessed data) of the voltage and current values ​​supplied to the motor unit 20 (motor 24), the temperature of the windings 31 of the stator 23 or a temperature, temperature difference or pressure correlated thereto, and the inlet temperature and flow rate of the handled liquid. However, in accordance with the learning data, the input data may be data that has been preprocessed on at least a portion of the voltage and current values ​​supplied to the motor unit 20 (motor 24), the temperature of the windings 31 of the stator 23 or a temperature, temperature difference or pressure correlated thereto, and the inlet temperature and flow rate of the handled liquid.

[0091] The inference unit 142 inputs the input data acquired by the input data acquisition unit 141 to the learning model 6, and performs an inference process to infer diagnostic information about the insulation state of the windings 31. For the inference process, a trained learning model 6 that has been generated by the machine learning device 4 and has undergone supervised learning is used.

[0092] The inference unit 142 may not only have the function of performing inference processing using the learning model 6, but may also have a preprocessing function of adjusting the input data acquired by the input data acquisition unit 141 into a desired format, etc., and inputting it to the learning model 6 as preprocessing of the inference processing, and a postprocessing function of finally diagnosing the insulation state of the winding 31 by applying a predetermined logical formula or calculation formula to the value of the output data output from the learning model 6 as postprocessing of the inference processing.

[0093] The trained model storage unit 144 is a database that stores trained learning models 6 used in the inference process of the inference unit 142. The number of learning models 6 stored in the trained model storage unit 144 is not limited to one. For example, multiple learning models 6 for different input data, different numbers of input data, or different machine learning techniques may be stored and appropriately selected for use.

[0094] An example of a case where the input data is different is when, in place of the stator winding temperature, data on temperature, temperature difference, or pressure that is correlated with the stator winding temperature is used in a learning model that uses data on motor voltage and current values, the stator winding temperature, and data on the inlet temperature and flow rate of the handled liquid.An example of a case where the number of input data is different is when data that affects the amount of heat dissipation is added to the heat balance model of the motor section (this will be described later).

[0095] The output processing unit 143 performs output processing to output the inference result of the inference unit 142, i.e., diagnostic information on the insulation state of the windings 31. As specific output means, various means can be adopted. For example, the output processing unit 143 may notify the operator of the diagnostic information by display or email, transmit the diagnostic information to the motor control device 26 or a higher-level management device and store it as a diagnostic history of the canned motor pump 2, or use it for drive control of the motor unit 20 and the pump unit 10.

[0096] (Insulation condition diagnosis method) 6 is a flowchart showing an example of an insulation state diagnosis method using the insulation state diagnosis device 5. In this example, a case will be described in which the insulation state diagnosis information is defined as either "0" if normal or "1" if abnormal. First, in step S200, the input data acquisition unit 141 acquires input data (motor voltage and current data at a specified timing, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated thereto, and data on the inflow temperature and flow rate of the handled liquid, or motor voltage and current data for a specified period of time, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated thereto, and data on the inflow temperature and flow rate of the handled liquid) based on measurements measured by the measuring devices 3 (motor voltage / current sensor 101, winding heat generation state measurement sensor 102, handled liquid measurement sensor 103).

[0097] Next, in step S210, the inference unit 142 inputs the input data to the input layer of the trained learning model 6 and performs inference. Thereafter, in step 220, the inference unit 142 judges whether or not there is an abnormality in the insulation state based on the inference result. That is, as an example of post-processing of supervised learning, the inference unit 142 compares the value of the output data (a number between 0 and 1) with a predetermined threshold value to judge whether it is normal or abnormal. For example, if the value of the output data is less than the predetermined threshold value, the insulation state is judged to be "normal" (NO), and if the value is equal to or greater than the predetermined threshold value, the insulation state is judged to be "abnormal" (YES).

[0098] Next, if the inference result of the inference unit 152 in step 220 (diagnosis result of the insulation state of the winding) is no abnormality (NO), the output processing unit 154 outputs information indicating "normal" in step S230, and if the inference result is abnormal (YES), the output processing unit 154 outputs information indicating "abnormal" in step 240 (step S240). After the diagnostic information is output in step S230 or S240, the process of diagnosing the insulation state of the winding is terminated.

[0099] (Effects of the insulation condition diagnosis device and insulation condition diagnosis method according to the first embodiment) According to the insulation condition diagnosis device 5 and the insulation condition diagnosis method of the first embodiment described above, it is possible to diagnose the insulation condition of the winding 31 with high accuracy without relying on the experience or intuition of an operator and without stopping the canned motor pump 2. That is, in order to properly judge the insulation condition under complicatedly changing conditions, since it is not possible to properly judge by monitoring each input data individually, conventionally, the canned motor pump is stopped to measure the insulation resistance and the resistance between terminals and manage the trend, which is largely dependent on the experience and intuition of the operator. However, with this diagnosis device, by using a learning model generated from input data such as data on the voltage and current values ​​supplied to the motor unit, the temperature of the winding or a temperature correlated therewith, data on the temperature difference or pressure, and data on the inflow temperature and flow rate of the handled liquid, it becomes possible to accurately diagnose the insulation condition of the winding without relying on the experience and intuition of a skilled worker, even when the insulation condition of the winding changes due to various influences.

