Information processing device, machine learning device, inference device, information processing method, machine learning method and inference method

Abstract

To provide an information processing device, a machine learning device, an inference device, an information processing method, a machine learning method and an inference method capable of verifying an amount of fluid passing through a valve mechanism, verifying the presence / absence of unexpected fluid from a gab between a valve body and a valve seat, verifying the leakage amount, and verifying a sign of unexpected leakage of fluid from the valve mechanism.SOLUTION: An information processing device 250 of the present disclosure predicts a state of a valve mechanism, and obtains a valve mechanism state indicating the state of the valve mechanism based on input information that is a predetermined variation between a valve body and a valve seat.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, a machine learning apparatus, an inference apparatus, an information processing method, a machine learning method, and an inference method.

Background Art

[0002] Conventionally, a reservoir valve having a plus-side valve seat with a fluid discharge port in a container and a plus-side valve capable of opening and closing the discharge port according to the pressure in the container is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a valve mechanism including a valve element and a valve seat provided on a fluid flow path, due to the importance of managing the fluid flowing inside, it is required that the valve mechanism reliably closes the flow path, that it is possible to verify the amount of fluid passing through the valve mechanism, that it is possible to verify the presence or absence of unexpected fluid leakage between the valve element and the valve seat, and that in the event that fluid is leaking from the valve mechanism, it is possible to verify the amount of the leakage. Further, in order to prevent fluid leakage from the valve mechanism due to unforeseen circumstances or to minimize the leakage, it is also required to verify signs of unexpected fluid leakage from the valve mechanism. In the case of handling fluids having volatility and flammability, or fluids having harmfulness to the human body and the environment, this requirement has been increasing further in recent years due to the growing consideration for animals, plants, and the environment. However, in conventional valve mechanisms, there has been a problem that until the flow path is closed and released, it is not possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve element and the valve seat, the amount of the leakage, and signs of unexpected fluid leakage from the valve mechanism. This problem has not been solved at all in the valve mechanism used in a reservoir valve that handles volatile fluids and the like shown as an example of the valve mechanism, and exists as a general problem of the valve mechanism.

[0005] The present disclosure has been made to solve the above problems, and an object thereof is to provide an information processing device, a machine learning device, an inference device, an information processing method, a machine learning method, and an inference method capable of verifying the amount of fluid passing through a valve mechanism, the presence or absence of unexpected fluid leakage between a valve element and a valve seat, the amount of the leakage, and signs of unexpected fluid leakage from the valve mechanism.

Means for Solving the Problems

[0006] An information processing device according to the present disclosure is an information processing device that predicts the state of a valve mechanism, and obtains a valve mechanism state indicating the state of the valve mechanism based on input information that is a predetermined variable between a valve element and a valve seat.

Effects of the Invention

[0007] The information processing apparatus, machine learning apparatus, inference apparatus, information processing method, machine learning method, and inference method according to the present disclosure can verify the amount of fluid passing through a valve mechanism, verify the presence or absence of unexpected fluid leakage between a valve body and a valve seat, verify the amount of the leakage, and verify a sign of unexpected fluid leakage from the valve mechanism.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Modes for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing the present disclosure will be described with reference to the drawings. In the following, the scope necessary for the description for achieving the object of the present disclosure is schematically shown, and mainly the scope necessary for the description of the corresponding part of the present disclosure will be described, and the parts where the description is omitted are assumed to be based on known techniques.

[0010] Embodiment 1. As an explanation of the valve system of the present disclosure, in Embodiment 1, a valve system applied to a reservoir valve is used. However, the valve system of the present disclosure is not limited to that applied to the reservoir valve, and can be appropriately used for a general valve mechanism. The same applies to the valve systems in Embodiment 2 and Embodiment 3 described later.

[0011] FIG. 1 is a schematic diagram showing a valve system 200 according to Embodiment 1. The valve system 200 includes a reservoir valve 5, a machine learning device 240, an information processing device 250, and a network 270 connecting each of them.

[0012] FIG. 2 is a schematic diagram showing the reservoir valve 5 of FIG. 1. The reservoir valve 5 is connected to the opening of the tank 4 via an upstream flange 4b. In FIG. 2, a part of the reservoir valve 5 is shown in a cross section in a plane including the axis of the flow path.

[0013] The tank 4 stores a fluid such as a combustible gas or liquid. Further, the fluid stored in the tank 4 also includes the fluid volatilized from the stored fluid. Examples of the combustible gas or liquid include fluids such as fossil fuels and volatile gases. The shape of the tank 4 is a shape such as a spherical shape, a cylindrical shape, a rectangular parallelepiped shape, and a cubic shape.

[0014] In the present Embodiment 1, the shape of the tank 4 is a shape in which the horizontal cross-sectional area of the tank 4 decreases as it goes toward the upper end. An attachment portion 4a is installed at the upper end of the tank 4. A through hole communicating with the inside of the tank 4 is formed in the attachment portion 4a. Thereby, the fluid inside the tank 4 is efficiently discharged through the attachment portion 4a.

[0015] The base of the buffer valve 5 is attached to the attachment portion 4a via the upstream flange 4b. In the first embodiment, it is assumed that the tank 4 is on the upstream side and the buffer valve 5 is installed on the downstream side with respect to the tank 4.

[0016] The buffer valve 5 can discharge the fluid inside the tank 4 to the atmosphere according to the internal pressure of the tank 4, and can also allow the atmosphere, which is the fluid for inhalation, to flow into the inside of the tank 4. That is, the buffer valve 5 can adjust the pressure inside the tank 4.

[0017] In the first embodiment, the tank 4 and the buffer valve 5 are installed outdoors and are exposed to the atmosphere.

[0018] The buffer valve 5 includes a main portion 10, an intake portion 20, and a discharge portion 40. The main portion 10 is a T-shaped pipe member. Each of the ends of the T-shaped pipe member of the main portion 10 is an inlet-side opening end portion 10a that opens downward in the vertical direction, an outlet-side opening end portion 10b that opens upward in the vertical direction, and an intake-side opening end portion 10c that opens in the horizontal direction.

[0019] The main portion 10 is installed in a posture where the inlet-side opening end portion 10a is on the lower side and the outlet-side opening end portion 10b is on the upper side. Let the flow path leading from the inlet-side opening end portion 10a to the outlet-side opening end portion 10b be the main flow path 110. The main portion 10 is installed such that the axis of the main flow path 110 is along the vertical direction. The main flow path 110 extends toward the discharge portion 40. The main flow path 110 extending to the discharge portion 40 will be described later.

[0020] Let the flow path that branches from the main flow path 110 and reaches the intake-side opening end portion 10c be the branch flow path 111. The axis of the branch flow path 111 is along the horizontal direction. The intake portion 20 is connected to the intake-side opening end portion 10c of the main portion 10.

[0021] The intake section 20 has an intake section main body 21 and an intake valve mechanism 22 provided on the intake section main body 21. The intake section main body 21 is a tubular member having two open end portions.

[0022] One end of the intake section main body 21 is a connection-side opening end portion 21a that opens in the horizontal direction. An intake port 21b that opens vertically downward is formed at the other end of the intake section main body 21. The intake flow path connecting the connection-side opening end portion 21a and the intake port 21b is defined as the intake flow path 120. Here, the other end of the intake section main body 21 that constitutes the periphery of the intake port 21b is defined as the intake valve seat 21x.

[0023] The intake valve mechanism 22 has an intake valve 23 that is an on-off valve, an intake valve shaft 24 fixed to the intake valve 23, and an intake valve guide 25 installed on the intake section main body 21. When the intake valve 23 contacts the intake valve seat 21x that constitutes the periphery of the intake port 21b, the intake port 21b is closed. When a gap is generated between the intake valve 23 and the intake valve seat 21x, the intake port 21b is opened. That is, the intake valve 23 can open and close the intake flow path 120.

[0024] The intake valve guide 25 supports the intake valve shaft 24 so as to be movable along the vertical direction. Thereby, the intake valve 23 can move between an intake closed position and an intake open position as the intake valve shaft 24 moves along the vertical direction. The intake valve 23 is an open valve. The intake valve 23 can move toward the intake closed position by falling along the intake valve guide 25 due to the self-weights of the intake valve 23 and the intake valve shaft 24.

[0025] When the intake valve 23 is in the intake closed position, the intake valve 23 closes the intake port 21b. That is, since the lower surface of the intake valve 23 is in contact with the intake valve seat 21x, the intake flow path 120 is closed, and the communication between the intake flow path 120 and the outside of the reservoir valve 5 is blocked.

[0026] When the intake valve 23 moves upward against its own weight from the intake closed position toward the intake open position, a gap is generated between the intake valve 23 and the intake valve seat 21xb. That is, the intake passage 120 is opened, and the intake passage 120 is in a state of communicating with the atmosphere outside the breather valve 5.

