Machine learning device, condition diagnosis device, inference device, machine learning method, machine learning program, condition diagnosis method, condition diagnosis program, inference method, and inference program

The machine learning device uses data from pump and pressure tank operations to accurately diagnose fluid supply systems, overcoming reliance on operator experience and expensive sensors, ensuring timely replacements.

JP7588523B2Active Publication Date: 2024-11-22EBARA CORP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2021021741
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-02-15
Publication Date
2024-11-22
Estimated Expiration
2041-02-15

AI Technical Summary

Technical Problem

Existing water supply equipment diagnosis systems rely on complex calculations and operator experience, making it difficult to accurately determine the optimal timing for replacement due to variations in usage scenarios, and they require expensive sensors.

Method used

A machine learning device that generates a learning model using data from the operating status of pumps, pressure tanks, and flow rates to diagnose the condition of fluid supply devices with high accuracy without relying on operator experience.

Benefits of technology

Enables precise diagnosis of fluid supply device conditions, allowing for timely replacements and reducing reliance on expensive sensors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007588523000001
    Figure 0007588523000001
  • Figure 0007588523000002
    Figure 0007588523000002
  • Figure 0007588523000003
    Figure 0007588523000003
Patent Text Reader

Abstract

To provide a machine learning device enabling highly accurately diagnosing a state of a fluid supply device without depending on experience of a worker.SOLUTION: A machine learning device 4 generates a learning model for diagnosing a state of a fluid supply device 1 having a pump for transferring fluid and the pressure tank provided on a discharge side of the pump. The machine learning device includes: a learning data storage section 401 storing a plurality of sets of learning data that include at least data on an operating state of the pump for predetermined period and data on a use flow rate of fluid used in a fluid supply destination to which fluid is supplied from the pressure tank for the predetermined period as input data; a machine learning section 402 causing the learning model to learn correlation between the input data and output data by inputting the plurality of sets of learning data to the learning model; and a learned model storage section 403 storing the learning model learned by the machine learning section 402.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a machine learning device, a state diagnosis device, an inference device, a machine learning method, and a machine learning program. The present invention relates to a system, a condition diagnosis method, a condition diagnosis program, an inference method, and an inference program. [Background technology]

[0002] A device for supplying water (tap water) to water supply targets such as office buildings or apartment buildings. Water supply devices are widely used for water supply. Water supply devices generally consist of a pump for pumping water. a motor for driving the pump, a control unit for controlling the operation of the pump, and a and a pressure tank connected thereto.

[0003] The water supply device delivers water to the destination by pumping water with a motor-driven pump. A check valve is provided between the pump and the pressure tank downstream of the pump. The check valve and pressure tank prevent water from entering the water supply pipe even after the pump has stopped. Proper pressure is maintained to deliver water to its destination.

[0004] Such water supply devices may operate repeatedly over the years as the pump operates or as water is supplied to the destination. Repeated operation will gradually deteriorate the water supply device. However, the deterioration of the water supply device The time required for replacement varies depending on the usage conditions, so it was difficult to determine the optimal timing for replacement. This is a device that can accurately diagnose the deterioration state of water supply equipment and determine the appropriate replacement time. has been proposed (see, for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 3596909 [Patent Document 2] Japanese Patent Application Publication No. 8-86278 Summary of the Invention [Problem to be solved by the invention]

[0006] In the devices disclosed in Patent Document 1 and Patent Document 2, individual physical quantities (pressure, motor This diagnoses the condition of the pressure tank of the water supply system based on the current of the water supply system or the water supply time. Therefore, the change in the state of the pressure tank of the water supply system may be expressed in physical quantities other than those mentioned above. In cases where the information is expressed in a composite manner in multiple physical quantities, see Patent Documents 1 and 2. The disclosed devices could not handle the above problem. In the diagnosis of a problem that involves a series of events, there are some parts that depend on the experience (including tacit knowledge) of the worker and some parts that depend on the individual knowledge of the worker. The difference is large, and there is a strong demand for a device that can automate such diagnosis.

[0007] In view of the above-mentioned problems, the present invention is directed to a method for detecting a temperature rise without relying on the experience of an operator and without installing expensive sensors. A machine learning device that can diagnose the state of a fluid supply device with high accuracy without Diagnosis device, inference device, machine learning method, machine learning program, condition diagnosis method, condition diagnosis program The present invention aims to provide a program, an inference method, and an inference program. [Means for solving the problem]

[0008] In order to achieve the above object, a machine learning device according to an aspect of the present invention comprises: A fluid supply system including a pump for transporting a fluid and a pressure tank provided on the discharge side of the pump. A machine learning device that generates a learning model for diagnosing a state of a feeding device, Data on the operation status of the pump during a predetermined period, and data on the pressure during the predetermined period Data on the usage flow rate of the fluid used at the fluid supply destination to which the fluid is supplied from the power tank A learning data storage unit that stores a plurality of sets of learning data including at least the above data as input data. and, A plurality of sets of the learning data are input to the learning model, whereby the input data and the flow a machine learning unit that causes the learning model to learn a correlation with diagnostic information of the body supply device; A trained model storage unit that stores the learning model trained by the machine learning unit; Equipped with. Effect of the Invention

[0009] According to the machine learning device of the present invention, diagnostic information of a fluid supply device can be inferred (diagnosed) with high accuracy. In addition, according to the condition diagnosis device of the present invention, Therefore, the condition of the fluid supply device can be diagnosed with high accuracy without relying on the experience of the operator. do.

[0010] Other objects, configurations and effects will become apparent from the detailed description of the invention described below. can be. [Brief description of the drawings]

[0011] [Figure 1] 1 is a diagram showing an example of a fluid supplying device 1 to which a condition diagnosis system 2 according to a first embodiment is applied. [Diagram 2] FIG. 2 is a hardware configuration diagram showing an example of a computer 200 that constitutes the machine learning device 4 and the condition diagnosis device 5. [Diagram 3] FIG. 2 is a block diagram showing an example of a machine learning device 4 according to the first embodiment. [Figure 4]FIG. 2 is a data configuration diagram showing an example of data (supervised learning) used in the machine learning device 4 according to the first embodiment. [Diagram 5] FIG. 2 is a schematic diagram illustrating an example of a neural network model used in the machine learning device 4 according to the first embodiment. [Figure 6] 4 is a flowchart showing an example of a machine learning method performed by the machine learning device 4 according to the first embodiment. [Figure 7] 1 is a block diagram showing an example of a condition diagnosis device 5 according to a first embodiment. [Figure 8] 5 is a flowchart showing an example of a condition diagnosis method by the condition diagnosis device 5 according to the first embodiment. [Figure 9] FIG. 11 is a data configuration diagram showing an example of data (unsupervised learning) used by the machine learning device 4 according to the second embodiment. [Figure 10] FIG. 11 is a schematic diagram illustrating an example of an autoencoder model used in a machine learning device 4 according to a second embodiment. [Figure 11] 13 is a flowchart showing an example of a machine learning method performed by the machine learning device 4 according to the second embodiment. [Figure 12] 10 is a flowchart showing an example of a condition diagnosis method by a condition diagnosis device 5 according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The scope necessary for the description of the present invention to achieve the object of the present invention is shown in a schematic manner, and the relevant part of the present invention is explained. The following description will focus on the scope necessary for clarity, and the parts that are omitted will be based on the prior art. It shall be so.

[0013] FIG. 1 shows a fluid supplying device 1 to which a condition diagnosis system 2 according to a first embodiment is applied. This fluid supplying device 1 is mainly used in buildings and residences such as apartment buildings, offices, commercial facilities, factories, schools, etc. The fluid supply device 1 is a device for supplying water to facilities (water supply targets) such as homes and parks. Water is introduced from a fluid supply source 41 through an inlet port via an inlet pipe 42. A water supply pipe 43 is connected to the discharge port of the fluid supply device 1. The water supply pipe 43 is connected to a fluid supply destination 44 such as a faucet in each building. The device 1 boosts the pressure of water from a fluid supply source 41 and supplies the water to each fluid supply destination 44 such as a building. .

[0014] In addition, the fluid supply device 1 of the present embodiment is illustrated as a water supply device that supplies water. The supply device 1 supplies liquids other than water, such as fuel and chemicals, as well as gases, such as hydrogen and oxygen. The fluid supply device may be one that supplies a fluid containing the fluid.

[0015] The fluid supply device 1 includes a pump 12 and a motor 1 as a drive unit for driving the pump 12. The inverter 14 controls the motor 13. The motor 14 is connected to a commercial power source 51 via a ground fault circuit interrupter 52 .

[0016] The fluid supply device 1 includes a check valve 15 and a flow switch 16 on the discharge side (downstream side) of the pump 12. The fluid supply device 1 shown in FIG. The fluid supply device 1 includes a motor 13, a check valve 15, and a flow switch 16. Even if the system has two or more sets of pumps 12, motors 13, check valves 15, and flow switches 16, The fluid supply device 1 includes a plurality of pumps 12, so that some of the pumps 12 can be In the event that one pump becomes inoperable, water supply can be continued using another pump 12 that is operable, thereby preventing water outages. This can be done.