[0100] In the above examples, changes in the amount of heat dissipation were not actively taken into account when considering the heat balance that affects the insulation state of the windings of the canned motor pump. However, when a cooling device is provided in the motor section 20, changes in the amount of heat dissipation cannot be ignored.

[0101] 7 shows an example of a canned motor pump equipped with a cooling device 70 in the motor section 20. In this example, a cooling jacket 71 is arranged around the motor section 20, i.e., on the outside of the outer casing 41. This cooling jacket 71 is formed by the outer casing 41, a jacket outer periphery 71a arranged outside the outer casing 41, and two end plates 71b arranged on both ends of the jacket outer periphery 71a. A cooling pipe 72 is arranged inside the cooling jacket 71, and the space other than the cooling pipe is filled with a heat transfer medium. Here, for example, oil, silica, aluminum powder, etc. are used as the heat transfer medium.

[0102] The cooling liquid supplied to the cooling pipe 72 in the cooling jacket 71 may be appropriately selected from a cooling liquid in a system separate from the handled liquid of the pump section 10, or the handled liquid flowing through the pump section 10 may be supplied. When the handled liquid flowing through the pump section 10 is supplied, the handled liquid is sent to the rotor chamber 50 after passing through the cooling pipe 72. Other configurations of the canned motor pump 2 are similar to those shown in FIG. 2, so the same parts are given the same reference numerals and the description thereof will be omitted.

[0103] When such a cooling device 70 is provided, the standard conditions to which the windings 31 are exposed change depending on the temperature and flow rate of the cooling liquid. Therefore, when such a cooling device 70 is provided, a coolant measurement sensor 104 is provided in the pipe 73 that supplies the cooling liquid to the cooling jacket 71 to measure the inlet temperature and flow rate of the coolant. The coolant measurement sensor 104 is composed of, for example, an inflow temperature sensor 104a and a flow rate sensor 104b provided in a pipe that supplies coolant to the cooling jacket 71. The inflow temperature sensor 104a and the flow rate sensor 104b may be the same type as the inflow temperature sensor 103a and the flow rate sensor 103b of the treated liquid measurement sensor 103.

[0104] 8, the inlet temperature and flow rate of the coolant measured by the coolant measurement sensor 104 may be added as data measured by the measuring device 3 used in the machine learning device 4 and the insulation condition diagnosis device 5. That is, the inlet temperature and flow rate of the coolant may be included in the input data included in the learning data in the learning phase, and the inlet temperature and flow rate of the coolant may be included in the input data for diagnosis in the inference phase. Even in this case, the inlet temperature and flow rate of the coolant used as input data are not limited to raw data (unprocessed data) obtained by the inlet temperature sensor 103a and the flow rate sensor 103b, and preprocessed data may be used. Furthermore, the data on the temperature and flow rate of the coolant may be data at a predetermined timing, or data for a predetermined period of time may be used to improve correlation accuracy and inference accuracy. Therefore, when the motor section 20 is equipped with a cooling device 70, by further taking into account the inflow temperature and flow rate of the coolant in the learning phase and inference phase, it is possible to more accurately infer (diagnose) the insulation condition of the windings 31.

[0105] Second embodiment In the above first embodiment, a case where "supervised learning" is adopted as machine learning has been described, but in this embodiment, a case where "unsupervised learning" is adopted will be described. Note that the basic configurations and operations of the measuring device 3, the machine learning device 4, and the insulation state diagnosis device 5 constituting the insulation state diagnosis system 1 for the canned motor pump 2 and the windings 31 according to the second embodiment are the same as those in the first embodiment, so descriptions will be omitted and the following description will focus on the differences from the first embodiment.

[0106] As in the first embodiment, the machine learning device 4 includes a learning data acquisition unit 121, a learning data storage unit 123, a machine learning unit 122, and a trained model storage unit 124, as shown in FIG. When "unsupervised learning" is adopted as the machine learning, the learning data uses only the input data when the diagnostic information indicates that the insulation state of the windings at a predetermined timing or during a predetermined period of time is in a predetermined state. In other words, the learning data does not include output data (teaching data).

[0107] When diagnosing the insulation state of the windings 31 for the presence or absence of an abnormality, the diagnostic information is configured as information indicating whether the insulation state is normal or abnormal. Here, it is configured only with input data when the insulation state of the windings is normal (data on the voltage and current values ​​supplied to the motor unit, data on the temperature of the stator windings or temperatures, temperature differences or pressures correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and, if a cooling device is provided, the inlet temperature and flow rate of the cooling liquid).