[0027] The intake side opening end 10c and the connection side opening end 21a are connected, and the intake part 20 is connected to the intake side opening end 10c of the main part 10. Thereby, the intake passage 120 inside the intake part main body 21 communicates with the branch passage 111 inside the main part 10. That is, the intake passage 120 extends along the horizontal direction from the branch passage 111.

[0028] A discharge part 40 is connected to the outlet side opening end 10b of the main part 10. The discharge part 40 includes a discharge part main body 41, a vent cover 47, a discharge valve mechanism 50 installed on the vent cover 47, a detection device 60, and a valve contact member 70.

[0029] The discharge part main body 41 is composed of a tubular introduction part 42 and an air discharge part 43 provided so as to surround one opening end of the introduction part 42. The discharge part main body 41 is installed with the pipeline of the introduction part 42 in a posture along the vertical direction.

[0030] FIG. 3 is a top view showing the introduction part 42 of FIG. 2. FIG. 4 is an enlarged view showing the part including the detection device 60 of FIG. 2. In FIG. 3, since the upper surface of the introduction part 42 is shown, the valve contact member 70 is not shown. The description will be continued based on FIGS. 2-4.

[0031] The downward opening end of the introduction part 42 is defined as the discharge part inlet side opening end 42a. The upward opening end of the introduction part 42 in the vertical direction is defined as the valve side end 42b. The opening of the valve side end 42b is defined as the valve side opening 42c, and the end face of the valve side end 42b is defined as the main body end face 42d. The discharge part inlet side opening end 42a and the outlet side opening end 10b of the main part 10 are connected.

[0032] The introduction part 42 is formed with one detector installation space 42e. The detector installation space 42e opens to the main body end face 42d, and is a space that opens to the outer peripheral side of the introduction part 42 through the wall of the introduction part 42 from the opening on the main body end face 42d. A part of the detection device 60 is installed in the detector installation space 42e.

[0033] The detection device 60 includes a detector 61 and a wiring 62 that transmits the signal of the detector 61 to an input / output device (not shown). The detector 61 can detect a predetermined variable of the detection target.

[0034] At this time, the detector 61 can detect a predetermined variable of the detection target in the direction the detector 61 is directed, and that direction is defined as the detection direction of the detector 61. That is, the detection direction of the detector 61 is the direction in which the detector 61 can detect a predetermined variable of the detection target.

[0035] One detector 61 and a part of the wiring 62 extending from the detector 61 are installed in the detector installation space 42e. The detector 61 is installed such that the detection direction of the detector 61 is from the detector installation space 42e toward the outside of the main body end face 42d. That is, the detector 61 can detect a predetermined variable of the detection target beyond the end face on the valve side end 42b side of the introduction part 42.

[0036] The wiring 62 extends from the outer periphery of the introduction part 42 toward the outside through the detector installation space 42e. The wiring 62 is connected to an input / output device (not shown). The input / output device can transmit the predetermined variable detected by the detector 61 onto the network 270.

[0037] The network 270 is an information transmission network constructed by wire or wirelessly. The network 270 may be connected to the Internet to enable information transmission. Devices connected to the network 270 can acquire the signal of the detector 61 transmitted onto the network 270. Other devices connected to the network 270 will be described later.

[0038] A valve contact member 70 is installed at the valve-side end portion 42b. FIG. 5 is a top view showing the valve contact member 70 of FIG. 2. The description will continue based on FIGS. 2 to 5.

[0039] The valve contact member 70 is an annular member. In the valve contact member 70, the cross-section along a line in the annular radial direction is L-shaped. That is, the valve contact member 70 has a shape in which an annular flat plate material is bent perpendicular to the plane on the entire inner peripheral side thereof. The valve contact member 70 is formed in a shape corresponding to the shape of the main body end face 42d.

[0040] The valve contact member 70 is installed in the introduction portion 42 so as to cover the main body end face 42d of the introduction portion 42 and a part of the inner peripheral surface of the introduction portion 42 continuous from the main body end face 42d. Here, the surface of the valve contact member 70 facing the discharge valve 53 is defined as the valve-facing surface 70a. The discharge valve 53 will be described later.

[0041] The opening of the detector installation space 42e formed in the main body end face 42d is closed by installing the valve contact member 70 in the introduction portion 42. That is, the detector 61 is installed in the detector installation space 42e covered by the valve contact member 70. Further, the detection direction of the detector 61 is directed toward the discharge valve 53 through the valve-facing surface 70a.

[0042] The valve contact member 70 is screwed and installed in the introduction portion 42. A screwing attachment location is provided on the outer peripheral portion of the valve contact member 70. However, for installing the valve contact member 70 in the introduction portion 42, well-known methods other than screwing may be used. The valve contact member 70 is preferably made of a material that does not significantly reduce the detection ability of the detector 61. For example, the valve contact member 70 is made of stainless steel.

[0043] It is preferable to devise the shape of the valve contact member 70 so as not to significantly reduce the detection ability of the detector 61. For example, by making the valve contact member 70 thinner, a significant reduction in the detection ability of the detector 61 can be prevented. As shown in FIGS. 2-5, the inner peripheral surface of the introduction portion 42 of the portion where the detector installation space 42e is formed protrudes further inward, and the thickness of the introduction portion 42 of the portion where the detector installation space 42e is formed is thicker than the thickness of other portions. Further, the valve contact member 70 is formed in a shape corresponding to the shape of the main body end surface 42d. However, it is not limited to this. For example, the thickness of the introduction portion 42 may be uniformly equal, that is, no portion protruding inward is formed on the inner peripheral surface of the introduction portion 42, and the inner peripheral surface of the introduction portion 42 viewed from the axial direction may be circular. Even in this case, the valve contact member 70 is formed in a shape corresponding to the shape of the main body end surface 42d.

[0044] Here, the valve-side end portion 42b of the introduction portion 42 is taken as the valve seat main body 3. The valve seat main body 3 may be a cylindrical member that constitutes a part of the flow path closed by the valve body so that the valve-side end portion 42b of the introduction portion 42 constitutes a part of the discharge flow path 140. Further, the main body end surface 42d of the introduction portion 42 is the end surface of the flow path formed in the valve seat main body 3 and is the main body end surface of the valve seat main body 3 facing the valve body. A detector installation space 42e is formed in the valve seat main body 3.

[0045] Also, the valve seat main body 3 which is the valve-side end portion 42b of the introduction portion 42 and the valve contact member 70 are taken as the valve seat 2. Therefore, the valve seat 2 constitutes a part of the flow path. Also, the valve seat 2 and the detection device 60 are taken as the valve seat mechanism 1. In this case, the valve-facing surface 70a of the valve contact member 70 is taken as the valve seat end surface 2a.

[0046] That is, the valve seat end surface 2a faces the lower surface of the discharge valve 53 which is the valve body, and when the discharge valve 53 closes the discharge flow path 140, it is the portion where the discharge valve 53 directly contacts. Further, a gap is formed between the discharge valve 53 and the valve seat end surface 2a, and when the discharge flow path 140 is opened, the fluid in the tank 4 is discharged through the gap between the discharge valve 53 and the valve seat end surface 2a.

[0047] In addition, the detection direction is toward the discharge valve 53 which is a valve body beyond the valve seat end face 2a in the state where the detector 61 is installed in the detector installation space 42e.

[0048] Returning to FIG. 2 and continuing the description. The air discharge portion 43 is formed so as to surround the valve-side end portion 42b of the introduction portion 42. An opening is formed in the upper end side of the air discharge portion 43. The upper end side of the air discharge portion 43 is defined as the valve mechanism-side opening end portion 43b. A plurality of discharge ports 43a that open in the horizontal direction are formed in the lower side of the valve mechanism-side opening end portion 43b of the air discharge portion 43, that is, in the body portion of the air discharge portion 43.

[0049] The vent cover 47 is connected to the valve mechanism-side opening end portion 43b. The vent cover 47 closes the opening of the valve mechanism-side opening end portion 43b. A well-known configuration can be adopted for the connection of the vent cover 47 to the valve mechanism-side opening end portion 43b. The discharge valve mechanism 50 is installed on the vent cover 47.

[0050] The discharge valve mechanism 50 has a discharge valve 53 which is a valve body capable of closing the valve-side opening 42c, a discharge valve shaft 54 fixed to the discharge valve 53, and a discharge valve guide 55 installed on the vent cover 47.

[0051] In the state where the vent cover 47 is connected to the valve mechanism-side opening end portion 43b, the discharge valve guide 55 extends vertically downward from the vent cover 47. The discharge valve guide 55 supports the discharge valve shaft 54 so as to be movable along the vertical direction.