[0017] The fluid supply device 1 also includes a backflow prevention device 11 upstream of the pump 12. The stop device 11 is provided in an introduction pipe 42 connected to the suction port of the fluid supply device 1, and the fluid The backflow of water from the supply device 1 to the fluid supply source 41 is prevented. In such a case, the fluid supplying device 1 does not need to include the backflow prevention device 11.

[0018] The fluid supplying device 1 has a check valve 15 in a discharge pipe connected to the discharge port of the pump 12. The stop valve 15 prevents water from flowing back to the pump 12 when the pump 12 stops. The body supply device 1 has a flow switch 16 downstream (secondary side) of the check valve 15. The flow switch 16 detects when the flow rate of water flowing through the discharge pipe drops to a predetermined value. Furthermore, the fluid supply device 1 includes a pressure tank downstream of the flow switch 16. The pressure tank 17 stores the discharge of the fluid supply device 1 while the pump 12 is stopped. This is a pressure retainer for maintaining the pressure on the outlet side.

[0019] The pressure tank 17 according to this embodiment has a diaphragm 17a that divides the inside of the container into an air chamber and a water chamber. The air chamber is filled with air in advance, and the water that flows into the water chamber from the pump 12 is The air is compressed through the diaphragm 17a. A check valve 1 is provided between the pressure tank 17 and the pump 12. 5 is provided, and this check valve 15 and the pressure tank 17 ensure that when the pump 12 stops, Even after the water supply, the water pressure in the water supply pipe is appropriately maintained, and water is sent to the fluid supply destination 44. When water is sent to the supply destination 44, the diaphragm 17a presses from the air chamber side to the water chamber side.

[0020] The fluid supplying device 1 includes a control unit 20 that controls the water supplying operation. If a circuit board with a central processing unit (Central Processing Unit) or a dedicated circuit board is used, The control unit 20 is supplied with power from a commercial power source 51 via a power line (not shown). However, the control unit 20 controls the flow rate of the fluid supplying device 1 through other components such as the inverter 14. Electrical power may be provided.

[0021] The control unit 20 and the inverter 14 are connected to each other through a communication line 21. The control unit 20 sends control commands to the inverter 14 regarding various setting values ​​and the rotation speed of the motor 13. The inverter 14 sends signals such as a frequency command value, an on / off signal, etc. to the control unit. The actual operating conditions such as frequency value and current value are sequentially sent to 20.

[0022] The control signal transmitted between the control unit 20 and the inverter 14 is an analog signal. For example, analog signals may be used for the rotation frequency, etc. A signal can be used for an operation stop command, and a digital signal can be used for an operation stop command, etc.

[0023] A status diagnosis system for diagnosing the status of the pressure tank 17 for the fluid supply device 1 having the above configuration. The condition diagnosis system 2 includes a measurement device 3, a machine learning device 4, and and a condition diagnosis device 5.

[0024] The measuring device 3 is installed in each part of the fluid supplying device 1 and measures the physical quantity and state of each part of the fluid supplying device 1. In the learning phase, the measurement device 3 is connected to the machine learning device 4 to measure the state of the object. In the inference phase, the data is collected by connecting the device to the condition diagnosis device 5. The measuring device 3 is a pump operation status sensor 31 and a usage flow rate sensor 32. The pump 1 is provided with a pump primary pressure sensor 33 and a pump secondary pressure sensor 34. The secondary pressure sensor 33 is a pump pressure sensor that measures the pressure related to the pump. Good too.

[0025] The pump operation status sensor 31 acquires the operation status of the pump 12. The conditions include, for example, ON / OFF of the pump 12, the rotation speed of the pump 12, the current value of the motor 13, etc. The pump operation status sensor 31 can measure time series data for a predetermined period of time. Preferably, the predetermined period of time may include the start-up time when the pump is started. By acquiring the operating status of the pump 12, the amount of fluid discharged from the pump 12 can be estimated. do.

[0026] The pump operation status sensor 31 detects the operation of the pump 12, the motor 13, or the inverter 14. It is preferable to be able to obtain time series data of the operating state indicating whether the operating The operation state is determined by ON / OFF control from the control unit 20 to the pump 12, the motor 13, or the inverter 14. The FF command is acquired. When the command of the control unit 20 is ON, the operation state is in operation, and when the command of the control unit 20 is ON, the operation state is O. In the case of FF, it is sufficient to recognize that the vehicle is stopped.

[0027] In addition, the pump operation status sensor 31 may acquire time series data of the rotation speed of the pump 12. The rotation speed of the pump 12 can be obtained by measuring the rotation speed of the pump 12 or the motor 13. In addition, the rotation speed of the motor 13 is determined by the output frequency of the inverter 14. , the output frequency of the inverter 14 may be obtained.

[0028] Furthermore, the pump operation status sensor 31 is connected to the motor 13 which is the driving source of the pump 12. By acquiring the motor current value, the power supply current can be calculated. The amount of work done by the pump 12 can be obtained. It is also possible to recognize that the flow rate is excessive.

[0029] The usage flow rate sensor 32 is a flow rate sensor for measuring the amount of fluid supplied from the pressure tank 17 during a predetermined period of time. The flow rate of the fluid used at the supply destination 44 is measured. When there are multiple fluid supply destinations 44, The usage flow rate sensor 32 measures the total usage flow rate obtained by adding up the flow rates of the multiple fluid supply destinations 44. It is preferable that the usage flow rate can be measured using time series data. For example, The source 32 may be provided on the upstream side where the fluid is supplied to a plurality of fluid destinations 44, as shown in FIG. The usage flow rate sensor 32 is connected to the supply destination 44 for each room of a collective housing unit such as an apartment or condominium. The usage flow rate sensor 32 may be provided in each room as a water meter corresponding to each room. The predetermined period may include a start time when the pump is started.

[0030] The usage flow rate sensor 32 may estimate the usage flow rate from other measurement data instead of directly measuring the usage flow rate. For example, The entry and exit records of people at a plurality of fluid supply destinations 44 are measured, and the flow rate used is calculated from the time series data. In addition, sensors can be installed in the toilets, bathroom showers, kitchen faucets, etc. of each room. The amount of fluid used may be estimated from the amount of fluid used. The usage flow rate of the fluid may be estimated from the usage rate of the gas.

[0031] The pump primary pressure sensor 33 is a pressure measuring device for measuring the suction side pressure of the pump 12. The pump primary pressure sensor 33 of this embodiment is disposed between the fluid supply source 41 and the backflow prevention device 11. The pump primary pressure sensor 33 is capable of measuring time series data for a predetermined period of time. Preferably, the predetermined period of time may include a start-up time point when the pump is started.

[0032] The pump secondary pressure sensor 34 is a pressure measuring device for measuring the pressure on the discharge side of the pump 12. The pump secondary pressure sensor 34 of this embodiment is connected to the flow switch 16 and the pressure tank 17. The pump secondary pressure sensor 34 is capable of measuring time series data for a predetermined period of time. Preferably, the predetermined period of time may include a start-up time when the pump is started.

[0033] The measuring device 3 measures the physical quantities and state quantities of each part at a predetermined measurement period, for example. Each time time passes, the measurement value at that measurement point can be output to the machine learning device 4 and the condition diagnosis device 5. The measuring device 3 is configured to be capable of measuring the pump operation status sensor 31 and the flow rate sensor 32. The measurement period of each of the pump pressure sensor 32, the pump primary pressure sensor 33, and the pump secondary pressure sensor 34 is The measurement periods may be the same or different. Instead of outputting a discrete measurement value every time a period passes, it outputs a continuous signal like an analog signal. The measurement value may be output.

[0034] The machine learning device 4 operates as a subject of the learning phase and diagnoses the state of the fluid supply device 1. The machine learning device 4 generates a learning model 6 used in the process of the machine learning. As a method for this, "supervised learning" can be adopted.

[0035] The state diagnosis device 5 operates as the subject of the inference phase and uses the state diagnosis device 5 generated by the machine learning device 4. Using the learned learning model 6, the fluid supply device is calculated from the measured values ​​measured by the measuring device 3. The machine learning device 4 then diagnoses the state of the device 1. The trained learning model 6 is transmitted from the machine learning device 4 to any communication network or The information is provided to the condition diagnostic device 5 via a recording medium or the like.

[0036] The external device 35 is a device for transmitting and receiving various information between the fluid supplying device 1 and the external device 35. For example, computers for plant management (including local servers and cloud servers). , diagnostic computer used by the operator (maintenance inspector), or USB memory or external H This external device 35 is configured with an external storage unit such as a DD. It is also possible to connect to the device 200 and transmit various data constituting the learning data set. In addition, the external device 35 is configured to notify an operator or the like when an abnormality occurs in the fluid supplying device 1. A GUI (Graphical User Interface) is used to notify the user of the occurrence of an abnormality and its details. The external device 35 and the like are provided with a notification means. For communication between the fluid supplying device 1 and the communication device 2, wireless communication may be used.

[0037] FIG. 2 shows an example of a computer 200 constituting the machine learning device 4 and the condition diagnosis device 5. This is a hardware configuration diagram.