[0108] When acquiring the above-mentioned learning data, the learning data acquiring unit 121 acquires as input data the data of the voltage value and current value supplied to the motor unit at a predetermined timing or during a predetermined period, the temperature of the stator winding or a temperature, temperature difference or pressure data correlated therewith, the inlet temperature and flow rate data of the handled liquid, and the inlet temperature and flow rate data of the cooling liquid if a cooling device is provided, all of which are measured by the measuring device 3 provided in the canned motor pump 2 as a tester. At the same time, the operator diagnoses the insulation state at the timing or during the predetermined period when the input data is measured, and inputs from the operation unit 112 that the diagnosis result is normal, thereby forming a set of learning data and storing it in the learning data storage unit 123. By repeating such operations, a plurality of sets of learning data are stored in the learning data storage unit 123.

[0109] Even in this case, the learning data acquisition unit 121 may collect the input data contained in the learning data by attaching each sensor (motor voltage / current sensor 101, winding heat generation state measurement sensor 102, handled liquid measurement sensor 103) as a measuring device 3 to each part of the canned motor pump 2 as a testing machine and connecting this measuring device 3 to the machine learning device 4 via the network 7, or if the collected learning data (motor voltage / current value data as input data, winding temperature or temperature, temperature difference or pressure data correlated therewith, and handled liquid inflow temperature and flow rate data) already exists, the learning data acquisition unit 121 may load the existing learning data into the learning data memory unit 123 via the media input / output unit 115, the communication unit 114, and the network 7. Also in this embodiment, the input data is not limited to raw data (unprocessed data), and data that has been subjected to the same preprocessing as described above on at least a portion of the data may be used.

[0110] The machine learning unit 122 inputs the learning data to the learning model, thereby making the learning model learn the correlation between the input data included in the learning data and the diagnostic information indicating that the insulation state of the winding is normal, and generates a trained model. As a method of unsupervised learning by the machine learning unit, for example, an autoencoder model may be adopted.

[0111] This autoencoder model is a well-known model that learns patterns and trends in the input data by inputting input data contained in the training data to the input layer and comparing this input data with output data output from the output layer as an inference result. This series of steps is repeatedly performed on the training model, and when a predetermined training end condition is met, the machine learning is terminated and a trained autoencoder model is generated.

[0112] FIG. 9 shows a flowchart of an example of a machine learning method using the machine learning device according to the second embodiment. Also in this example, as a preparation before the machine learning device 4 performs machine learning, the learning data acquisition unit 121 acquires a desired number of learning data and stores the acquired multiple sets of learning data in the learning data storage unit 123. The number of learning data prepared here is appropriately set in consideration of the inference accuracy required for the learning model 6.

[0113] Various methods can be used to acquire the learning data, but for example, input data constituting the learning data is prepared by acquiring various measured values ​​at a predetermined timing or for a predetermined period of time when the insulation state of the windings 31 in the canned motor pump 2 serving as a testing machine is normal, using the measuring device 3. Then, by repeating such an operation, multiple sets of learning data are prepared.

[0114] In addition, to start machine learning, a pre-learning learning model 6 composed of an autoencoder model is prepared. In the input layer of this learning model 6, data on the voltage and current values ​​supplied to the motor unit as input data included in the learning data, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated therewith, and data on the inlet temperature and flow rate of the handled liquid are associated with each other, and in the case where a cooling device is provided, data on the inlet temperature and flow rate of the cooling liquid are further associated with the input data.

[0115] After the advance preparation is completed, first, in step S300, the machine learning unit 122 acquires one set of learning data from the multiple sets of learning data stored in the learning data storage unit 123. The learning data may be acquired in a predetermined order or randomly.

[0116] Next, in step S310, the machine learning unit 122 performs unsupervised machine learning. That is, the machine learning unit 122 inputs input data included in the acquired set of learning data to a prepared learning model, causes the model to output an inference result, compares the input data included in the learning data with output data output from the output layer as an inference result, and performs machine learning using a known autoencoder technique.

[0117] Thereafter, using this learning model under learning, the above-mentioned operations are performed on the remaining prepared learning data, and learning is continued in the machine learning unit 122. At this time, the machine learning unit 122 determines whether or not to continue machine learning based on the number of learning times, the remaining amount of unlearned learning data stored in the learning data storage unit 123, and the like (step S320). That is, if the machine learning unit 122 determines in step S320 to continue machine learning (YES), it performs steps S300 to S310 on the currently-learned learning model 6 using unlearned learning data. On the other hand, if the machine learning unit 122 determines in step S320 not to continue machine learning (NO), in step S330, the machine learning unit 122 stores the generated trained learning model 6 in the trained model storage unit 124 and ends the machine learning.