[0052] The discharge valve 53 is movable between a discharge closed position and a discharge open position by the discharge valve shaft 54 moving along the vertical direction. The discharge valve 53 is an open valve.

[0053] The discharge valve 53 can move toward the discharge closed position by falling along the discharge valve guide 55 due to the self-weight of the discharge valve 53 and the discharge valve shaft 54.

[0054] When the discharge valve 53 is in the discharge closed position, the discharge valve 53 closes the valve-side opening 42c. Specifically, when the discharge valve 53 is in the discharge closed position, the surface of the discharge valve 53 contacts the valve facing surface 70a of the valve contact member 70. At this time, around the valve-side opening 42c, the surface of the discharge valve 53 and the valve facing surface 70a are in continuous contact.

[0055] In the first embodiment, the surface of the discharge valve 53 that contacts the valve facing surface 70a is the lower surface of the discharge valve 53. That is, the detection device 60 is installed so as to face the lower surface of the discharge valve 53 and can detect the state up to the discharge valve 53.

[0056] When the discharge valve 53 moves against its own weight from the discharge closed position toward the discharge open position, a gap is generated between the discharge valve 53 and the valve-side opening 42c.

[0057] In the discharge section 40, a discharge flow path 140 is formed that passes from the discharge section inlet-side opening end 42a through the valve-side opening 42c and leads to a plurality of discharge ports 43a. When the discharge valve 53 is in the discharge closed position, the main flow path 110 extending from the inside of the main section 10 and the discharge flow path 140 are in a state where communication is blocked.

[0058] When the discharge valve 53 moves from the discharge closed position toward the discharge open position and a gap is generated between the discharge valve 53 and the valve-side opening 42c, the main flow path 110 extending from the inside of the main section 10 and the discharge flow path 140 are in a communicating state.

[0059] Next, the operation of the reservoir valve 5 will be described. The reservoir valve 5 operates based on the internal pressure of the tank 4.

[0060] First, when the internal pressure of the tank 4 is normal pressure, each of the intake valve 23 and the discharge valve 53 is in a closed state. In this state, intake from the intake valve 23 and exhaust from the discharge valve 53 are not performed, and the internal pressure in the tank 4 is maintained.

[0061] Next, the case where the internal pressure of the tank 4 becomes lower than the normal pressure will be described. In the intake section 20, since the internal pressure of the intake section 20 is low, the intake valve 23 is pushed by the atmosphere. Therefore, the intake valve 23 moves from the intake closed position toward the intake open position.

[0062] Specifically, the intake valve 23 is pushed by the atmosphere and rises against its own weight. The total weight of the intake valve 23 and the intake valve shaft 24 is set to a weight that rises when the internal pressure of the intake section 20 becomes equal to or lower than the normal pressure and is pushed by the atmosphere.

[0063] When the intake valve 23 rises against its own weight, the intake passage 120 is opened, and the atmosphere enters the inside of the intake section 20 from the intake port 21b.

[0064] On the other hand, since the internal pressure of the discharge section 40 is low, the discharge valve 53 has moved downward due to its own weight, and the discharge valve 53 remains in the discharge closed position. That is, the valve-side opening 42c is maintained in a state of being closed by the discharge valve 53.

[0065] As a result, the atmosphere flows in from the intake port 21b, and eventually the internal pressure of the tank 4 increases. The intake valve 23 moves to the intake closed position due to its own weight and closes the intake port 21b. In this way, the internal pressure of the tank 4 becomes the pressure set by the weight of the intake valve 23.

[0066] Next, the case where the internal pressure of the tank 4 is higher than the normal pressure will be described. At this time, in the intake section 20, since the internal pressure of the intake section 20 is high, the intake valve 23 remains in the intake closed position due to the internal pressure of the intake section 20 and its own weight. Therefore, the intake port 21b is closed.

[0067] In the discharge section 40, since the internal pressures of the tank 4, the main section 10, and the intake section 20 are high, the discharge valve 53 moves from the discharge closed position toward the discharge open position. Specifically, the discharge valve 53 is pushed by the fluid inside the tank 4 and rises against its own weight. Note that the total weight of the discharge valve 53 and the discharge valve shaft 54 is set to a weight that rises against its own weight when the internal pressure of the main section 10 becomes normal pressure or higher.

[0068] Accordingly, the fluid in the tank 4 is discharged from inside the tank 4 through the main flow path 110, the valve-side opening 42c, and the discharge flow path 140. That is, when the internal pressure of the discharge section 40 becomes higher than the normal pressure, the discharge valve mechanism 50 connects the main flow path 110 and the discharge flow path 140. Thereby, the fluid can be discharged from inside the tank 4 through the discharge flow path 140 to the downstream side of the discharge valve mechanism 50.

[0069] When the fluid in the tank 4 is discharged from the discharge section 40, the discharge valve 53 eventually moves to the discharge closed position by its own weight based on the internal pressure of the tank 4, closing the valve-side opening 42c.

[0070] Thereby, the internal pressure of the tank 4 becomes the pressure based on the weight of the discharge valve 53. In this way, the reservoir valve 5 can maintain the pressure in the tank 4 at a constant pressure.

[0071] Note that the fluid inside the tank 4 includes, as described above, the fluid inside the tank 4 and the fluid obtained by volatilizing and gasifying the fluid. Therefore, the discharged fluid also includes the fluid inside the tank 4 and the fluid obtained by volatilizing and gasifying the fluid.

[0072] Next, the detection device 60 will be described. The detector 61 can constantly detect the states of the discharge valve 53 and the valve seat 2. The predetermined variable of the detection target detected by the detector 61 can be recognized as the state of the valve mechanism, which is the state of the discharge valve 53 or the state between the discharge valve 53 and the valve seat 2.

[0073] For example, as the detector 61, a distance sensor capable of measuring the distance to the lower surface of the discharge valve 53 can be used. In this case, the state of the discharge valve 53 that can be detected from the detection result of the detector 61 is the current distance to the discharge valve 53, that is, the current position of the discharge valve 53.

[0074] Note that the detector 61 does not have to be a distance sensor. For example, a vibration sensor directed toward the lower surface of the discharge valve 53 can also be used for the detector 61. The vibration of the valve-side end portion 42b facing the discharge valve 53 may be measured by the vibration sensor. Even if a vibration sensor is used for the detector 61, the state of the valve mechanism can be detected in the same manner as the distance sensor.

[0075] Also, for example, an acoustic sensor directed toward the lower surface of the discharge valve 53 may be used for the detector 61. The sound between the discharge valve 53 and the acoustic sensor may be measured. The acoustic sensor can detect the operating sound of the discharge valve 53 and the sound of the fluid between the valve seat and the discharge valve 53. Even if an acoustic sensor is used for the detector 61, the state of the valve mechanism can be detected in the same manner as the distance sensor. In the above, three types of sensors are exemplified as the sensors used for the detector 61, but the types of sensors used for the detector 61 are not limited to the above three types, and various types of sensors can be used for the detector 61.

[0076] The machine learning device 240 is a device that operates as the main body in the learning phase of machine learning. FIG. 6 is a configuration diagram showing the machine learning device 240 of FIG. 1. FIG. 7 is a conceptual diagram showing the elements of machine learning implemented by the machine learning device 240 of FIG. 6. The machine learning device 240 includes a machine learning control unit 241, a machine learning communication unit 242, a learning data storage unit 243, and a machine learning model storage unit 244.

[0077] The machine learning control unit 241 generates a learning model 245 from which output information corresponding to the input information can be obtained. The machine learning control unit 241 uses one or more learning data 246 to generate the learning model 245. The learning data 246 is composed of learning input information 201a and a learning valve mechanism state 201b corresponding to the learning input information 201a.

[0078] Here, the input information is a predetermined variable of the detection target detected by the detector 61, and indicates a predetermined variable between the discharge valve 53, which is the valve body detected from the valve seat 2, and the valve seat 2. The valve mechanism state indicates the state of the valve mechanism, that is, the state of the discharge valve 53, which is the valve body, and the valve seat 2, and the state between the discharge valve 53 and the valve seat 2. Note that the valve mechanism is composed of the discharge valve 53, which is the valve body, and the valve seat 2, or the valve seat mechanism 1.

[0079] The learning data 246 is data used as training data, verification data, and test data, which are teacher data in supervised learning. Further, the learning valve mechanism state 201b is data used as a correct label in supervised learning.

[0080] Note that the learning input information 201a and the learning valve mechanism state 201b, which is the valve mechanism state corresponding to the learning input information 201a, are those in a state where the input information 200a and the valve mechanism state 200b, which is the valve mechanism state corresponding to the input information 200a, are stored in the learning data storage unit 243 as the learning data 246.