[0038] Each of the machine learning device 4 and the condition diagnosis device 5 is a general-purpose or dedicated computer 200 As shown in FIG. 2, the computer 200 is configured by the following main components: A bus 210, a processor 212, a memory 214, an input device 216, a display device 218, storage device 220, communication I / F (interface) unit 222, external device I / F unit 224, I / O (input / output) device I / F unit 226, and media input / output unit 22 8. The above components are appropriately selected depending on the purpose for which the computer 200 is used. It may be omitted if appropriate.

[0039] The processor 212 may be one or more processing units (CPU, MPU, GPU, DSP, etc.). The memory 21 is made up of a plurality of memory units 21a, 21b, 21c, 21d, 21e, 21f, 21g, 21h, 21h, 21i, 21j, 21m ... 4 stores various data and programs 230 and functions as, for example, a main memory. There are two types of memory: volatile memory (DRAM, SRAM, etc.) that can be used with a single chip, and non-volatile memory (ROM, flash memory, etc.) that can be used with a single chip. It consists of the following:

[0040] The input device 216 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc. The display device 218 may be, for example, a liquid crystal display, an organic EL display, or an electronic The input device 216 and the display device 218 are composed of paper, a projector, etc. The storage device may be integrally configured with the display, such as a touch panel display. 220 is composed of, for example, a HDD, SSD, etc., and contains an operating system and programs. It stores various data necessary for the execution of program 230.

[0041] The communication I / F unit 222 is connected to a network 240 such as the Internet or an intranet. It is connected by wire or wirelessly and transmits data between other computers according to a specified communication standard. The external device I / F unit 224 is connected to an external device 250 such as a printer or a scanner. The device is connected by wire or wirelessly, and data is transmitted between the device and the external device 250 in accordance with a predetermined communication standard. The means of wireless communication typically conforms to international standards. As communication means, IEEE802.15.4, IEEE802.15.1, IEEE8 02.15.11a, 11b, 11g, 11n, 11ac, 11ad, ISO / IEC1 IEEE 802.15.4g and 4513-3-10. ooth (registered trademark), Bluetooth Low Energy, Wi-Fi, ZigB ee (registered trademark), Sub-GHz, EnOcean (registered trademark), etc. can also be used. The I / O device I / F unit 226 is a unit for connecting various I / O devices such as sensors and actuators. The I / O device 260 is connected to the I / O device 260, and, for example, a detection signal from a sensor or Sends and receives various signals and data, such as control signals to the actuator. Media I / O section 228 is composed of a drive device such as a DVD drive, a CD drive, etc. The optical disc drive 240 reads and writes data from and to a medium 270 such as a CD.

[0042] In the computer 200 having the above configuration, the processor 212 executes the program 23. 0 is loaded into the work memory area of ​​the memory 214 and executed, and the program is then transmitted to the computer via the bus 210. The program 230 controls each part of the computer 200 instead of the memory 214. The program 230 may be installed in the storage device 220. Recorded in file format or executable file format on non-transient recording media such as CDs and DVDs and provided to the computer 200 via the media input / output unit 228. The RAM 230 downloads the data via the network 240 through the communication I / F unit 222. The information may be provided to the computer 200 by

[0043] The computer 200 may be, for example, a desktop computer or a portable computer. The computer 200 is a client-type computer. Alternatively, a server-type computer or a cloud-type computer may be used. 0 may be applied to devices other than the machine learning device 4 and the condition diagnosis device 5.

[0044] (Machine Learning Device 4) FIG. 3 is a block diagram showing an example of the machine learning device 4 according to the first embodiment.

[0045] The machine learning device 4 includes a learning data acquisition unit 400, a learning data storage unit 401, and a machine The machine learning device 4 includes a learning unit 402 and a trained model storage unit 403. The machine learning device 4 includes, for example, The learning data acquisition unit 400 is configured as the computer 200 shown in FIG. The machine learning unit 402 is configured by the communication I / F unit 222 or the I / O device I / F unit 226. , a processor 212, a learning data storage unit 401 and a learned model storage unit 4 03 is composed of a storage device 220.

[0046] The learning data acquisition unit 400 is connected to various external devices via the communication network 300 and receives input. The external device is an interface unit for acquiring learning data including at least the data. The device 35 includes, for example, a measuring device 3 provided in the fluid supply device 1 and an operating device used by an operator. The service provider terminal 8, etc. When the status diagnostic device 5 is connected to the communication network 300, The learning data acquisition unit 400 is provided for the fluid supply device 1 to be diagnosed by the condition diagnosis device 5. The learning data may be acquired from the measurement device 3 that has been installed.

[0047] The learning data storage unit 401 stores the learning data acquired by the learning data acquisition unit 400 in a The learning data storage unit 401 is a database that stores multiple sets of learning data. The specific configuration of the database can be designed as appropriate.

[0048] The machine learning unit 402 performs machine learning using the learning data stored in the learning data storage unit 401. That is, the machine learning unit 402 inputs a plurality of pieces of learning data to the learning model 6. By inputting a set of input data, the input data included in the learning data and the diagnostic information of the fluid supplying device 1 are matched. By having the learning model 6 learn the correlation, a trained learning model 6 is generated. In this embodiment, as a specific method of supervised learning by the machine learning unit 402, a neural network is used. This section explains the case where a network is adopted.

[0049] The trained model storage unit 403 stores the trained model generated by the machine learning unit 402. The trained model storage unit 403 stores trained models 6. The learning model 6 is transmitted to a real system (e.g., a state diagnosis system) via any communication network or recording medium. In FIG. 3, a learning data storage unit 401 and a trained model Although the memory unit 403 and the memory unit 404 are shown as separate memory units, they are composed of a single memory unit. This is also fine.

[0050] FIG. 4 shows data (supervised learning) used in the machine learning device 4 according to the first embodiment. FIG. 11 is a data configuration diagram showing an example.

[0051] The learning data is data on the operating status of the pump 12 during a predetermined period as input data. The input data includes at least the flow rate of the fluid used at the fluid supply destination 44. data on the operation status of the pump 12 as a fluid supply source, and data on the fluid used at the fluid supply destination 44. The predetermined period for each of the flow rate data is basically set to the same period. If a time lag is found between the data, the period is set to the period corresponding to the time lag. You may do so.

[0052] The input data includes data on the operation status of the pump 12 and data on the fluid supply destination 44. The data may include other data in addition to the data on the flow rate of the fluid. For example, The primary pressure on the suction side of the pump 12, the secondary pressure on the discharge side of the pump 12, and the sound generated when the pump 12 is operating , the temperature of at least one of the pump 12 or the motor 13, the lubrication pressure of the pump 12, the amount of the lubricant At least the following data: flow rate, lubricant temperature, and lubricant property values ​​(color, particle size distribution) It may further include one piece of data.

[0053] The data on the operation status of the pump 12 during a predetermined period is stored as data on the operation state indicating either one of the above, data on the number of revolutions of the pump 12 during a predetermined period, and The data of the motor current value supplied to the motor 13 which is the driving source of the pump 12 during a predetermined period of time. In this embodiment, the data on the operation status of the pump 12 is preferably at least one of the following: Data on the operation state of the pump 12, indicating whether it is operating or stopped, data on the pump 12 during a predetermined period, Data on the number of revolutions of the pump 12 or the number of revolutions of the motor 1 which is the driving source of the pump 12 during a predetermined period In the following description, the data is assumed to consist of motor current value data supplied to 3.

[0054] The operation status data indicating whether the pump 12 is operating or stopped during a predetermined period is At multiple measurement points within a predetermined period, multiple measurements are made by the pump operation status sensor 31. The data on the operating state is, for example, The data is linked to the measurement time and arranged in chronological order by measurement time. In addition, when the pump operation status sensor 31 outputs continuous measured values, the learning The measurement data acquisition unit 400 converts the measurement values ​​into data at a predetermined sampling period. The data on the operating state during a given period is collected at multiple sampling points during the given period. It consists of multiple measured values ​​(operation / stop, etc.)

[0055] The data on the number of revolutions of the pump 12 during a predetermined period is collected at a plurality of measurement points during the predetermined period. The rotation speed is composed of a plurality of measured values ​​(rotation speeds) measured by the pump operation status sensor 31. The data of the number of turns is, for example, linked to the measurement time indicating the time of measurement and arranged in chronological order by the measurement time. The pump operation status sensor 31 is configured as data arranged in a continuous manner. When a measurement value is to be output, the learning data acquisition unit 400 outputs the measurement value at a predetermined sampling frequency. This allows the data on the number of rotations for a given period to be recorded. It is composed of multiple measurement values ​​(number of rotations) at multiple sampling points within the interval.

[0056] The data of the motor current value supplied to the motor 13 which is the driving source of the pump 12 during a predetermined period The data is measured by the pump operation status sensor 31 at multiple measurement points within a predetermined period. The data of the current value is composed of a number of measured values ​​(current values) that indicate the time of measurement, for example. The data is linked to a fixed time and arranged in chronological order according to the measurement time. In the case where the pump operation status sensor 31 outputs continuous measured values, the learning data The data acquisition unit 400 converts the measurement values ​​into data at a predetermined sampling period. The data of the current value during a predetermined period is a plurality of data at a plurality of sampling points during the predetermined period. It is composed of the measured value (current value).