[0118] (Effects of the Machine Learning Device and Machine Learning Method According to the Second Embodiment) By using the machine learning device and machine learning method according to the second embodiment described above, it is possible to provide a learning model 6 that can infer (estimate) diagnostic information on the insulation state of the winding with high accuracy from data on motor voltage and current values ​​at a specified timing, data on the temperature of the stator winding or a temperature, temperature difference, or pressure correlated therewith, and data on the inflow temperature and flow rate of the handled liquid, or data on motor voltage and current values ​​for a specified period, data on the temperature of the stator winding or a temperature, temperature difference, or pressure correlated therewith, and data on the inflow temperature and flow rate of the handled liquid.

[0119] The insulation state diagnosis device 5 in this embodiment has the same configuration as that in the first embodiment in Fig. 5. That is, the insulation state diagnosis device 5 has an input data acquisition unit 141, an inference unit 142, an output processing unit 143, and a trained model storage unit 144. As in the first embodiment, the inference unit 152 inputs the input data acquired by the input data acquisition unit 141 into the trained learning model 6 and performs inference processing to infer diagnostic information about the insulation state of the windings. For the inference processing, the trained model on which unsupervised learning has been performed by the machine learning device 4 is used.

[0120] 10 is a flowchart showing an example of a method for diagnosing the insulation state of the winding 31 by the insulation state diagnosis device 5 according to the second embodiment. In this example, a case will be described in which the diagnosis information of the insulation state is defined as either "0" if normal or "1" if abnormal.

[0121] First, in step S400, the input data acquisition unit 141 acquires input data (motor voltage and current data at a specified timing or for a specified period of time, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and, if a cooling device is present, data on the inlet temperature and flow rate of the coolant) based on measurements measured by the measuring devices 3 (motor voltage / current sensor 101, winding heat generation state measurement sensor 102, handled liquid measurement sensor 103, and, if a cooling device is present, coolant measurement sensor 104). Here too, the input data may be partially pre-processed.

[0122] Next, in step S410, the inference unit 142 inputs input data to the input layer of the learning model 6 to perform inference, and obtains output data output from the output layer of the learning model 6.

[0123] Then, in step S420, the inference unit 142 determines whether or not there is an abnormality in the insulation state based on the inference result. That is, as an example of post-processing of unsupervised learning, the inference unit 142 obtains the difference between the feature amount based on the input data and the feature amount based on the output data, and if the difference is less than a predetermined threshold, it determines that the insulation state is "normal" (NO), and if the difference is equal to or greater than the predetermined threshold, it determines that the insulation state is "abnormal" (YES).

[0124] Next, in step S430, if output processing unit 154 determines that the diagnostic information on the insulation state of the winding, which is the inference result of inference unit 152, is normal (NO), it outputs information indicating "normal" (step S430), and if it determines that the diagnostic information is "abnormal" (YES), it outputs information indicating "abnormal" (step S440). After the diagnosis information is output in step S430 or S440, the process of diagnosing the insulation state of the winding is terminated.

[0125] (Effects of the insulation condition diagnosis device and insulation condition diagnosis method according to the second embodiment) The insulation condition diagnosis device 5 and insulation condition diagnosis method according to the second embodiment described above also make it possible to diagnose the insulation condition of the windings with high accuracy without relying on the experience or intuition of an operator and without stopping the canned motor pump 2.

[0126] (Other embodiments) In the above-described embodiment, the case where a neural network (first embodiment) and an autoencoder (second embodiment) are adopted as specific methods of machine learning by the machine learning unit 122 has been described, but the machine learning unit 122 may adopt any other machine learning method. For example, tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, neural network types (including deep learning) such as recurrent neural networks and convolutional neural networks, clustering types such as hierarchical clustering, non-hierarchical clustering, k-nearest neighbors and k-means, multivariate analysis such as principal component analysis, factor analysis, and logistic regression, support vector machines, etc. may be adopted.

[0127] In addition, the above-mentioned machine learning device 4 and insulation status diagnosis device 5 can also be provided in the form of a program (machine learning program or insulation status diagnosis program) for executing each step of the above-mentioned machine learning method or insulation status diagnosis method.

[0128] In the above example, the measurement data of each sensor at a predetermined timing or for a predetermined period of time is used as input data for learning data as data on the temperature of winding 31 of stator 23 or data on temperature, temperature difference, or pressure correlated therewith, but the input data may appropriately be data on a temperature difference correlated with the temperature of winding 31. For example, even if the voltage and current values ​​supplied to motor unit 20 are constant, if the winding resistance values ​​of each phase become unbalanced due to insulation deterioration, variations in the temperatures of the windings of each phase will occur, and therefore data on the temperature difference of the windings of each phase may be used. Furthermore, as temperature difference data correlated with the temperature of the windings 31, the difference (Δt) between the temperature of each phase of the windings and the temperature of the handled liquid, or the difference (T5-T4) between the temperatures T4, T5 of the front and rear backup sleeves 34a, 34b can be monitored to detect abnormal heat generation in the motor (windings 31), and therefore these temperature difference data may be used as input data.