[0081] The input information 200a and the valve mechanism state 200b are obtained by various product tests such as tests and trials on the bleeder valve 5. The learning data storage unit 243 in which the input information 200a, the valve mechanism state 200b, the learning input information 201a, the learning valve mechanism state 201b, and the learning data 246 are stored will be described later.

[0082] The machine learning control unit 241 can cause the learning model 245 to learn the correlation between the learning input information 201a and the learning valve mechanism state 201b in one or more pieces of learning data 246. Thereby, the machine learning control unit 241 can generate a learned learning model 245.

[0083] The learning model 245 employs the structure of a neural network. The learning model 245 has an input layer 245a, an intermediate layer 245b, and an output layer 245c. The input layer 245a has a number of neurons corresponding to the number of parameters of the learning input information 201a. The output layer 245c has a number of neurons corresponding to the number of conditions of the learning valve mechanism state 201b.

[0084] Synapses (not shown) that connect the respective neurons are formed between the layers. Each synapse can be weighted.

[0085] The machine learning control unit 241 adjusts a weight parameter group composed of the weights of the respective synapses by machine learning. The weight parameter group is reflected in the learning model 245.

[0086] In the machine learning control unit 241, each parameter of the learning input information 201a is input to each neuron of the input layer 245a, and through the learning model 245, a learning result valve mechanism state 201c indicating the state of the valve mechanism corresponding to the learning input information 201a is output. The machine learning control unit 241 examines the learning result valve mechanism state 201c and adjusts the weight of each synapse based on the examination result.

[0087] When the learning model 245 is configured as a regression model, the learning valve mechanism states 201b are each output as numerical values normalized within a predetermined range (for example, 0 to 1). Also, when the learning model 245 is configured as a classification model, the learning valve mechanism states 201b are each output as numerical values normalized within a predetermined range (for example, 0 to 1) as scores (accuracies) for each class.

[0088] The learning data storage unit 243 can store a plurality of learning data 246 as a database. Note that the specific configuration of the database constituting the learning data storage unit 243 can be designed as appropriate.

[0089] Input information 200a obtained in advance by product testing or the like and the valve mechanism state 200b corresponding to the input information 200a are input to the learning data storage unit 243. Each of the input information 200a and the valve mechanism state 200b input to the learning data storage unit 243 is stored as learning input information 201a and learning valve mechanism state 201b. Therefore, the learning valve mechanism state 201b corresponds to the learning input information 201a. Thereby, one piece of learning data 246 is stored.

[0090] The learning input information 201a and the learning valve mechanism state 201b are based on the input information 200a obtained by the detector 61 in the product test of the bleed valve 5 and the valve mechanism state 200b actually observed and measured in the product test or the like.

[0091] The aforementioned product tests are those carried out in the design, prototype production, and pre-shipment product inspection of the bleed valve 5. The detector 61 acquires a predetermined variable of the detection target detected by various product tests as the input information 200a.

[0092] Also, during product testing, the amount of fluid passing between the discharge valve 53 and the valve seat 2 that is observed or measured simultaneously with the detection of the variable, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of such leakage, and signs of unexpected fluid leakage from between the valve body and the valve seat are acquired as the valve mechanism state 200b. In product testing, the reservoir valve 5 and the machine learning device 240 are connected so as to be able to exchange information, and the variables detected by the detector 61 during the product test are sequentially input as input information 200a into the learning data storage unit 243. Then, the valve mechanism state 200b corresponding to the input information 200a determined by the judgment of the operator or the like is input into the learning data storage unit 243. Note that the variables detected in the product test may be stored in a storage device (not shown), and after determining the corresponding valve state, the operator may input such information as input information 200a and the valve mechanism state 200b corresponding to the input information 200a into the learning data storage unit 243. In this case, the reservoir valve 5 and the machine learning device 240 do not necessarily have to be connected so as to be able to exchange information.

[0093] In product testing, even when the opening degree of the discharge valve 53 is zero, that is, when the flow path is closed by the discharge valve 53, a predetermined variable to be detected is detected by the detector 61. That is, in product testing, since the variables to be detected are constantly detected by the detector 61, time-series data of those variables can be acquired.

[0094] In product testing, the opening degree of the discharge valve 53 and the flow rate of the fluid discharged from the discharge valve 53 are actually measured using a measuring instrument or the like, and the amount of fluid passing between the discharge valve 53 and the valve seat 2 obtained based on the measurement results can be acquired as the valve mechanism state 200b.

[0095] Also, the observed results of the discharge valve 53 and the valve seat 2, such as whether the state of the valve seat 2 and the discharge valve 53 is a normal state, an abnormal state, and if it is an abnormal state, what kind of abnormal state it is, can be acquired as the valve mechanism state 200b by an operator who can determine the state of the valve seat 2 and the discharge valve 53.

[0096] Furthermore, when the state of the discharge valve 53 and the valve seat 2 is an abnormal state, the presence or absence of fluid passing between the discharge valve 53 and the valve seat 2 is regarded as the presence or absence of unexpected fluid leakage, and the presence or absence of such unexpected fluid leakage can be acquired as the valve mechanism state 200b.

[0097] Furthermore, when the state of the discharge valve 53 and the valve seat 2 is an abnormal state, the amount of fluid passing between the discharge valve 53 and the valve seat 2 is regarded as the amount of unexpected fluid leakage, and the amount of such unexpected fluid leakage can be acquired as the valve mechanism state 200b.

[0098] Furthermore, when the state of the discharge valve 53 and the valve seat 2 is an abnormal state and the amount of fluid passing between the discharge valve 53 and the valve seat 2 is not zero, a sign of unexpected fluid leakage can be acquired as the valve mechanism state 200b. That is, when the state of the discharge valve 53 and the valve seat 2 is an abnormal state and the amount of fluid passing between the discharge valve 53 and the valve seat 2 is not zero, for the time-series input information over a certain period when the amount of fluid passing between the discharge valve 53 and the valve seat 2 before that was zero, the valve mechanism state 200b is acquired as a sign of unexpected fluid leakage.

[0099] Product tests are also carried out for those that reproduce the occurrence of defects. For example, there are product tests assuming a situation where some foreign matter is trapped between the valve seat 2 and the discharge valve 53, or product tests carried out in a state where at least one of the valve seat 2 and the discharge valve 53 is corroded. Furthermore, product tests such as operating the valve mechanism for a long time simulating the actual operating situation to confirm the state of aging deterioration and durability are also conceivable.

[0100] In such product tests, it is determined that the state of the discharge valve 53 and the valve seat 2 is abnormal due to defects or aging deterioration, and the presence or absence of unexpected fluid leakage, the amount of unexpected fluid leakage, and a sign of unexpected fluid leakage can be acquired as the valve mechanism state 200b.

[0101] Furthermore, not only product tests, but also input information 200a obtained from the currently operating preservation valve 5 and information that can be obtained through maintenance inspections and the like at that time can be obtained as valve mechanism state 200b. Alternatively, data created by simulation may be used.

[0102] In this way, the correlation between the input information 200a obtained from product tests and the like and the valve mechanism state 200b is reasonable because it is obtained as a result of using the actual machine. Therefore, it is desirable to use such data as learning data 246 for machine learning.

[0103] The variable that is the input information 200a is specifically determined by the type of sensor used for the detector 61. Since distance sensors, vibration sensors, acoustic sensors, or the like can be adopted for the detector 61, as the input information 200a, predetermined variables corresponding to the types of the above sensors can be obtained.

[0104] The valve mechanism state 200b may be indicated using numerical values and error codes. For example, if the valve mechanism state 200b is obtained quantitatively, such as flow rate or leakage amount, the valve mechanism state 200b may be indicated by the specific amount. For example, when the state of the valve mechanism is normal, it may be indicated as 1, and when it is abnormal, it may be indicated as 0 for the valve mechanism state 200b.

[0105] For example, when indicating a sign of unexpected fluid leakage, the case where there is no sign of the leakage may be set to 0, and the case where the sign of the leakage can be grasped may be set to 1. Alternatively, the case where there is no sign of unexpected fluid leakage may be set to 0, and the case where the sign of the leakage is frequently observed and the sign of unexpected fluid leakage can be grasped with a high probability may be set to 100, and numerical values in between may be used.

[0106] The machine learning control unit 241 can extract any one or more pieces of learning data 246 from the plurality of pieces of learning data 246 stored in the learning data storage unit 243 and use them for machine learning.

[0107] The machine learning model storage unit 244 is a database that stores the learned learning model 245 generated by the machine learning control unit 241, that is, the adjusted weight parameter group.

[0108] The machine learning communication unit 242 is a communication interface unit. By being connected to an external device via the network 270, the machine learning communication unit 242 can transmit and receive various data. The learned learning model 245 stored in the machine learning model storage unit 244 is provided to the information processing device 250 via the network 270, a storage medium, or the like.