[0057] Used at the fluid supply destination 44 to which the fluid is supplied from the pressure tank 17 during a specified period The fluid flow data is a measurement of the total usage flow rate, calculated by adding up the flow rates of multiple fluid supply destinations 44. The fluid is supplied from the pressure tank 17 to the fluid supply destination 44. For example, the flow rate data is linked to the measurement time, which indicates the time of measurement, and is sorted in chronological order by the measurement time. The flow rate sensor 1 outputs continuous measured values. In the case of outputting the learning data, the learning data acquisition unit 400 measures the learning data at a predetermined sampling period. This makes it possible to obtain data on the amount of fluid supplied from the pressure tank 17 during a given period. The data on the flow rate of the fluid used at the fluid supply destination 44 is collected from multiple samples taken over a given period. The flow rate of the fluid used at the fluid supply destination 44 is determined by a number of measurements at the time of the measurement. .

[0058] The diagnosis information of the fluid supplying device 1 is the flow information when the abnormality diagnosis of the fluid supplying device 1 is performed. The information indicates whether or not some abnormality has occurred in the body supplying device 1, and the data format thereof is Various types of abnormality diagnosis can be used. Not only abnormalities that are discovered after the fact, but also abnormalities that are considered normal at the time of abnormality diagnosis Although it is within the acceptable range, it also includes signs of abnormality that may predict the occurrence of abnormalities in the future. nothing.

[0059] For example, as an example of the diagnostic information, as shown in FIG. 4, the fluid supplying device 1 is in a normal state. The information must consist of information indicating either that the device is working (no abnormality) or that the device is malfunctioning (abnormality). In this case, the diagnostic information can be classified into two values. For example, when the fluid supply device 1 is in a normal state, The value indicating that the fluid supply device 1 is in an abnormal state is set to "0", and the value indicating that the fluid supply device 1 is in an abnormal state is set to " 1" in a form associated with the input data by the worker using the work computer 8. In this case, the specific information about the abnormality is not required. Not necessarily necessary.

[0060] In addition, among the above diagnostic information, the information indicating that the fluid supply device 1 is abnormal is The specific content of the abnormality may also be included. For example, the specific content of the abnormality may be 17, an abnormality in the pump secondary pressure sensor 34 provided on the discharge side of the pump 12, An abnormality in the flow switch 16 provided on the discharge side of the pump 12 or The diagnostic information may include a plurality of values ​​(three or more) For example, the value indicating that the fluid supply device 1 is in a normal state is set to "0", and The supply device 1 sets the value "1" to indicate that there is an abnormality in the pressure tank 17, and the discharge The value indicating that the pump secondary pressure sensor 34 installed on the outlet side is abnormal is set to "2", and so on. The value is uniquely determined in advance according to the content of each abnormality, and the operating computer 8 is used to calculate the abnormality. The operator should input the corresponding value in association with the input data. By setting the interruption information, not only can you know whether an abnormality has occurred, but also what kind of abnormality it is when it occurs. Specific information (corresponding to Abnormality 1 / Abnormality 2 / ... / Abnormality n shown in Figure 4) is also included. A learning data set can be prepared. The diagnostic information as one aspect of the above can be In the machine learning described in , it is used when performing supervised learning (see Figure 4). It is.

[0061] In addition, the diagnostic information of the solenoid unit 3 may be other than those described above. For example, the diagnostic information in another aspect may be information that the fluid supplying device 1 is normal and not abnormal. In this case, the diagnostic information may include only the information indicating that the fluid supplying device 1 is normal. Since the diagnostic information is included as output data, the only information included is that the diagnostic information is not necessarily included as output data. The training data set is composed of input data and output data when the fluid supplying device 1 is normal. Therefore, the training dataset in this case is Since the output data is always the same, the training dataset contains the output data. It will be obvious to those skilled in the art that it is not necessary for the other In the machine learning described below, the diagnostic information as a form is used when performing unsupervised learning. It is something that will be utilized.

[0062] As another aspect of the diagnostic information, as shown in FIG. 4, the fluid supply device 1 may be in a normal state. (no abnormality) and the remaining life of the fluid supplying device 1 is within a preset period (e.g., several hours) Either the product is in an abnormal state (abnormal) within the last few years (e.g., days, months, or years) In this case, the diagnostic information is classified into two values, e.g., The value indicating that the fluid supplying device 1 is in a normal state is set to "0", and the remaining life of the fluid supplying device 1 is set to "1". The value indicating an abnormal state within a preset period is set to "1", and the work computer is The corresponding value may be input by the operator using the computer 8 in a manner associated with the input data. In this case, information regarding the specific nature of the abnormality is not necessarily required.

[0063] In addition, among the above diagnostic information, the remaining life of the fluid supplying device 1 is within a preset period. The information showing that the product is in good condition includes specific details about the remaining life, as shown by the dashed line in Figure 4. In this case, the diagnostic information is classified into multiple values ​​(at least three or more) and the fluid supply The fluid supply device 1 is in a normal state, and the remaining life of the fluid supply device 1 is a preset number of remaining lifespans. The information that indicates that the abnormality corresponds to one of the following within the period of life: do.

[0064] For example, the value indicating that the fluid supply device 1 is in a normal state is set to "0", and A value indicating that the remaining life of is within the first period (e.g., 6 months or more but less than 1 year) The remaining life of the fluid supplying device 1 is set to "1", and the remaining life of the fluid supplying device 1 is set to a second period (for example, less than six months) that is shorter than the first period. The value "2" indicates that the abnormality corresponds to the above condition, and the values ​​below are set according to the content of each abnormality. The input data is uniquely determined in advance, and then the operator uses the work computer 8 to input the The relevant values ​​should be entered in a linked format. By setting the diagnostic information in this way, Not only whether an abnormality occurred, but also specific information on the remaining life when an abnormality occurred (Fig. 4 We prepared a learning dataset that also included anomaly 1 / anomaly 2 / ... / anomaly n shown in The life prediction information as one aspect described above can be used in the machine learning described below. In this case, it is used when performing supervised learning (see Figure 4).

[0065] In addition, other information than the above may be used as the life prediction information for the fluid supplying device 1. For example, the life prediction information as another aspect can be obtained when the fluid supplying device 1 is normal and not abnormal. In this case, the life prediction information may include information indicating only that the fluid supply device Since the only information included is that 1 is normal, this life prediction information is inevitably output to the output device. The learning data set includes the input data when the fluid supplying device 1 is normal. The only dataset that is composed of the output data is the training data. The output data of the training dataset is always the same, so the training dataset is It is obvious to those skilled in the art that it is not necessary to have the information as data. The life expectancy prediction information in another form is a teacher in the machine learning described below. This is used when performing learning without

[0066] When using "supervised learning" as machine learning, the learning data corresponds to the input data. The output data is, for example, a pressure sensor (not shown) in a pressure tank of the test device. The diagnostic information of the charged pressure of the pressure tank 17 during a given period measured by the The secondary pressure during a given period measured by the pump secondary pressure sensor 34 installed on the outlet side The diagnostic information of the flow rate measured by the flow switch 16 installed on the discharge side of the pump. or operation information of the check valve 15 provided on the discharge side of the pump. The output data may further include, for example, training data or a correct answer in supervised learning. It is called a label.

[0067] Diagnostic information on the pressure of the pressure tank 17, the pump secondary pressure sensor installed on the discharge side of the pump The diagnostic information of the secondary pressure measured by the pressure sensor 34 for a predetermined period of time, diagnostic information of the flow rate measured by the flow switch 16 during a predetermined period of time; or The operation information of the check valve 15 provided on the discharge side of the pump is a time point included in a predetermined period or a predetermined Point data at a time point after the period, or including a specified period or a time point after the specified period The data is time series data covering a period.

[0068] Therefore, the learning data according to this embodiment is, as shown in FIG. Data on the operation status of the pump 12 and data on the flow rate of the fluid used at the fluid supply destination 44 The input data including the diagnostic data is associated with the output data including the diagnostic information of the fluid supplying device 1. It is composed.

[0069] Here, the input data included in the learning data (operation status of the pump 12 during a predetermined period) data of the fluid used at the fluid supply destination 44), and a fluid supply device The correlation between the diagnostic information in 1 will be explained.

[0070] The diagnostic information of the fluid supply device 1 varies depending on various parameters. For example, expensive sensors are required to measure the pressure of the pressure tank 17 and other components. Each of these tasks requires a certain level of skill, and traditionally this has depended heavily on the experience of the worker. The input data includes the operating status of the pump 12 during a predetermined period and the By measuring the flow rate of the fluid used at the fluid supply destination 44 between the fluid supply devices 1 This makes it possible to diagnose the following:

[0071] When acquiring the learning data, the learning data acquiring unit 400 acquires the learning data by Data on the operating status of the pump 12 for a predetermined period of time measured by the provided measuring device 3; and data on the flow rate of the fluid used at the fluid supply destination 44 during a specified period of time as input data. is acquired from the measuring device 3.