[0129] (Embodiments of the invention) Next, the embodiments of the present invention that can be understood from the above-described embodiments will be described below, using the terms and symbols described in the respective embodiments.

[0130] A first embodiment of the present invention includes a motor section (e.g., motor section 20) and a pump section (e.g., pump section 10) driven by the motor section, The motor unit includes a rotor (e.g., rotor 22) rotatable about a shaft (e.g., shaft 21), a stator (e.g., stator 23) facing the rotor with a gap therebetween, and a cylindrical can (e.g., can 33) that defines a rotor chamber (e.g., rotor chamber 50) for accommodating the rotor on the inside and a stator chamber (e.g., stator chamber 45) for accommodating the stator together with a motor housing (e.g., motor housing 25) on the outside, A machine learning device (e.g., machine learning device 4) that generates a learning model (e.g., learning model 6) to be used in an insulation state diagnosis device (e.g., insulation state diagnosis device 5) for diagnosing an insulation state of a winding (e.g., winding 31) of a stator used in a canned motor pump (e.g., canned motor pump 2) that circulates a portion of a handled liquid in the pump section to the rotor chamber, a learning data acquisition unit (e.g., learning data acquisition unit 121) that acquires a plurality of sets of learning data including, as input data, unprocessed data or data that has been at least partially preprocessed, such as data on voltage and current values ​​supplied to the motor unit, data on the temperature of the stator windings (e.g., the windings 31 and the coil ends 31a and 31b) or temperatures correlated therewith (e.g., the temperatures of the stator core 30, the backup sleeves 34a and 34b, the end bells 42 and 43, or the bearing holders 44 and 46), data on temperature differences (e.g., the temperature differences of the windings of each phase, the difference (Δt) between the temperature of each phase of the windings and the temperature of the handled liquid, or the difference (T5-T4) between the temperatures T4 and T5 of the front and rear backup sleeves 34a and 34b) or data on pressure (e.g., the pressure of the stator chamber 45 or the coil end housing portions 45a and 45b), and data on the inflow temperature and flow rate of the handled liquid; a machine learning unit (e.g., the machine learning unit 122) that inputs the learning data into the learning model to cause the learning model to learn a correlation between the input data and diagnostic information on the insulation state of the winding; and a trained model storage unit (e.g., trained model storage unit 124) that stores the learning model trained by the machine learning unit." It is a machine learning device. This configuration makes it possible to provide a learning model that can infer (estimate) diagnosis information for the motor section's winding insulation with high accuracy from unprocessed data or data that has been at least partially preprocessed, such as data on the voltage and current values ​​supplied to the motor section of the canned motor pump, data on the temperature of the stator winding of the motor section or data on the temperature, temperature difference, or pressure correlated therewith, and data on the inlet temperature and flow rate of the handled liquid in the pump section.It is also possible to provide a learning model that can accurately diagnose the insulation state of the windings without stopping the canned motor pump.

[0131] A second embodiment of the present invention is a machine learning device in which, in the first embodiment, a cooling jacket (e.g., cooling jacket 71) is further provided on at least a part of the motor housing of the motor section, and the input data is data on the inlet temperature and flow rate of the coolant supplied into the cooling jacket, and further includes unprocessed data or data that has been preprocessed at least in part. According to this configuration, in addition to the input data of the first embodiment, data on the inlet temperature and flow rate of the coolant is further added as input data contained in the learning data, and unprocessed data or data that has been at least partially preprocessed is further added, thereby providing a learning model that can infer (estimate) diagnostic information for the winding insulation of the motor section with higher accuracy.

[0132] A third embodiment of the present invention is a machine learning device in which, in the first embodiment, data on voltage and current values ​​supplied to a motor unit is data supplied to the motor unit over a predetermined period of time, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated therewith is data over the predetermined period of time, and data on the inlet temperature and flow rate of the handled liquid is data over the predetermined period of time. According to this configuration, since data for a predetermined period is used as the input data used in the first embodiment, it is possible to improve the accuracy of the correlation of the learning data.

[0133] A fourth embodiment of the present invention is a machine learning device in which, in the second embodiment, data on voltage and current values ​​supplied to the motor unit is data supplied to the motor unit during a predetermined period, data on the temperature of the stator winding or a temperature, temperature difference or pressure correlated therewith is data during the predetermined period, data on the inlet temperature and flow rate of the handled liquid is data during the predetermined period, and data on the inlet temperature and flow rate of the cooling liquid supplied into the cooling jacket is data during the predetermined period. According to this configuration, since data for a predetermined period is used as the input data used in the second embodiment, it is possible to improve the accuracy of the correlation of the learning data.