[0109] In FIG. 6, the learning data storage unit 243 and the machine learning model storage unit 244 are shown as separate storage units, but they may be configured as a single storage unit.

[0110] FIG. 8 is a schematic diagram showing the information processing device 250 of FIG. 1. The information processing device 250 is a device that operates as the main body in the inference phase of machine learning. The information processing device 250 uses the learning model 245 generated by the machine learning device 240 to predict a new valve mechanism state 202b corresponding to the newly input prediction input information 202a. The prediction input information 202a is a variable acquired by the detector 61 in the currently operating buffer valve 5. That is, the information processing device 250 obtains a new valve mechanism state 202b based on the prediction input information 202a in the currently operating buffer valve 5.

[0111] The information processing device 250 includes an information processing control unit 251, an information processing storage unit 255, and an information processing communication unit 256. The information processing control unit 251 includes an information acquisition unit 252, an information prediction unit 253, and an output processing unit 254.

[0112] The information acquisition unit 252 acquires, as prediction input information 202a, the data acquired by the detector 61 and output from the detection device 60. The prediction input information 202a is input information for obtaining a new valve mechanism state. Here, the valve mechanism state corresponding to the prediction input information 202a is defined as the new valve mechanism state 202b.

[0113] The information prediction unit 253 predicts the new valve mechanism state 202b by inputting the prediction input information 202a acquired by the information acquisition unit 252 into the learning model 245. The output processing unit 254 outputs the new valve mechanism state 202b predicted by the information prediction unit 253 to the information processing and communication unit 256.

[0114] The information prediction unit 253 can select and use one learning model 245 from among the plurality of learning models 245 stored in the information processing storage unit 255.

[0115] The information processing storage unit 255 is a database that stores the learned learning model 245 used by the information prediction unit 253. The information processing storage unit 255 can store a plurality of learned learning models 245 input from the machine learning device 240.

[0116] Each of the plurality of learning models 245 is, for example, a plurality of learned models that differ in machine learning methods, types of data included in the learning input information 201a, types of data included in the learning valve mechanism state 201b, and the like.

[0117] The information processing storage unit 255 may be substituted by a storage unit of an external computer such as a server-type computer or a cloud-type computer. In that case, the information prediction unit 253 can access the storage unit of the external computer to acquire the learning model 245.

[0118] The information processing and communication unit 256 is communicably connected to devices outside the valve system 200 via the network 270. The information processing and communication unit 256 is a communication interface unit that transmits and receives various data. The information processing and communication unit 256 can output the new valve mechanism state 202b output by the output processing unit 254 to the information processing and communication unit 256.

[0119] Figure 9 is a hardware configuration diagram of the computer 900. The machine learning device 240 and the information processing device 250 of the valve system 200 are constituted by a general-purpose or dedicated computer 900.

[0120] The computer 900 includes a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication interface unit 922, an external device interface unit 924, an input / output device interface unit 926, and a media input / output unit 928. Note that the above components may be appropriately omitted according to the application for which the computer 900 is used.

[0121] The processor 912 is constituted by one or a plurality of arithmetic processing units (such as a CPU (Central Processing Unit), an MPU (Micro-processing unit), a DSP (digital signal processor), a GPU (Graphics Processing Unit), etc.), and operates as a control unit that overall controls the computer 900.

[0122] The memory 914 stores various data and programs 930, and is constituted by, for example, a volatile memory (such as DRAM, SRAM, etc.) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0123] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is composed of, for example, an audio output device including sound, a vibration device, etc., and functions as an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, an electronic paper, a projector, etc., and functions as an output unit.

[0124] The input device 916 and the display device 918 may be integrally configured like a touch panel display. The storage device 920 is composed of, for example, an HDD, an SSD (Solid State Drive), etc., and functions as a storage unit. The storage device 920 stores various data necessary for the execution of an operating system and a program 930.

[0125] The communication interface unit 922 is connected to a network 940 such as the Internet or an intranet, either wired or wirelessly, and functions as a communication unit that transmits and receives data to and from other computers according to a predetermined communication standard. The network 940 may be the same as the network 270.

[0126] The external device interface unit 924 is connected to an external device 950 such as a camera, a printer, a scanner, a reader / writer, etc., either wired or wirelessly, and functions as a communication unit that transmits and receives data to and from the external device 950 according to a predetermined communication standard.

[0127] The input / output device interface unit 926 is connected to an input / output device 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the input / output device 960.

[0128] The media input / output unit 928 is composed of, for example, a drive device such as a DVD drive and a CD drive, and reads and writes data to a media 970 which is a storage medium such as a DVD and a CD.

[0129] In the computer 900 having the above configuration, the processor 912 calls the program 930 stored in the storage device 920 into the memory 914 and executes it, and controls each part of the computer 900 via the bus 910. Note that the program 930 may be stored in the memory 914 instead of the storage device 920.

[0130] The program 930 may be recorded on the medium 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the network 940 through the communication interface unit 922.

[0131] Also, the computer 900 may be configured to implement various functions realized when the processor 912 executes the program 930 using hardware such as an FPGA or an ASIC.

[0132] The computer 900 is composed of, for example, a stationary computer or a portable computer, and is an electronic device in any form. The computer 900 may be a client-type computer, a server-type computer, or a cloud-type computer. The computer 900 may also be applied to devices other than the machine learning device 240 and the information processing device 250 of the valve system 200.

[0133] Next, a machine learning method will be described. FIG. 10 is a flowchart showing the machine learning method by the machine learning device 240 of FIG. 1.

[0134] First, in advance, an operator inputs one or more learning data 246 and stores them in the learning data storage unit 243. The number of learning data 246 to be stored is set in consideration of the inference accuracy required for the finally obtained learning model 245. Preferably, a plurality of sets of learning data 246 are stored.

[0135] In the machine learning method, as step S100, a learning model preparation process is performed. The machine learning control unit 241 prepares a learning model 245 before learning. In the prepared learning model 245, the weight of each synapse is set to an initial value.

[0136] Next, as step S110, a machine learning process is performed. In the machine learning process, first, as step S111, a learning data acquisition process is performed. The machine learning control unit 241 randomly acquires one learning data 246 from a plurality of learning data 246 stored in the learning data storage unit 243.

[0137] Next, as step S112, an inference result output process is performed. The machine learning control unit 241 inputs the learning input information 201a included in the acquired one learning data 246 into the input layer 245a of the prepared learning model 245. As a result, the learning result valve mechanism state 201c is output as an inference result from the output layer 245c of the learning model 245.

[0138] The learning result valve mechanism state 201c output as an inference result is generated by the learning model 245 before or during learning. Therefore, the learning result valve mechanism state 201c is different from the learning valve mechanism state 201b, which is the correct label included in the learning data 246.

[0139] Next, as step S113, a weight adjustment process is performed. The machine learning control unit 241 compares the learning valve mechanism state 201b of the learning data 246 acquired in step S111, which is the correct label, with the learning result valve mechanism state 201c output as an inference result in step S112. Based on the comparison, the machine learning control unit 241 performs backpropagation, which is a process of adjusting the weight of each synapse, and performs machine learning.

[0140] Thereby, the machine learning control unit 241 causes the learning model 245 to learn the correlation between the learning input information 201a and the learning valve mechanism state 201b.

[0141] Next, as step S114, a machine learning end determination process is performed. The machine learning control unit 241 determines whether or not a predetermined learning end condition is satisfied. This determination is performed based on, for example, the evaluation value of the error function based on the learning valve mechanism state 201b, which is the correct label, and the learning result valve mechanism state 201c, or the remaining number of unlearned learning data 246 stored in the learning data storage unit 243.

[0142] In step S114, when the machine learning control unit 241 determines that the learning end condition is not satisfied and machine learning is to be continued, that is, when the result in step S114 is No, the process returns to step S111. In this way, the processes of steps S111 to S114 are repeatedly performed on the unlearned learning data 246 with respect to the learning model 245 during learning.

[0143] On the other hand, in step S114, when the machine learning control unit 241 determines that the learning end condition is satisfied and machine learning is to be terminated, that is, when the result in step S114 is Yes, the process proceeds to step S120.

[0144] Then, as step S120, a learned model storage process is performed. The machine learning control unit 241 stores the learned learning model 245 in which the weight of each synapse is adjusted, that is, the learning model 245 in which the adjusted weight parameter group is reflected, in the machine learning model storage unit 244. Thereby, the machine learning method ends.

[0145] Next, a method for predicting the new valve mechanism state 202b of the valve system 200 by the information processing apparatus 250 will be described. FIG. 11 is a flowchart showing a method for predicting the learning valve mechanism state by the information processing apparatus 250 of FIG. 1.