[0072] In addition, the operator may select the fluid supply device during the predetermined period in which the input data was measured by the measuring device 3. When the device 1 is diagnosed and the diagnosis value is input to the operator terminal 8, the learning data acquisition unit 400 The diagnostic value inputted at the operator terminal 8 is used as output data (teaching data). The learning data acquisition unit 400 acquires the input data and the output data from the terminal 8. The learning data is stored in the learning data storage unit 401. Remember.

[0073] FIG. 5 shows a neural network model used in the machine learning device 4 according to the first embodiment. FIG. 1 is a schematic diagram showing an example of a delta.

[0074] The learning model 6 is configured as a neural network model shown in FIG. The neural network model consists of l neurons (x1 to xl) in the input layer, m neurons (y11~y1m) in the first hidden layer, n neurons (y2 It consists of o neurons (z1 to zo) in the output layer.

[0075] Each neuron in the input layer is associated with one input data set contained in the training data. Each neuron in the output layer is assigned a corresponding output data set included in the training data. In addition, a certain preprocessing may be performed on the input data before it is input to the input layer. Alternatively, a predetermined post-processing may be performed on the output data after it is output from the output layer.

[0076] The first and second hidden layers are also called hidden layers, and are used in the neural network. In addition to the first and second hidden layers, the neural network may further include a plurality of hidden layers. Only the first hidden layer may be a hidden layer. Between the intermediate layer and the second hidden layer, and between the second hidden layer and the output layer, there are connections between the neurons of each layer. Each synapse has a weight wi (i is a natural number). Can be attached.

[0077] The neural network model uses the training data to The input data is input to the input layer, and the inference result is output from the output layer. By comparing the input data with the output data (teacher data) contained in the learning data, The system learns the correlation between the input data and the output data.

[0078] Specifically, each neuron in the input layer is assigned a unique number of input data points included in the training data. The value of each neuron in the output layer is the input The value of the input neuron and the synapse connecting the output neuron and the input neuron are The process of calculating the sum of the sequence of multiplication values ​​of the weights wi associated with the input layers is performed on the layers other than the input layer. It is calculated by performing this on all neurons.

[0079] Then, the values ​​(z1 to zo) output to each neuron in the output layer as inference results and the learning The values ​​of the teacher data (t1 to to) corresponding to each of the output data included in the use data are The error is calculated by comparing each of them, and each synapse is assigned a value that minimizes the error. Then, a process of adjusting the weights wi (backpropagation) is performed.

[0080] The above series of steps is repeated a predetermined number of times, or the above error is reduced to a value smaller than the allowable value. When a certain condition for ending the learning is met, such as the machine learning being stopped, the trained Neural network model (all weights wi associated with each synapse) is generated as:

[0081] (Machine learning methods) FIG. 6 is a flow diagram showing an example of a machine learning method performed by the machine learning device 4 according to the first embodiment. The machine learning method corresponds to the learning phase in Figure 1.

[0082] First, in step S10, the learning data acquisition unit 400 executes As a preliminary step, a desired number of training data are prepared and the prepared training data are used for learning. The training data is stored in the training data storage unit 401. The number of training data to be prepared here is It is only necessary to set it taking into consideration the inference accuracy required for the learning model 6 obtained in the intended manner.

[0083] There are several methods for preparing training data. For example, When diagnosing a specific fluid supply device 1, various measured values ​​before and after the diagnosis are The measurement device 3 acquires the measurements, and the worker uses the worker terminal 8 to record the measurements. By inputting the diagnostic results in a form corresponding to the fixed value, the input data and output data that constitute the learning data are By repeating this process, multiple sets of learning data are created. Alternatively, for example, the target portion of the fluid supplying device 1 may be It is also possible to obtain learning data by intentionally setting the value to a predetermined value.

[0084] Next, in step S11, the machine learning unit 402 performs pre-learning The learning model 6 before learning is prepared as shown in FIG. It is composed of a neural network model, in which the weights of each synapse are set to their initial values. Each neuron in the input layer is connected to data on the operation status of the pump 12 during a given period, and The data of the flow rate of the fluid used at the fluid supply destination 44 during a predetermined period corresponds to each other. Each neuron in the output layer is assigned the output data included in the training data. Diagnostic information on the pressure of the pressure tank 17, and the pump secondary pressure sensor provided on the discharge side of the pump 34, the secondary pressure during a specified period measured by the Diagnostic information of the flow rate during a predetermined period measured by the flow switch 16 installed in the Each of the diagnostic information of the fluid supply device 1, such as the operation information of the check valve 15 provided on the discharge side of the pump, These are matched.

[0085] Next, in step S12, the machine learning unit 402 stores the learning data in the learning data storage unit 401. For example, one piece of learning data is randomly selected from the plurality of sets of learning data stored.

[0086] Next, in step S13, the machine learning unit 402 performs The force data is input to the input layer of the prepared learning model 6 before learning (or during learning). As a result, output data is output from the output layer of the learning model 6 as an inference result. The data is generated by a learning model6 before (or during) learning. Before learning (or during learning), the output data output as the inference result is the learning data. This indicates information different from the output data (teacher data) contained in the data.

[0087] Next, in step S14, the machine learning unit 402 In step S14, the output data (teacher data) included in the selected learning data is The output data output from the output layer is compared with the inference results, and the weights of each synapse are adjusted. In this way, the machine learning unit 402 performs machine learning by synthesizing input data and output data. The correlation between the input data and the learning model 6 is then learned.

[0088] Next, in step S15, the machine learning unit 402 determines whether it is necessary to continue machine learning. For example, the error between the output data and the teacher data, or the learning data storage unit 401 The determination is made based on the remaining number of stored unlearned learning data.

[0089] In step S15, if the machine learning unit 402 determines to continue machine learning (step S16), If the answer is No in step S15, return to step S12 and perform step S14 on the learning model 6 being trained. Steps S12 to S14 are performed multiple times using unlearned learning data. In S15, when the machine learning unit 402 determines that the machine learning is to be ended (step S1 5), proceed to step S16.

[0090] Then, in step S16, the machine learning unit 402 calculates the The trained learning model 6 generated by adjusting the weights is stored in the trained model storage unit 40. 3, and the series of machine learning methods shown in FIG. 6 is terminated. Step S10 is a learning data storage step, steps S11 to S15 are machine learning steps, and step S 16 corresponds to the learned model storage process.

[0091] As described above, according to the machine learning device 4 and the machine learning method of this embodiment, Data on the operation status of the pump 12 during a predetermined period as input data included in the data, and From the data on the flow rate of the fluid used at the fluid supply destination 44 during a specified period, It is possible to provide a learning model 6 capable of inferring (diagnosing) the state of the device 1 with high accuracy. Cut.

[0092] (Condition diagnosis device 5) FIG. 7 is a block diagram showing an example of the condition diagnosis device 5 according to the first embodiment.

[0093] The condition diagnosis device 5 includes an input data acquisition unit 500, an inference unit 501, and a trained model memory. The condition diagnosis device 5 includes, for example, a computer shown in FIG. In this case, the input data acquisition unit 500 is configured with the communication I / F unit 22. 2 or an I / O device I / F unit 226, and the inference unit 501 and the output processing unit 503 are The trained model storage unit 502 is configured with the processor 212, and the trained model storage unit 502 is configured with the storage device 220. The condition diagnosis device 5 may be incorporated in the fluid supply device 1, or A management device higher than the fluid supply device 1 (for example, a controller for the equipment, a device for managing multiple equipment) It may be incorporated into a system (such as a facility management system).

[0094] The input data acquisition unit 500 is a measuring device 3 (for measuring the pump operation status) provided in the fluid supplying device 1. The flow rate sensor 31 and the flow rate sensor 32 are connected to the measuring device 3. Input data based on values ​​(data on the operation status of the pump 12 during a predetermined period and data on the fluid The interface unit acquires data on the flow rate of the fluid used at the supply destination 44. do.

[0095] The inference unit 501 converts the input data acquired by the input data acquisition unit 500 into a learning model 6. The inference process is performed by inputting the data into a machine learning device and diagnosing the state of the fluid supply device 1. A pre-trained learning model 6 in which supervised learning was performed using a machine learning method was used. do.

[0096] The inference unit 501 not only performs inference processing using the learning model 6, but also performs As a process, the input data acquired by the input data acquisition unit 500 is adjusted to a desired format, etc. The pre-processing function inputs the learning model 6 to the learning model 6 as a post-processing of the inference process. By applying a predetermined logical formula or calculation formula to the output data value, the fluid supply device 1 It also includes a post-processing function for finally diagnosing the state. It is preferable to store the trained model in the trained model storage unit 502 or another storage device (not shown). The inference results of the learning model 6 can be further improved by online learning and It can be used as learning data for re-learning.

[0097] The trained model storage unit 502 stores trained models used in the inference process of the inference unit 501. The trained model storage unit 502 stores the trained model 6. The number of learning models 6 to be used is not limited to one. For example, the number of input data may be different, or A plurality of learning models 6 using different machine learning techniques may be stored and selectively available. .