[0134] A fifth embodiment of the present invention is a machine learning device in which, in any one of the first to fourth embodiments, the learning data is associated with the input data and further includes, as output data, the diagnostic information indicating that the insulation state of the winding is one of a plurality of states, and the machine learning unit causes the learning model to learn the correlation between the input data and the output data through supervised learning. According to this configuration, a learning model can be generated that learns the correlation between the input data and the diagnostic information on the insulation state of the winding through supervised learning.

[0135] A sixth embodiment of the present invention is a machine learning device in which, in any one of embodiments 1 to 4, the learning data includes only input data when the diagnostic information indicates that the insulation state of the winding is in a predetermined state, and the machine learning unit causes the learning model to learn the correlation between the input data and the diagnostic information indicating that the insulation state of the winding is in the predetermined state by unsupervised learning. According to this configuration, a learning model can be generated that learns the correlation between the input data and the diagnostic information on the insulation state of the windings through unsupervised learning.

[0136] A seventh embodiment of the present invention is an insulation state diagnosis device (for example, insulation state diagnosis device 5) for diagnosing an insulation state of a winding of a stator used in the canned motor pump by using a learning model generated by the machine learning device in any one of the first to sixth embodiments, an input data acquisition unit (e.g., an input data acquisition unit 141) that acquires input data including unprocessed data or data that has been at least partially preprocessed, such as data on a voltage value and a current value supplied to the motor unit, data on the temperature of the winding of the stator or a temperature, a temperature difference, or a pressure correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and data on the inlet temperature and flow rate of a cooling liquid as necessary; an inference unit (e.g., an inference unit 142) that inputs the input data acquired by the input data acquisition unit into the learning model and infers diagnostic information of an insulation state of the stator winding; The insulation condition diagnostic device is provided with: According to this configuration, diagnostic information for the insulation condition of the stator windings can be inferred using input data including unprocessed data or data that has been at least partially preprocessed, such as data on the voltage and current values ​​supplied to the motor unit, data on the temperature of the stator windings or data on temperatures, temperature differences, or pressures correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and, if necessary, data on the inlet temperature and flow rate of the cooling liquid.This makes it possible to diagnose the insulation condition of the windings with high accuracy, without stopping the plant.

[0137] An eighth embodiment of the present invention provides a pump having a motor section and a pump section driven by the motor section, the motor unit includes a rotor rotatable about a shaft, a stator facing the rotor with a gap therebetween, and a cylindrical can that defines a rotor chamber for accommodating the rotor on the inside and a stator chamber for accommodating the stator together with a motor housing on the outside, A machine learning method for learning a learning model used in an insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump that circulates a part of a pumped liquid in the pump section to the rotor chamber, comprising: a learning data acquisition step (e.g., steps S100 and S300) in which input data is unprocessed data or data that has been at least partially preprocessed, the data being data on voltage and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on temperatures, temperature differences, or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid, and the input data is used to acquire a plurality of sets of learning data including at least this input data; a machine learning process (e.g., steps S110 and S310) of inputting the learning data into the learning model to allow the learning model to learn a correlation between the input data and diagnostic information on the insulation state of the winding; This is a machine learning method comprising a trained model storage process (e.g., processes S130, S330) of storing the learned model trained by the machine learning process in a trained model storage unit. This configuration makes it possible to provide a learning model that can infer (estimate) diagnosis information for the motor section's winding insulation with high accuracy from unprocessed data or data that has been at least partially preprocessed, such as data on the voltage and current values ​​supplied to the motor section of the canned motor pump, data on the temperature of the stator winding of the motor section or data on the temperature, temperature difference, or pressure correlated therewith, and data on the inlet temperature and flow rate of the handled liquid in the pump section.It is also possible to provide a learning model that can accurately diagnose the insulation state of the windings without stopping the canned motor pump.

[0138] A ninth embodiment of the present invention is the eighth embodiment, wherein the motor section further comprises a cooling jacket on at least a part of an outer periphery of the motor housing, The machine learning method further includes input data including data on the inlet temperature and flow rate of the cooling liquid supplied to the cooling jacket, the data being unprocessed or at least partially preprocessed. According to this configuration, in addition to the input data of the eighth embodiment, data on the inlet temperature and flow rate of the coolant is further added as input data contained in the learning data, and unprocessed data or data that has been preprocessed at least in part is further added, so that a learning model can be provided that can infer (estimate) diagnostic information for the winding insulation of the motor section with higher accuracy.