[0146] The learning valve mechanism state prediction method, which is an information processing method, is a method for determining the valve mechanism state indicating the state of the valve mechanism, and can obtain the valve mechanism state based on input information, which is a predetermined variable between the discharge valve 53, which is a valve body, and the valve seat 2.

[0147] First, as step S200, a prediction input information acquisition step is performed. By inputting the data of the variables obtained by the detection device 60 into the information processing device 250 as the prediction input information 202a, the information acquisition unit 252 acquires the prediction input information 202a.

[0148] Next, as step S210, a prediction step is performed. The information prediction unit 253 inputs the prediction input information 202a acquired in step S200 into the learning model 245. Thereby, the information prediction unit 253 predicts a new valve mechanism state 202b corresponding to the prediction input information 202a.

[0149] Next, as step S220, an output processing step is performed. The output processing unit 254 displays, as output processing, the new valve mechanism state 202b generated in step S210 on a display screen (not shown) or the like. Thereby, the prediction and output of the new valve mechanism state 202b are completed. Note that the new valve mechanism state 202b may be transmitted to the designated e-mail address described in an e-mail or the like.

[0150] Further, since a predetermined variable is constantly output from the detection device 60, the prediction input information acquisition step is accordingly performed.

[0151] The present disclosure can also be provided in the form of a machine learning program that causes a computer 900 to function as each unit included in the machine learning device 240, or a machine learning program that causes a computer 900 to execute each step included in the machine learning method.

[0152] The present disclosure can also be provided in the form of a valve mechanism state output program that causes a computer 900 to function as each unit included in the information processing device 250, or a valve mechanism state output program that causes a computer 900 to execute each step included in the information processing method according to Embodiment 1.

[0153] In addition, the present disclosure can be provided not only in the form of the information processing apparatus 250, information processing method, or information processing program according to Embodiment 1, but also in the form of an inference apparatus, inference method, or inference program used to infer the state of the valve mechanism. In that case, the inference apparatus, inference method, or inference program may include a memory 914 and a processor 912, and the processor 912 among them may execute a series of processes.

[0154] The series of processes includes an information acquisition process (information acquisition step) for acquiring input information, an inference process (inference step) for inferring the state of the valve mechanism using the learning model 245 stored in the memory 914, and an output process (output step) for outputting the inferred valve mechanism state to the external device 950. In the output process, the valve mechanism state may be output onto the network 940 via the communication interface unit 922.

[0155] According to the information processing apparatus 250 according to Embodiment 1, it predicts the state of the valve mechanism, and based on the input information, which is a predetermined variable between the discharge valve 53, which is a valve body, and the valve seat 2, it is possible to obtain a valve mechanism state indicating the state of the valve mechanism. Thereby, it is possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve body and the valve seat, the amount of that leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0156] According to the information processing apparatus 250 according to Embodiment 1, it includes one or more detectors 61 capable of detecting a predetermined variable of a detection target in the detection direction. Further, the valve seat 2 forms a part of the flow path, and a valve seat end face 2a is formed on the valve seat 2 where the flow path is closed when the discharge valve 53, which is a valve element, comes into contact with it. In addition, one or more detector installation spaces 42e are formed in the valve seat 2, and the detector 61 is installed in each detector installation space 42e. The detection direction is toward the discharge valve 53, which is a valve element, beyond the valve seat end face 2a when the detector 61 is installed in the detector installation space 42e. Thereby, a predetermined variable between the valve seat 2 and the discharge valve 53, which is a valve element, can be detected by the detector 61. Therefore, it is possible to more accurately verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve element and the valve seat, the amount of that leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0157] According to the information processing apparatus 250 according to Embodiment 1, at least one of the one or more detectors 61 uses one type of sensor among a distance sensor, a vibration sensor, and an acoustic sensor. Although various types of sensors can be used for the detector 61, by using one of the distance sensor, the vibration sensor, and the acoustic sensor, a generally commercially available and easily obtainable sensor can be used as the detector 61. Therefore, it is possible to easily handle the design, manufacture, and maintenance of the valve seat mechanism 1.

[0158] According to the information processing apparatus 250 according to Embodiment 1, the valve mechanism state includes at least one of the flow rate of the fluid flowing between the discharge valve 53, which is a valve element, and the valve seat 2, the presence or absence of unexpected fluid leakage between the discharge valve 53, which is a valve element, and the valve seat 2, the amount of unexpected fluid leakage between the discharge valve 53, which is a valve element, and the valve seat 2, and the sign of unexpected fluid leakage between the discharge valve 53, which is a valve element, and the valve seat 2. Thereby, based on the output of the information processing apparatus 250, the state of the valve mechanism can be easily and quickly verified.

[0159] According to the information processing apparatus 250 according to Embodiment 1, when input information is input, the valve mechanism state is determined using a learning model in which the correlation between the input information and the valve mechanism state is learned by machine learning, and the determined valve mechanism state is output. Thereby, the machine learning method based on the accumulated information can be used for verifying the state of the valve mechanism. Therefore, it is possible to more accurately verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of the leakage, and the prediction of unexpected fluid leakage from the valve mechanism.

[0160] According to the machine learning apparatus 240 according to Embodiment 1, a learning model 245 for inferring a valve mechanism state indicating the state of the valve mechanism is generated. Further, it includes a learning data storage unit 243 that stores a plurality of sets of learning data 246 composed of input information, which is a predetermined variable between the discharge valve 53, which is the valve body, and the valve seat 2, and the valve mechanism state corresponding to the input information. Further, when a plurality of sets of learning data 246 are input, a machine learning model storage unit that causes the learning model to learn the correlation between the input information and the valve mechanism state and stores the learned learning model 245 is provided. Thereby, the learning model 245 in which the correlation between the input information and the valve mechanism information is learned can be generated and stored. Therefore, it is possible to more accurately verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of the leakage, and the prediction of unexpected fluid leakage from the valve mechanism using the learned learning model 245.

[0161] According to the inference device according to Embodiment 1, it includes a memory 914 and at least one processor 912, and infers the valve mechanism state indicating the state of the valve mechanism. Further, at least one processor 912 executes an information acquisition process of acquiring input information which is a predetermined variable between a discharge valve 53 which is a valve element and a valve seat 2, an inference process of inferring the valve mechanism state using a learning model 245 by machine learning stored in the memory 914 when the input information is acquired, and an output process of outputting the inferred valve mechanism state. Thereby, it is possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve element and the valve seat, the amount of the leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0162] According to the inference method according to Embodiment 1, it is executed by an inference device including a memory 914 and at least one processor 912, and infers the valve mechanism state indicating the state of the valve mechanism. Further, at least one processor 912 executes an information acquisition step of acquiring input information which is a predetermined variable between a discharge valve 53 which is a valve element and a valve seat 2. Further, when the input information is acquired, an inference step of inferring the valve mechanism state using a learning model 245 by machine learning stored in the memory 914 is executed. Further, an output step of outputting the inferred valve mechanism state is executed. Thereby, it is possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve element and the valve seat, the amount of the leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0163] According to the information processing method according to Embodiment 1, the valve mechanism state indicating the state of the valve mechanism is determined. Further, based on the input information which is a predetermined variable between a discharge valve 53 which is a valve element and a valve seat 2, the valve mechanism state is obtained. Thereby, it is possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage between the valve element and the valve seat, the amount of the leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0164] According to the machine learning method according to Embodiment 1, a learning model 245 for inferring the valve mechanism state indicating the state of the valve mechanism is generated. Further, in a state where one or more pieces of learning data 246 composed of input information, which is a predetermined variable between the discharge valve 53, which is a valve body, and the valve seat 2, and the valve mechanism state corresponding to the input information are stored, a plurality of sets of the learning data 246 are input, and a machine learning process is executed to cause the learning model to learn the correlation between the input information and the valve mechanism state. Further, a learned model storage process is executed to store the learning model 245 learned in the machine learning process in the machine learning model storage unit 244. Thereby, it is possible to verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of the leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0165] In Embodiment 1, a neural network-based learning model 245 is adopted. However, it is not limited to this. As the learning model 245, other machine learning models may be adopted. Examples of other machine learning models include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, recurrent neural networks, convolutional neural networks, neural network types (including deep learning) such as LSTM (Long Short Term Memory), hierarchical clustering, non-hierarchical clustering, clustering types such as k-nearest neighbor method and k-means method, multivariate analysis such as principal component analysis, factor analysis, and logistic regression, and support vector machines. and so on.

[0166] Embodiment 2. As an explanation of the valve system 200 of the present disclosure, the valve system 200 used for the reservoir valve 5 is also used in Embodiment 2. However, the valve system 200 of the present disclosure is not limited to being applied to the reservoir valve 5, and can be appropriately used for a general valve mechanism.