[0098] The output processing unit 503 outputs the inference result of the inference unit 501, that is, the state of the fluid supplying device 1. As a specific output means, various means can be adopted. The processing unit 503 notifies the operator of the state of the fluid supplying device 1 by display or sound, for example, The state of the fluid supplying device 1 is recorded as a history in, for example, a management device (not shown) above the fluid supplying device 1. The information is then stored in the storage unit of the management device of the fluid supplying device 1, and used for driving control of the motor 13, etc. It may be used.

[0099] (Condition diagnosis method) FIG. 8 is a flow chart showing an example of a condition diagnosis method by the condition diagnosis device 5 according to the first embodiment. In FIG. 8, the diagnostic information of the fluid supplying device 1 is normal "0" and abnormal "1". The following description will be given assuming that the two-value classifications are defined as either of the two values. The diagnostic method corresponds to the inference phase of FIG.

[0100] When a current is supplied to the motor 13, the motor 13 is rotated, and the pump 12 At this time, the series of state diagnosis methods shown in FIG. The diagnosis may be performed at a predetermined timing, for example. It can be at intervals or when a specific event occurs (when an operator issues an instruction, when a maintenance operation is performed, etc.). Good too.

[0101] First, in step S21, the input data acquisition unit 500 acquires the data of the measurement device 3 (pump operation Input data based on measurements taken by the status sensor 31 and the usage flow sensor 32) Data (data on the operation status of the pump 12 during a specified period and data on the use of the fluid supply destination 44) The input data is acquired for the same period as the specified period. Or it is required to include measurements taken by the measuring device 3 for a period longer than a predetermined period. can be.

[0102] Next, in step S22, the inference unit 501 performs preprocessing on the input data to generate a learning model. The input data is input to the input layer of learning model 6, and the output data is obtained from the output layer of learning model 6. do.

[0103] Next, in step S23, the inference unit 501 performs the following as an example of post-processing of supervised learning: The value of the output data (a number between 0 and 1) is compared with a predetermined threshold value. For example, If the value is less than the threshold, the diagnostic information is judged to be "normal"; if the value is greater than or equal to the threshold, If there is a problem, the diagnostic information is judged to be "abnormal" and the judgment result is output as the inference result. To exert effort.

[0104] Next, in step S24, the output processing unit 503 outputs the inference result of the inference unit 501 as Determine whether the diagnostic information of the fluid supply device 1 indicates "normal" or "abnormal" and If it is determined that the error is "abnormal", proceed to step S25. Go to 26.

[0105] Then, in step S25, the output processing unit 503 outputs information indicating "normal". It should be noted that step S25 may be omitted.

[0106] In step S26, the output processing unit 503 outputs information indicating "abnormality." The series of steps in the diagnostic method for the fluid supply device 1 shown in FIG. 8 is completed. Step S20 is an input data acquisition step, steps S21 and S22 are an inference step, Steps S23 to S25 correspond to the output processing step.

[0107] As described above, according to the condition diagnosis device 5 and the condition diagnosis method of the present embodiment, The state of the fluid supplying device 1 can be diagnosed with high accuracy without relying on experience.

[0108] Second Embodiment In the first embodiment, the machine learning method is a supervised learning method. However, in this embodiment, a case where "unsupervised learning" is adopted will be described. The measurement device constituting the fluid supply device 1 and the fluid supply device diagnostic system 2 according to the second embodiment The basic configurations and operations of the determination device 3, the machine learning device 4, and the condition diagnosis device 5 are the same as those of the first embodiment. Therefore, the following description will focus on the differences from the first embodiment.

[0109] (Machine Learning Device 4) The machine learning device 4 includes a learning data acquisition unit 400, as in the first embodiment (see FIG. 4). A learning data storage unit 401, a machine learning unit 402, and a trained model storage unit 403. Equipped with.

[0110] FIG. 9 shows data (unsupervised learning) used in the machine learning device 4 according to the second embodiment. FIG. 11 is a data configuration diagram showing an example.

[0111] When using "unsupervised learning" as machine learning, the learning data is The input data includes only the input data when the state of the fluid supplying device 1 in the In other words, the learning data may not include the output data. Depending on the machine learning method adopted by the company, the presence or absence of output data and the format of the output data are appropriately selected. It is possible.

[0112] When the presence or absence of an abnormality is diagnosed as the state of the fluid supply device 1, the diagnosis information is The information indicates that the device 1 is in a normal or abnormal state. In this case, the learning data according to the present embodiment is used when the fluid supplying device 1 is in a normal state, as shown in FIG. Data on the operating status of the pump 12 during a predetermined period when the fluid is normally This consists only of data on the flow rate of the fluid used in 4.

[0113] When acquiring the learning data, the learning data acquiring unit 400 acquires the learning data by Data on the operating status of the pump 12 during a predetermined period measured by the provided measuring device 3 The flow rate data of the fluid used at the fluid supply destination 44 is used as input data, and the measurement device The input data is acquired from the measuring device 3. The state of the fluid supply device 1 in the test is diagnosed, and the result of the diagnosis is normal. When the user inputs the data into the user terminal 8, the learning data acquisition unit 400 performs one learning process using only the input data. The learning data is then constructed and stored in the learning data storage unit 401.

[0114] The machine learning unit 402 inputs one or more sets of learning data to the learning model 6 to perform learning. The input data included in the training data and the diagnostic information indicating that the fluid supply device 1 is in a normal state A trained learning model 6 is generated by having the learning model 6 learn the correlation between the information and the In this embodiment, as a specific method of unsupervised learning by the machine learning unit 402, A case where an encoder is used will be described.

[0115] FIG. 10 shows an autoencoder model used in the machine learning device 4 according to the second embodiment. FIG.

[0116] The learning model 6 is configured as an autoencoder model shown in FIG. The coder model consists of l neurons (x1 to xl) in the input layer and m neurons in the hidden layer. It consists of neurons (y1~ym) in the input layer and o neurons (z1~zo) in the output layer. The number of neurons in the input layer and the output layer is the same, and the number of neurons in the hidden layer is There are also many.

[0117] Each neuron in the input layer is associated with one input data set contained in the training data. The intermediate layer is also called a hidden layer, and there may be multiple hidden layers. Between the input layer and the hidden layer, and between the hidden layer and the output layer, there are connections between the neurons of each layer. Synapses are connected, and each synapse is assigned a weight wi (i is a natural number). can be done.

[0118] The autoencoder model uses training data to extract the inputs contained in the training data. Data is input to the input layer, and the output data output from the output layer as the inference result is Compare the input data contained in the learning data and perform a process to adjust the weights wi. It learns patterns and trends in the input data.

[0119] The above series of steps is repeated a predetermined number of times, or the above error is reduced to a value smaller than the allowable value. When a certain condition for ending the learning is met, such as the machine learning being stopped, the trained As an autoencoder model (all weights wi associated with each synapse) is generated.

[0120] (Machine learning methods) FIG. 11 is a flow chart showing an example of a machine learning method performed by the machine learning device 4 according to the second embodiment. -Chart.

[0121] First, in step S30, the learning data acquisition unit 400 executes As a preliminary step, a desired number of training data are prepared and the prepared training data are used for learning. The learning data is stored in the learning data storage unit 401.

[0122] There are several methods for preparing training data. For example, Measure various measurements for a predetermined period of time when a specific fluid supply device 1 is in a normal state. The input data constituting the training data is prepared by acquiring the input data using the device 3. Then, By repeating this process, multiple sets of learning data can be prepared.

[0123] Next, in step S31, the machine learning unit 402 performs pre-learning The learning model 6 before learning prepared here is the one shown in FIG. It is composed of an autoencoder model, in which the weights of each synapse are set to an initial value. Each neuron in the input layer is input with the pump 12 as input data included in the learning data. Data on the operating status and data on the flow rate of the fluid used at the fluid supply destination 44 can be associated.

[0124] Next, in step S32, the machine learning unit 402 performs the learning data storage unit 401 to store the learning data. For example, one piece of learning data is randomly selected from the plurality of sets of learning data stored.

[0125] Next, in step S33, the machine learning unit 402 performs The force data is input to the input layer of the prepared learning model 6 before learning (or during learning). As a result, output data is output from the output layer of the learning model 6 as an inference result. The data is generated by a learning model6 before (or during) learning. Before learning (or during learning), the output data output as the inference result is the learning data. This indicates information that is different from the input data contained in the input data.

[0126] Next, in step S34, the machine learning unit 402 The input data included in the training data is inferred from the output layer in step S33. The resulting output data is compared with the weights of each synapse, and the machine Conduct learning.

[0127] Next, in step S35, the machine learning unit 402 determines whether it is necessary to continue machine learning. As a result, if it is determined that the operation should be continued (No in step S35), the step Return to step S32 and perform steps S32 to S34 on the learning model 6 being trained. If it is determined that the machine learning is to be ended (Yes in step S35), the process proceeds to step S36. move on.