[0139] A tenth embodiment of the present invention is a machine learning program for causing a computer to execute each step of the machine learning method according to the eighth or ninth embodiment. This configuration makes it possible to provide a learning model that can infer (estimate) diagnosis information for the motor section winding insulation with high accuracy from unprocessed data or data that has been at least partially preprocessed, such as data on the voltage and current values ​​supplied to the motor section of the canned motor pump, data on the temperature of the stator winding of the motor section or data on the temperature, temperature difference, or pressure correlated therewith, data on the inlet temperature and flow rate of the liquid handled by the pump section, and, as necessary, data on the inlet temperature and flow rate of the cooling liquid.It is also possible to provide a learning model that can accurately diagnose the insulation state of the windings without stopping the canned motor pump.

[0140] An eleventh embodiment of the present invention is an insulation condition diagnosis method for diagnosing an insulation condition of a winding of a stator used in the canned motor pump by using a learning model generated by the machine learning device according to any one of the first to sixth embodiments, an input data acquisition step (e.g., steps S200 and S400) for acquiring input data including unprocessed data or data that has been at least partially preprocessed, such as data on voltage and current values ​​supplied to the motor unit, data on the temperature of the winding of the stator or data on a temperature, temperature difference, or pressure correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and data on the inlet temperature and flow rate of the cooling liquid as necessary; an inference step (steps S210 and S410) of inputting the input data acquired by the input data acquisition step into the learning model and inferring diagnostic information on the insulation state of the stator winding; The insulation condition diagnosis method includes the steps of: According to this configuration, it is possible to infer (estimate) diagnosis information for the motor winding insulation with high accuracy using input data including data on voltage and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on temperatures, temperature differences or pressures correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and, as necessary, data on the inlet temperature and flow rate of the cooling liquid, and which includes unprocessed data or data that has been at least partially preprocessed. Also, it is possible to accurately diagnose the insulation state of the winding without stopping the canned motor pump.

[0141] A twelfth embodiment of the present invention is an insulation state diagnosis program for causing a computer to execute each step of the insulation state diagnosis method according to the eleventh embodiment. According to this configuration, diagnostic information for the motor section winding insulation can be inferred (estimated) with high accuracy from input data including unprocessed data or at least partially preprocessed data, such as data on the voltage and current values ​​supplied to the motor section of the canned motor pump, data on the temperature of the stator winding of the motor section or data on temperatures, temperature differences or pressures correlated therewith, data on the inlet temperature and flow rate of the liquid handled by the pump section, and, as necessary, data on the inlet temperature and flow rate of the cooling liquid.In addition, the insulation condition of the windings can be diagnosed with high accuracy without stopping the canned motor pump. [Explanation of symbols]

[0142] 1. Insulation condition diagnostic system 2 Canned motor pump 3. Measuring Equipment 4. Machine learning equipment 5. Insulation condition diagnostic device 6 Learning Model 10 Pump section 20 Motor section 21 Shaft 22 Rotor 23 Stator 25 Motor housing 31 Windings 33 Can 45 Stator Room 50 Rotor Room 71 Cooling jacket 101 Motor voltage / current sensor 102 Winding heat generation state measurement sensor 103 Handling liquid measurement sensor 104 Coolant measurement sensor 121 Learning Data Acquisition Unit 122 Machine Learning Department 123 Learning Data Storage Unit 124 Trained model memory 141 Input data acquisition unit 142 Reasoning part 143 Output Processing Section 144 Trained model memory

Claims

1. A motor unit and a pump unit driven by the motor unit, the motor unit includes a rotor rotatable about a shaft, a stator facing the rotor with a gap therebetween, and a cylindrical can that defines a rotor chamber for accommodating the rotor on the inside and a stator chamber for accommodating the stator together with a motor housing on the outside, A machine learning device that generates a learning model to be used in an insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump that circulates a part of a pumped liquid in the pump section to the rotor chamber, the machine learning device comprising: a learning data acquisition unit which receives as input data unprocessed data or data at least partially preprocessed, the data being data on voltage values ​​and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on temperatures, temperature differences or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid, and acquires a plurality of sets of learning data including at least this input data; a machine learning unit that inputs the learning data into the learning model to cause the learning model to learn a correlation between the input data and diagnostic information about the insulation state of the winding; A trained model storage unit that stores the learning model trained by the machine learning unit. Machine learning device.

2. The motor unit further includes a cooling jacket on at least a portion of the motor housing. The input data further includes data on an inlet temperature and a flow rate of a cooling liquid supplied into the cooling jacket. The machine learning device according to claim 1 .

3. the data of the voltage value and the current value supplied to the motor unit is data supplied to the motor unit during a predetermined period of time, the data on the temperature of the stator winding or a temperature, temperature difference, or pressure correlated therewith is data for the predetermined period of time; The data of the inlet temperature and flow rate of the handled liquid is data for the predetermined period. The machine learning device according to claim 1 .