[0167] The information processing apparatus 250 according to Embodiment 2 differs from the valve system 200 according to Embodiment 1 in that it outputs the new valve mechanism state 202b without using the learning model obtained by machine learning.

[0168] The information processing apparatus 250 can output a new valve mechanism state 202b corresponding to the acquired input information for prediction 202a.

[0169] The information prediction unit 253 determines the new valve mechanism state 202b from the input information for prediction 202a acquired by the information acquisition unit 252 by a predetermined determination method. Since these determination methods do not use a machine learning method, they also do not use a learning model. The output processing unit 254 can output the determined new valve mechanism state 202b to the information processing communication unit 256.

[0170] In the information processing apparatus 250, the information acquisition unit 252 can also sequentially store the input information for prediction 202a acquired in the information processing storage unit 255. Thereby, the stored input information for prediction 202a can be treated as time-series data. The information processing storage unit 255 according to Embodiment 1 functioned as a database of the learning model 245, but in Embodiment 2, the information processing storage unit 255 functions as a storage device that can store information.

[0171] The predetermined determination methods implemented by the information prediction unit 253 include those based on comparison with stored waveform data, those for determining normal or abnormal by a threshold value, those for calculating physical quantities by arithmetic operations using coefficients, and other well-known statistical analysis calculations.

[0172] In the information processing storage unit 255, information such as waveform data, threshold values, or coefficients necessary for the determination method implemented by the information prediction unit 253 is stored in advance. Examples of the stored waveform data include time-series data of a predetermined variable detected by the detector 61 that can be a sign of unexpected fluid leakage.

[0173] The information prediction unit 253 can implement a predetermined determination method using this waveform data. For example, the corresponding valve mechanism state can be determined based on whether the stored waveform data as described above, or the waveform data based on the prediction input information 202a, or the features of the waveform data match. If they match, a new valve mechanism state 202b such as a sign of unexpected fluid leakage can be determined.

[0174] Also, as the stored threshold value, there is one that stores the time as the threshold value assuming that the state where the discharge valve 53 keeps the flow path open for a certain period of time or more is an abnormal state, or one that stores the time as the threshold value assuming that the state where the fine movement of the discharge valve 53 continues for a certain period of time or more is an abnormal state.

[0175] The information prediction unit 253 can implement a predetermined determination method using this threshold value. For example, it determines whether the opening of the flow path by the discharge valve 53 or the fine movement of the discharge valve 53 based on the prediction input information 202a continues for a time equal to or longer than the threshold value. If a time equal to or longer than the threshold value has elapsed, a new valve mechanism state 202b such as the valve mechanism being abnormal can be determined.

[0176] Also, as the stored coefficient, there are those necessary for calculating physical quantities. For example, it is a coefficient necessary for calculating the flow rate of the fluid flowing out from between the discharge valve 53 and the valve seat 2.

[0177] The information prediction unit 253 can implement a predetermined determination method using this coefficient. For example, it calculates and determines the flow rate using the stored coefficient. The calculated flow rate can be used to determine a new valve mechanism state 202b as the flow rate of the fluid flowing out from the valve mechanism.

[0178] The information processing control unit 251 can determine the new valve mechanism state 202b based on the prediction input information 202a by using the waveform data, threshold values, and coefficients stored in advance. Further, according to the second embodiment, the waveform data, threshold values, and coefficients stored in advance are not limited to those described above and can be appropriately selected. Further, in order to determine the new valve mechanism state 202b, not only the determination method described above but also well-known arithmetic and statistical methods can be used.

[0179] In the second embodiment, since machine learning is not used, the configurations related to the learning model 245, the machine learning device 240, and the inference device in the first embodiment are not used. Since the other configurations of the second embodiment are the same as those of the first embodiment, the description thereof is omitted.

[0180] According to the information processing device 250 according to the second embodiment, when input information is input, the valve mechanism state is determined from the input information based on a predetermined determination method that does not use a machine learning method, and the determined valve mechanism state is output. Thereby, the state of the currently installed valve mechanism can be verified based on the knowledge of the past valve mechanism. Therefore, it is possible to more accurately verify the amount of fluid passing through the valve mechanism, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of the leakage, and the sign of unexpected fluid leakage from the valve mechanism.

[0181] Embodiment 3. As an explanation of the valve system 200 of the present disclosure, the valve system 200 used for the buffer valve 5 is also used in the third embodiment. However, the valve system 200 of the present disclosure is not limited to being applied to the buffer valve 5 and can be appropriately used for a general valve mechanism.

[0182] In the third embodiment, it is different from the first embodiment or the second embodiment in that three detectors 61 are installed on the valve seat 2. FIG. 12 is a top view showing the introduction part 42 according to the third embodiment.

[0183] The detection device 60 includes three detectors 61, an input / output device (not shown), and wiring 62 that transmits the signals of the respective detectors 61 to the input / output device. In the introduction part 42, three detector installation spaces 42e are formed. In one detector installation space 42e, one detector 61 and the wiring 62 connected to the detector 61 are installed.

[0184] The valve contact member 70 is formed in a shape corresponding to the shape of the main body end face 42d. The openings of the plurality of detector installation spaces 42e formed in the main body end face 42d are closed when the valve contact member 70 is installed in the introduction part 42. That is, the plurality of detectors 61 are installed in the detector installation spaces 42e covered by the valve contact member 70. Each of the plurality of detectors 61 is installed along the valve facing surface 70a. As shown in FIG. 12, the inner peripheral surface of the introduction part 42 at the portion where each detector installation space 42e is formed protrudes further inward, and the thickness of the introduction part 42 at the portion where the detector installation space 42e is formed is thicker than the thickness of the other portions. Also, the valve contact member 70 is formed in a shape corresponding to the shape of the main body end face 42d. However, it is not limited to this. For example, the thickness of the introduction part 42 may be uniformly equal, that is, no protruding portion is formed on the inner peripheral surface of the introduction part 42 toward the inside, and the inner peripheral surface of the introduction part 42 viewed from the axial direction may be circular. Even in this case, the valve contact member 70 is formed in a shape corresponding to the shape of the main body end face 42d.

[0185] Each of the plurality of detectors 61 is of the same type of sensor. For example, all three detectors 61 may be distance sensors. Since the other configurations of the third embodiment are the same as the configurations disclosed in the first embodiment, the description thereof is omitted.

[0186] In addition, in the third embodiment, three detectors 61 were installed in the introduction part 42. However, it is not limited to this. The number of detectors 61 arranged in the introduction part 42 may be two or more, that is, a plurality. Also, one or a plurality of detectors 61 may be installed in one detector installation space 42e. The detectors 61 of the valve seat mechanism 1 in the third embodiment are installed in plurality along the valve seat end face 2a. Thereby, a slight inclination or vibration of the discharge valve 53 can be examined in more detail. Therefore, the behavior of the valve body can be observed in more detail.

[0187] The plurality of detectors 61 of the valve seat mechanism 1 in the third embodiment are of a single type of sensor. Thereby, the signals obtained from each detector 61 can be easily compared and examined. Therefore, a slight inclination or vibration of the discharge valve 53 can be detected in more detail easily.

[0188] In addition, the three detectors 61 in the third embodiment are all of the same type of sensor. However, it is not limited to this. For example, the types of sensors of the three detectors 61 may be one or more distance sensors and one or more vibration sensors. That is, for the plurality of detectors 61, a plurality of types of sensors may be used.

[0189] In the valve seat mechanism 1 in the third embodiment, at least two detectors 61 are sensors of different types from each other. Thereby, the behavior of the discharge valve 53 can be examined from multiple angles.

[0190] Also, the valve system 200 and the valve seat mechanism 1 in the first to third embodiments are provided in the bleeder valve 5. However, it is not limited to this. As long as it is a valve mechanism that closes the flow path by closing the valve seat end face 2a of the valve seat 2 with a valve member and opens the flow path by creating a gap between the valve member and the valve seat 2, the valve system 200 and the valve seat mechanism 1 in the first to third embodiments can be provided. Examples of such a valve mechanism include a rotary valve such as a ball valve and a diaphragm valve.

[0191] Also, in the valve system 200 according to Embodiments 1 to 3, a predetermined variable detected by the detector 61 installed in the detector installation space 42e formed in the valve seat 2 is used as input information. However, it is not limited to this. The installation location of the detector 61 may be installed anywhere on the valve seat 2 or the valve mechanism.

[0192] (Other embodiments) The present disclosure is not limited to the above-described embodiments, and various modifications can be made and implemented within the scope not departing from the gist of the present disclosure. And all of them are included in the technical idea of the present disclosure.

[0193] Hereinafter, various aspects of the present disclosure will be summarized and described as appendices.