[0128] Then, in step S36, the machine learning unit 402 The trained learning model 6 generated by adjusting the weights is stored in the trained model storage unit 40. 3, and the series of machine learning methods shown in FIG. 11 is completed. Step S30 is a learning data storage step, steps S31 to S35 are machine learning steps, and step S36 corresponds to the learned model storage step.

[0129] As described above, according to the machine learning device 4 and the machine learning method of this embodiment, The data on the operation status of the pump 12 and the data on the amount of fluid used at the fluid supply destination 44 The diagnostic information of the fluid supply device 1 can be inferred (diagnosed) with high accuracy from the flow rate data. A learning model 6 can be provided.

[0130] (Fluid supply device 1) The fluid supplying device 1 includes an input data acquiring unit 500 and a It comprises an inference unit 501, a learned model storage unit 502, and an output processing unit 503.

[0131] The inference unit 501 converts the input data acquired by the input data acquisition unit 500 into a learning model 6. The diagnostic information of the fluid supplying device 1 is inferred by inputting the diagnostic information to the inference process. A learning device 4 and a trained learning model 6 that has been trained using a machine learning method and unsupervised learning are used. can be done.

[0132] (Condition diagnosis method) FIG. 12 is a flowchart showing an example of a condition diagnosis method according to the second embodiment. In 12, the diagnostic information of the fluid supplying device 1 is a binary value indicating whether it is normal or abnormal. It will be explained as defined as a classification.

[0133] First, in step S40, the input data acquisition unit 500 acquires the data of the measurement device 3 (pump operation Input data (based on measurements taken by the status sensor 31 and the usage flow rate sensor 32) Data on the operation status of the pump 12 and the fluid used at the fluid supply destination 44 during a specified period of time. The flow rate of the fluid is obtained.

[0134] Next, in step S41, the inference unit 501 performs preprocessing on the input data to generate a learning model. The input data is input to the input layer of learning model 6, and the output data is obtained from the output layer of learning model 6. do.

[0135] Next, in step S42, the inference unit 501 performs the following as an example of post-processing of the unsupervised learning: The difference between the feature amount based on the input data and the feature amount based on the output data is calculated. For example, the parameters are expressed as feature vectors in a multidimensional space, and the difference is The inference unit 501 then determines whether the difference is less than a predetermined threshold. If it is, the diagnostic information is judged as "normal"; if it is equal to or greater than a certain threshold, the diagnostic information is judged as "abnormal." By judging that the condition is "normal," the judgment result is output as the inference result.

[0136] Next, in step S43, the output processing unit 503 outputs the inference result of the inference unit 501 as It is determined whether the diagnostic information of the fluid supplying device 1 indicates "normal" or "abnormal". If the result is "normal", the process proceeds to step S44. If the result is "abnormal", the process proceeds to step S45. Then, the process proceeds to step S45 (optional), and the series of steps in the fluid supply device diagnosis method shown in FIG. 12 is completed. In the condition diagnosis method, step S40 is an input data acquisition step, and steps S41 to S42 corresponds to the inference step, and steps S43 to S45 correspond to the output processing step.

[0137] As described above, according to the condition diagnosis device 5 and the condition diagnosis method of the present embodiment, The state of the fluid supplying device 1 can be diagnosed with high accuracy without relying on experience.

[0138] (Other embodiments) The present invention is not limited to the above-described embodiment, and the scope of the present invention is not limited to the above-described embodiment. Various modifications and variations are possible within the scope of the present invention. It is contained in the idea.

[0139] In the above embodiment, the machine learning unit 402 performs machine learning using neural network. The machine learning unit 402 may be any of the following: Other machine learning techniques such as decision trees may be used. , tree-based learning such as regression trees, ensemble learning such as bagging and boosting, recurrent neural Neural network type (deep neural network, convolutional neural network, etc.) learning), hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, k-means Clustering methods such as the average mean square method, principal component analysis, factor analysis, logistic regression, and other multivariate analyses; Examples include support vector machines.

[0140] In the present invention, the computer 200 shown in FIG. 2 is provided with the machine learning method according to the above embodiment. The machine learning program 230 is provided to execute each step of the process. In addition, the present invention relates to a computer 200 shown in FIG. A program (condition diagnosis program) 23 for executing each step of the condition diagnosis method It can also be provided in the form of 0.

[0141] (Inference device, inference method, and inference program) The present invention relates to a condition diagnosis device 5 (condition diagnosis method or condition diagnosis program) according to the above embodiment. ) as well as the inference used to diagnose the condition of the fluid supply device 1. It may also be provided in the form of an apparatus (an inference method or an inference program). The device (inference method or inference program) includes a memory and a processor, The processor may execute a series of processes, which may include: Data on the operation status of the pump 12 and the fluid used at the fluid supply destination 44 during a specified period of time. Input data acquisition process (input data acquisition) to acquire input data including the flow rate data of the fluid When the input data is acquired in the input data acquisition process, the status of the fluid supply device 1 is diagnosed. and an inference process (inference step) for inferring information.

[0142] By providing the inference device (inference method or inference program), the condition diagnosis device 5 It is possible to apply the inference device (inference method or When the inference program infers the state of the fluid supplying device 1, the machine learning device according to the above embodiment A condition diagnosis device using a trained learning model generated by a machine learning method and a device 4. It will be obvious to those skilled in the art that the inference method implemented by the inference unit 501 in the fifth embodiment may be applied. It can be understood as follows. [Explanation of symbols]

[0143] 1...fluid supply device, 12...pump, 13...motor, 14...inverter, 17...pressure tank, 41...fluid supply source, 44...fluid supply destination, 2...Condition diagnostic system, 3...Measuring device, 31...Pump operation status sensor, 32...Use flow rate sensor, 33...Pump primary Pressure sensor, 34...Pump secondary pressure sensor, 4...Machine learning device, 5...Condition diagnosis device, 6...Learning model, 400...learning data acquisition unit, 401...learning data storage unit, 402...machine learning unit, 40 3...Model storage unit, 500: input data acquisition unit, 501: inference unit, 502: model storage unit, 503: output processing Department, 200…Computer

Claims

1. A machine learning device that generates a learning model for diagnosing a state of a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, a learning data storage unit that stores a plurality of sets of learning data including, as input data, at least data on the operating status of the pump during a predetermined period and data on the usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; a machine learning unit that causes the learning model to learn a correlation between the input data and diagnostic information of the fluid supplying device by inputting a plurality of sets of the learning data to the learning model; A trained model storage unit that stores the learning model trained by the machine learning unit, The data of the usage flow rate included in the input data is time series data of a total usage flow rate obtained by summing up the measurement results of the usage flow rate measuring meters provided at the plurality of fluid supply destinations; Time series data of entry and exit records provided at the plurality of fluid supply destinations; Time series data of faucet usage amounts provided at the plurality of fluid supply destinations; Time series data of electricity usage provided at the plurality of fluid supply destinations, or Time series data of gas usage provided at the plurality of fluid supply destinations; That is, Machine learning device.

2. A machine learning device that generates a learning model for diagnosing a state of a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, a learning data storage unit that stores a plurality of sets of learning data including, as input data, at least data on the operating status of the pump during a predetermined period and data on the usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; a machine learning unit that causes the learning model to learn a correlation between the input data and diagnostic information of the fluid supplying device by inputting a plurality of sets of the learning data to the learning model; A trained model storage unit that stores the learning model trained by the machine learning unit, The diagnostic information includes: indicates that the fluid supply device is in a normal state or that the fluid supply device is in an abnormal state within a preset remaining life period; Machine learning device.

3. A machine learning device that generates a learning model for diagnosing a state of a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, a learning data storage unit that stores a plurality of sets of learning data including, as input data, at least data on the operating status of the pump during a predetermined period and data on the usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; a machine learning unit that causes the learning model to learn a correlation between the input data and diagnostic information of the fluid supplying device by inputting a plurality of sets of the learning data to the learning model; A trained model storage unit that stores the learning model trained by the machine learning unit, The diagnostic information includes: The fluid supply device is in a normal state, or the fluid supply device is in an abnormal state within any one of a plurality of preset remaining life periods. Machine learning device.

4. A machine learning device that generates a learning model for diagnosing a state of a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, a learning data storage unit that stores a plurality of sets of learning data including, as input data, at least data on the operating status of the pump during a predetermined period and data on the usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; a machine learning unit that causes the learning model to learn a correlation between the input data and diagnostic information of the fluid supplying device by inputting a plurality of sets of the learning data to the learning model; A trained model storage unit that stores the learning model trained by the machine learning unit, The diagnostic information includes, as a state of the fluid supply device, the diagnostic information regarding the condition of the pressure tank; The diagnostic information relating to the state of a pressure sensor provided on the discharge side of the pump; the diagnostic information relating to the state of a flow sensor provided on the discharge side of the pump; or The diagnostic information is related to a state of a check valve provided on a discharge side of the pump. Machine learning device.

5. The learning data is the diagnostic information indicating that the state of the fluid supply device is one of a plurality of states is further included as output data, and the input data and the output data are associated with each other; The machine learning unit is causing 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 the input data when the fluid supply apparatus is in a predetermined state; The machine learning unit is a correlation between the input data and the diagnostic information indicating that the fluid supplying apparatus is in the predetermined state is learned by the learning model through unsupervised learning; The machine learning device according to claim 1 .