4. the data of the voltage value and the current value supplied to the motor unit is data supplied to the motor unit during a predetermined period of time, the data on the temperature of the stator winding or a temperature, temperature difference, or pressure correlated therewith is data for the predetermined period of time; The data of the inflow temperature and flow rate of the handled liquid is data for the predetermined period, The data of the inlet temperature and flow rate of the cooling liquid supplied into the cooling jacket is data for the predetermined period. The machine learning device according to claim 2.

5. The learning data is The output data further includes the diagnostic information, which is associated with the input data and indicates that the insulation state of the winding is one of a plurality of states; The machine learning unit causes the learning model to learn a correlation between the input data and the output data through supervised learning. The machine learning device according to claim 1 .

6. The learning data is the diagnostic information includes only input data when the insulation condition of the winding is in a predetermined state; the machine learning unit causes the learning model to learn a correlation between the input data and the diagnostic information indicating that the insulation state of the winding is in the predetermined state by unsupervised learning; The machine learning device according to claim 1 .

7. 4. An insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump, using a learning model generated by the machine learning device according to claim 1 or 3, an input data acquisition unit that acquires input data including unprocessed data or data that has been at least partially preprocessed, such as data on voltage values ​​and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on temperatures, temperature differences, or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid; an inference unit that inputs the input data acquired by the input data acquisition unit into the learning model and infers diagnostic information on an insulation state of the stator winding; Equipped with Insulation condition diagnostic device.

8. 5. An insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump, using a learning model generated by the machine learning device according to claim 2 or 4, comprising: an input data acquisition unit that acquires input data including unprocessed data or at least partially preprocessed data, such as data on voltage values ​​and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on a temperature, temperature difference, or pressure correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and data on the inlet temperature and flow rate of a cooling liquid; an inference unit that inputs the input data acquired by the input data acquisition unit into the learning model and infers diagnostic information on an insulation state of the stator winding; Equipped with Insulation condition diagnostic device.

9. A motor unit and a pump unit driven by the motor unit, the motor unit includes a rotor rotatable about a shaft, a stator facing the rotor with a gap therebetween, and a cylindrical can that defines a rotor chamber for accommodating the rotor on the inside and a stator chamber for accommodating the stator together with a motor housing on the outside, A machine learning method for learning a learning model used in an insulation condition diagnosis device for diagnosing an insulation condition of a winding of a stator used in a canned motor pump that circulates a part of a pumped liquid in the pump section to the rotor chamber, comprising: a learning data acquisition step of acquiring a plurality of sets of learning data including at least the input data, the input data being unprocessed data or data that has been at least partially preprocessed, the input data being data on voltage and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on temperatures, temperature differences or pressures correlated therewith, and data on the inlet temperature and flow rate of the treated liquid; a machine learning process for inputting the learning data into the learning model to cause the learning model to learn a correlation between the input data and diagnostic information on the insulation state of the winding; A trained model storage step of storing the trained model trained by the machine learning step in a trained model storage unit. Machine learning methods.

10. The motor unit further includes a cooling jacket on at least a portion of an outer periphery of the motor housing. The input data further includes data on an inlet temperature and a flow rate of a cooling liquid supplied into the cooling jacket. The machine learning method of claim 9.

11. A method for causing a computer to execute each step of the machine learning method according to claim 9 or 10, Machine learning programs.

12. 4. An insulation condition diagnosis method for diagnosing an insulation condition of a winding of a stator used in a canned motor pump, using a learning model generated by the machine learning device according to claim 1 or 3, comprising: an input data acquisition step of acquiring input data including data on voltage and current values ​​supplied to the motor unit, data on the temperature of the stator winding or data on a temperature, temperature difference or pressure correlated therewith, and data on the inlet temperature and flow rate of the treated liquid, the input data including unprocessed data or data that has been at least partially preprocessed; an inference step of inputting the input data acquired by the input data acquisition step into the learning model and inferring diagnostic information on an insulation state of the stator winding; An insulation condition diagnosis method comprising:

13. 5. An insulation condition diagnosis method for diagnosing an insulation condition of a winding of a stator used in a canned motor pump, using a learning model generated by the machine learning device according to claim 2 or 4, comprising: an input data acquisition step of acquiring input data including data on voltage and current values ​​supplied to the motor unit, data on the temperature of the windings of the stator or data on a temperature, temperature difference, or pressure correlated therewith, data on the inlet temperature and flow rate of the handled liquid, and data on the inlet temperature and flow rate of the cooling liquid, the input data including unprocessed data or data that has been at least partially preprocessed; an inference step of inputting the input data acquired by the input data acquisition step into the learning model and inferring diagnostic information on an insulation state of the stator winding; An insulation condition diagnosis method comprising:

14. A method for causing a computer to execute each step of the insulation condition diagnosis method according to claim 12, Insulation condition diagnostic program.

15. A method for causing a computer to execute each step of the insulation condition diagnosis method according to claim 13, Insulation condition diagnostic program.

Images