[0194] (Appendix 1) An information processing apparatus for predicting the state of a valve mechanism, Based on input information that is a predetermined variable between a valve body and a valve seat, a valve mechanism state indicating the state of the valve mechanism is obtained. Information processing apparatus. (Appendix 2) Comprising one or more detectors capable of detecting the predetermined variable of a detection target in a detection direction, The valve seat constitutes a part of a flow path, The valve seat is formed with a valve seat end face where the flow path is closed when the valve body contacts it, One or more detector installation spaces are formed in the valve seat, Each of the detector installation spaces has the detector installed therein, The detection direction is toward the valve body beyond the valve seat end face in a state where the detector is installed in the detector installation space. The information processing apparatus according to Appendix 1. (Appendix 3) At least one of the one or more detectors uses one type of sensor among a distance sensor, a vibration sensor, and an acoustic sensor. The information processing apparatus according to Appendix 2. (Appendix 4) The valve mechanism state includes at least one of the flow rate of fluid flowing between the valve body and the valve seat, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of unexpected fluid leakage from between the valve body and the valve seat, and the sign of unexpected fluid leakage from between the valve body and the valve seat. The information processing apparatus according to any one of Appendices 1 to 3. (Appendix 5) When the input information is input, the valve mechanism state is determined using a learning model in which the correlation between the input information and the valve mechanism state is learned by machine learning, and the determined valve mechanism state is output. The information processing apparatus according to any one of Appendices 1 to 4. (Appendix 6) A machine learning apparatus for generating a learning model for inferring a valve mechanism state indicating the state of a valve mechanism, A learning data storage unit that stores a plurality of sets of learning data composed of input information, which is a predetermined variable between the valve body and the valve seat, and the valve mechanism state corresponding to the input information, A machine learning model storage unit that learns the correlation between the input information and the valve mechanism state in a learning model when a plurality of sets of the learning data are input, and stores the learned learning model, and includes a machine learning apparatus. (Appendix 7) An inference apparatus that includes a memory and at least one processor and infers a valve mechanism state indicating the state of a valve mechanism, The at least one processor performs an information acquisition process of acquiring input information, which is a predetermined variable between the valve body and the valve seat, When the input information is acquired, an inference process of inferring the valve mechanism state using a learning model by machine learning stored in the memory, and an output process of outputting the inferred valve mechanism state. and executes an inference apparatus. (Appendix 8) An information processing method for determining a valve mechanism state indicating the state of a valve mechanism, Determining the valve mechanism state corresponding to input information that is a predetermined variable between the valve body and the valve seat, Information processing method. (Appendix 9) A machine learning method for generating a learning model for inferring a valve mechanism state indicating the state of a valve mechanism, In a state where one or more pieces of learning data composed of input information that is a predetermined variable between the valve body and the valve seat and the valve mechanism state corresponding to the input information are stored, A machine learning step of causing a learning model to learn the correlation between the input information and the valve mechanism state by inputting the learning data, A learned model storage step of storing the learning model learned in the machine learning step in a machine learning model storage unit, Executing, Machine learning method. (Appendix 10) An inference method executed by an inference device including a memory and at least one processor for inferring a valve mechanism state indicating the state of a valve mechanism, The at least one processor includes an information acquisition step of acquiring input information that is a predetermined variable between the valve body and the valve seat, When the input information is acquired, an inference step of inferring the valve mechanism state using a learning model by machine learning stored in the memory, An output step of outputting the inferred valve mechanism state, Executing, Inference method

Explanation of reference numerals

[0195] 1 valve seat mechanism, 2 valve seat, 2a valve seat end face, 3 valve seat body, 4 tank, 4a mounting portion, 4b upstream flange, 5 breather valve, 10 main portion, 10a inlet side opening end, 10b outlet side opening end, 10c intake side opening end, 20 intake portion, 21 intake portion body, 21a connection side opening end, 21b intake port, 21x intake valve seat, 22 intake valve mechanism, 23 intake valve (valve body), 24 intake valve shaft, 25 intake valve guide, 40 discharge portion, 41 discharge portion body, 42 introduction portion, 42a discharge portion inlet side opening end, 42b valve side end, 42c valve side opening, 42d body end face, 42e detector installation space, 43 atmosphere discharge portion, 43a discharge port, 43b valve mechanism side opening end, 47 vent cover, 50 discharge valve mechanism, 53 discharge valve (valve body), 54 discharge valve shaft, 55 discharge valve guide, 60 detection device, 61 detector, 62 wiring, 70 valve contact member, 110 main flow path, 111 branch flow path, 120 intake flow path, 140 discharge flow path, 200 valve system, 200a input information, 200b valve mechanism state, 201a learning input information, 201b learning valve mechanism state, 201c learning result valve mechanism state, 202a prediction input information, 202b new valve mechanism state, 240 machine learning device, 241 machine learning control unit, 242 machine learning communication unit, 243 learning data storage unit, 244 machine learning model storage unit, 245 learning model, 245a input layer, 245b intermediate layer, 245c output layer, 246 learning data, 250 information processing device, 251 information processing control unit, 252 information acquisition unit, 253 information prediction unit, 254 output processing unit, 255 information processing storage unit, 256 information processing communication unit, 270 network, 900 computer, 910 bus, 912 processor, 914 memory, 916 input device, 917 output device, 918 display device, 920 storage device, 922 communication interface unit, 924 external device interface unit, 926 input / output device interface unit, 928 media input / output unit, 930 program, 940 network, 950 external device, 960 input / output device, 970 media (non-temporary storage medium).

Claims

1. An information processing device for predicting the state of a valve mechanism, comprising: Based on input information which is a predetermined variable between a valve body and a valve seat, obtaining a valve mechanism state indicating the state of the valve mechanism; An information processing device.

2. Comprising one or more detectors capable of detecting the predetermined variable of a detection target in a detection direction, The valve seat forms a part of a flow path, On the valve seat, a valve seat end face is formed where the flow path is closed when the valve body contacts it, One or more detector installation spaces are formed on the valve seat, Each of the detector installation spaces has the detector installed therein, The detection direction is directed towards the valve body beyond the valve seat end face when the detector is installed in the detector installation space; The information processing device according to Claim 1.

3. At least one of the one or more detectors uses one type of sensor among a distance sensor, a vibration sensor, and an acoustic sensor; The information processing device according to Claim 2.

4. The valve mechanism state includes at least one of the flow rate of the fluid flowing between the valve body and the valve seat, the presence or absence of unexpected fluid leakage from between the valve body and the valve seat, the amount of unexpected fluid leakage from between the valve body and the valve seat, and the omen of unexpected fluid leakage from between the valve body and the valve seat; The information processing device according to Claim 1.

5. When the input information is input, using a learning model in which the correlation between the input information and the valve mechanism state is learned by machine learning, determining the valve mechanism state and outputting the determined valve mechanism state; The information processing device according to Claim 1.

6. A machine learning device for generating a learning model for inferring a valve mechanism state indicating the state of a valve mechanism, comprising: A learning data storage unit storing a plurality of sets of learning data composed of input information which is a predetermined variable between a valve body and a valve seat and the valve mechanism state corresponding to the input information; By inputting a plurality of sets of the learning data, causing a learning model to learn the correlation between the input information and the valve mechanism state, and storing the learned learning model in a machine learning model storage unit; Comprising; A machine learning device.

7. Comprising a memory and at least one processor, an inference device for inferring a valve mechanism state indicating the state of a valve mechanism, The at least one processor performs an information acquisition process of acquiring input information which is a predetermined variable between the valve body and the valve seat, when acquiring the input information, an inference process of inferring the valve mechanism state using a learning model by machine learning stored in the memory, and an output process of outputting the inferred valve mechanism state, and executes an inference device.

8. An information processing method for determining a valve mechanism state indicating the state of a valve mechanism, comprising: obtaining the valve mechanism state corresponding to input information which is a predetermined variable between the valve body and the valve seat. Information processing method.

9. A machine learning method for generating a learning model for inferring a valve mechanism state indicating the state of a valve mechanism, comprising: in a state where one or more pieces of learning data composed of input information which is a predetermined variable between the valve body and the valve seat and the valve mechanism state corresponding to the input information are stored, a machine learning step of causing the learning model to learn the correlation between the input information and the valve mechanism state by inputting the learning data, and a learned model storage step of storing the learning model learned in the machine learning step in a machine learning model storage unit. and executes a machine learning method.

10. An inference method executed by an inference device including a memory and at least one processor for inferring a valve mechanism state indicating the state of a valve mechanism, comprising: the at least one processor performs an information acquisition step of acquiring input information which is a predetermined variable between the valve body and the valve seat, when acquiring the input information, an inference step of inferring the valve mechanism state using a learning model by machine learning stored in the memory, and an output step of outputting the inferred valve mechanism state. and executes an inference method.

Images