7. The data on the operation status of the pump included in the input data is Time series data of the operation state of the pump, which indicates whether the pump is operating or stopped; Time series data of the rotation speed of the pump, or Time series data of a motor current value supplied to a motor which is a driving source of the pump. The machine learning device according to claim 1 .

8. 8. A condition diagnosis device that diagnoses a condition of a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, using a learning model generated by the machine learning device according to any one of claims 1 to 7, an input data acquisition unit that acquires input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; an inference unit that inputs the input data acquired by the input data acquisition unit into the learning model and infers diagnostic information of the fluid supply device, Condition diagnostic device.

9. 1. An inference device used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, The inference device comprises a memory and a processor; The processor, an input data acquisition process for acquiring input data including data on an operating status of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired by the input data acquisition process, an inference process is executed to infer diagnostic information of the fluid supply device; The data of the usage flow rate included in the input data is time series data of a total usage flow rate obtained by summing up the measurement results of the usage flow rate measuring meters provided at the plurality of fluid supply destinations; Time series data of entry and exit records provided at the plurality of fluid supply destinations; Time series data of faucet usage amounts provided at the plurality of fluid supply destinations; Time series data of electricity usage provided at the plurality of fluid supply destinations, or Time series data of gas usage provided at the plurality of fluid supply destinations; That is, Reasoning device.

10. 1. An inference device used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, The inference device comprises a memory and a processor; The processor, an input data acquisition process for acquiring input data including data on an operating status of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired in the input data acquisition process, a diagnosis of the fluid supply device is performed. An inference process for inferring information; The diagnostic information includes: indicates that the fluid supply device is in a normal state or that the fluid supply device is in an abnormal state within a preset remaining life period; Reasoning device.

11. 1. An inference device used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, The inference device comprises a memory and a processor; The processor, an input data acquisition process for acquiring input data including data on an operating status of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired by the input data acquisition process, an inference process is executed to infer diagnostic information of the fluid supply device; The diagnostic information includes: The fluid supply device is in a normal state, or the fluid supply device is in an abnormal state within any one of a plurality of preset remaining life periods. Reasoning device.

12. 1. An inference device used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, The inference device comprises a memory and a processor; The processor, an input data acquisition process for acquiring input data including data on an operating status of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired by the input data acquisition process, an inference process is executed to infer diagnostic information of the fluid supply device; The diagnostic information includes, as a state of the fluid supply device, the diagnostic information regarding the condition of the pressure tank; The diagnostic information relating to the state of a pressure sensor provided on the discharge side of the pump; the diagnostic information relating to the state of a flow sensor provided on the discharge side of the pump; or The diagnostic information is related to a state of a check valve provided on a discharge side of the pump. Reasoning device.

13. A machine learning method for generating a learning model for diagnosing a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, comprising: a learning data storage step of storing a plurality of sets of learning data in a learning data storage unit, the learning data including at least input data of an operating condition of the pump during a predetermined period of time and data of a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period of time; a machine learning process for inputting a plurality of sets of the learning data into the learning model, thereby causing the learning model to learn a correlation between the input data and diagnostic information of the fluid supply device; A trained model storage step of storing the trained model trained by the machine learning step in a trained model storage unit, The data of the usage flow rate included in the input data is time series data of a total usage flow rate obtained by summing up the measurement results of the usage flow rate measuring meters provided at the plurality of fluid supply destinations; Time series data of entry and exit records provided at the plurality of fluid supply destinations; Time series data of faucet usage amounts provided at the plurality of fluid supply destinations; Time series data of electricity usage provided at the plurality of fluid supply destinations, or Time series data of gas usage provided at the plurality of fluid supply destinations; That is, Machine learning methods.

14. A machine learning method for generating a learning model for diagnosing a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, comprising: a learning data storage step of storing a plurality of sets of learning data in a learning data storage unit, the learning data including at least input data of an operating condition of the pump during a predetermined period of time and data of a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period of time; a machine learning process for inputting a plurality of sets of the learning data into the learning model, thereby causing the learning model to learn a correlation between the input data and diagnostic information of the fluid supply device; A trained model storage step of storing the trained model trained by the machine learning step in a trained model storage unit, The diagnostic information includes: indicates that the fluid supply device is in a normal state or that the fluid supply device is in an abnormal state within a preset remaining life period; Machine learning methods.

15. A machine learning method for generating a learning model for diagnosing a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, comprising: a learning data storage step of storing a plurality of sets of learning data in a learning data storage unit, the learning data including at least input data of an operating condition of the pump during a predetermined period of time and data of a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period of time; a machine learning process for inputting a plurality of sets of the learning data into the learning model, thereby causing the learning model to learn a correlation between the input data and diagnostic information of the fluid supply device; A trained model storage step of storing the trained model trained by the machine learning step in a trained model storage unit, The diagnostic information includes: The fluid supply device is in a normal state, or the fluid supply device is in an abnormal state within any one of a plurality of preset remaining life periods. Machine learning methods.

16. A machine learning method for generating a learning model for diagnosing a fluid supply device including a pump that transfers a fluid and a pressure tank provided on a discharge side of the pump, comprising: a learning data storage step of storing a plurality of sets of learning data in a learning data storage unit, the learning data including at least input data of an operating condition of the pump during a predetermined period of time and data of a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period of time; a machine learning process for inputting a plurality of sets of the learning data into the learning model, thereby causing the learning model to learn a correlation between the input data and diagnostic information of the fluid supply device; A trained model storage step of storing the trained model trained by the machine learning step in a trained model storage unit, The diagnostic information includes, as a state of the fluid supply device, the diagnostic information regarding the condition of the pressure tank; The diagnostic information relating to the state of a pressure sensor provided on the discharge side of the pump; the diagnostic information relating to the state of a flow sensor provided on the discharge side of the pump; or The diagnostic information is related to a state of a check valve provided on a discharge side of the pump. Machine learning methods.

17. 8. A condition diagnosis method for diagnosing a condition of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, using a learning model generated by the machine learning device according to any one of claims 1 to 7, comprising: an input data acquisition step of acquiring input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; an inference step of inputting the input data acquired by the input data acquisition step into the learning model and inferring diagnostic information of the fluid supply device. How to diagnose the condition.

18. 1. An inference method used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, comprising: an input data acquisition step of acquiring input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired in the input data acquisition step, an inference step of inferring diagnostic information of the fluid supply device is executed; The data of the usage flow rate included in the input data is time series data of a total usage flow rate obtained by summing up the measurement results of the usage flow rate measuring meters provided at the plurality of fluid supply destinations; Time series data of entry and exit records provided at the plurality of fluid supply destinations; Time series data of faucet usage amounts provided at the plurality of fluid supply destinations; Time series data of electricity usage provided at the plurality of fluid supply destinations, or Time series data of gas usage provided at the plurality of fluid supply destinations; That is, Reasoning method.

19. 1. An inference method used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, comprising: an input data acquisition step of acquiring input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired in the input data acquisition step, an inference step of inferring diagnostic information of the fluid supply device is executed; The diagnostic information includes: indicates that the fluid supply device is in a normal state or that the fluid supply device is in an abnormal state within a preset remaining life period; Reasoning method.

20. 1. An inference method used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, comprising: an input data acquisition step of acquiring input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired in the input data acquisition step, a diagnosis of the fluid supply device is performed. an inference step of inferring information; The diagnostic information includes: The fluid supply device is in a normal state, or the fluid supply device is in an abnormal state within any one of a plurality of preset remaining life periods. Reasoning method.

21. 1. An inference method used to diagnose a state of a fluid supply device including a pump for transporting a fluid and a pressure tank provided on a discharge side of the pump, comprising: an input data acquisition step of acquiring input data including data on an operating state of the pump during a predetermined period and data on a usage flow rate of the fluid used at a fluid supply destination to which the fluid is supplied from the pressure tank during the predetermined period; When the input data is acquired in the input data acquisition step, an inference step of inferring diagnostic information of the fluid supply device is executed; The diagnostic information includes, as a state of the fluid supply device, the diagnostic information regarding the condition of the pressure tank; The diagnostic information relating to the state of a pressure sensor provided on the discharge side of the pump; the diagnostic information relating to the state of a flow sensor provided on the discharge side of the pump; or The diagnostic information is related to a state of a check valve provided on a discharge side of the pump. Reasoning method.

22. A method for causing a computer to execute each step of the machine learning method according to any one of claims 13 to 16, Machine learning programs.

23. A method for causing a computer to execute each step of the condition diagnosis method according to claim 17, How to diagnose the condition.

24. A method for causing a computer to execute each step of the inference method according to any one of claims 18 to 21, Inference program.

Citation Information

Patent Citations

  • Inspection device for feed water unit

    JP1996086278A

  • Method for detecting abnormality in pressure tank, and water supply system

    JP2006161337A

  • Diaphragm inspection method for liquid supply system and apparatus therefor

    JP3596909B2