Processing apparatus, method, and program

Abstract

To predict the effects of flow deviations that occur in the piping at the site where the flow meter is installed. [Solution] The processing device calculates the flow velocity profile at the point where the flow rate is measured by a flow meter under each of two piping conditions: a first piping condition in which the dimensions of the first pipe are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set. Based on the flow velocity profile for each of the two piping conditions, it calculates a predicted value of the flow rate measured by the flow meter and outputs the result of comparing the predicted values ​​between the two piping conditions.

Description

[Technical Field]

[0001] This disclosure relates to processing apparatus, methods, and programs. [Background technology]

[0002] To achieve high accuracy and stability in flow rate measurement, it is preferable that the flow at the measurement point within the piping is stable and the flow distribution is symmetrical. For example, if the straight pipe length is insufficient, the flow at the measurement point becomes unstable or the flow distribution becomes asymmetrical from the central axis of the pipe, resulting in a decrease in the accuracy of flow rate measurement. For this reason, it is preferable to ensure a sufficient straight pipe length, but in actual field work, it is not always possible to secure sufficient piping space.

[0003] One conventional technique to address the effects of such flow deviation is to calculate the measurement error that occurs when flow deviation occurs under specific piping conditions and correct the measured flow rate based on that measurement error. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Patent No. 4949892 [Patent Document 2] Patent No. 5566991 [Patent Document 3] Patent No. 3103264 [Patent Document 4] Japanese Patent Publication No. 2024-107870 [Overview of the project] [Problems that the invention aims to solve]

[0005] However, the conventional techniques described above calculate measurement errors under fixed piping conditions prepared as an experimental environment, and therefore cannot necessarily predict the effects of flow deviations that occur at the measurement point in the actual piping where the flow meter is installed, which leaves room for improvement.

[0006] In one aspect, this disclosure aims to provide a processing device, method, and program that can predict the effects of flow deviations occurring in field piping where flow meters are installed. [Means for solving the problem]

[0007] The processing apparatus according to the present disclosure comprises a processor which performs the following: calculates a flow velocity profile at a point where the flow rate is measured by a flow meter under each of two piping conditions, a first piping condition in which the dimensions of the first pipe are set and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set; calculates a predicted value of the flow rate measured by the flow meter based on the flow velocity profile for each of the two piping conditions; and outputs the result of comparing the predicted values ​​between the two piping conditions.

[0008] The method according to the present disclosure involves a computer calculating a flow velocity profile at a point where the flow rate is measured by a flow meter under each of two piping conditions: a first piping condition in which the dimensions of the first pipe are set and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set; calculating a predicted value of the flow rate measured by the flow meter based on the flow velocity profile for each of the two piping conditions; and outputting the result of comparing the predicted values ​​between the two piping conditions.

[0009] The program according to this disclosure causes a computer to perform the following processes: calculate a flow velocity profile at a point where the flow rate is measured by a flow meter under each of two piping conditions: a first piping condition in which the dimensions of the first pipe are set and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set; calculate a predicted value of the flow rate measured by the flow meter based on the flow velocity profile for each of the two piping conditions; and output the result of comparing the predicted values ​​between the two piping conditions. [Effects of the Invention]

[0010] According to this disclosure, it is possible to predict the effects of flow deviations occurring in the piping at the site where the flow meter is installed. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 shows an example of the configuration of a prediction system. [Figure 2] Figure 2 is a schematic diagram illustrating one aspect of a problem-solving approach. [Figure 3] Figure 3 is a block diagram showing an example of the functional configuration of a server device. [Figure 4] Figure 4 is Figure (1), which shows an example of a piping model. [Figure 5] Figure 5 is Figure (2), which shows an example of a piping model. [Figure 6] Figure 6 shows an example of setting parameters for flow drift generation. [Figure 7] Figure 7 is Figure (1), which shows an example of the results of a fluid simulation. [Figure 8] Figure 8 is Figure (2), which shows an example of the results of a fluid simulation. [Figure 9] Figure 9 is a schematic diagram (1) illustrating the input and output of the calculation block. [Figure 10] Figure 10 is a schematic diagram illustrating the sensing principle of an ultrasonic flow meter. [Figure 11] Figure 11 is a schematic diagram (2) illustrating the input and output of the calculation block. [Figure 12] Figure 12 is a schematic diagram illustrating the sensing principle of an electromagnetic flow meter. [Figure 13] Figure 13 is a schematic diagram (3) illustrating the input and output of the calculation block. [Figure 14] Figure 14 is a schematic diagram illustrating the sensing principle of a vortex flowmeter. [Figure 15] Figure 15 is a schematic diagram (4) illustrating the input and output of the computation block. [Figure 16] Figure 16 is a schematic diagram illustrating the sensing principle of an orifice flow meter. [Figure 17]Figure 17 is a schematic diagram (5) illustrating the input and output of the computation block. [Figure 18] Figure 18 is a schematic diagram illustrating the sensing principle of a Coriolis flow meter. [Figure 19] Figure 19 is a flowchart showing the steps of the generation process. [Figure 20] Figure 20 is a flowchart showing the steps of the prediction process. [Figure 21] Figure 21 is a schematic diagram (1) showing an example of a surrogate AI model. [Figure 22] Figure 22 is a schematic diagram (2) showing an example of a surrogate AI model. [Figure 23] Figure 23 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0012] Hereinafter, embodiments for implementing the processing apparatus, method, and program relating to this disclosure (hereinafter referred to as "embodiments") will be described with reference to the attached drawings. It should be noted that these embodiments represent only one example or aspect, and such examples do not limit the structure, operation, function, properties, characteristics, methods, and applications relating to this disclosure.

[0013] <Embodiment 1> <System Configuration> Figure 1 shows an example of the configuration of prediction system 1. Figure 1 shows prediction system 1, which provides a prediction service to predict the effects of flow deviations occurring in the field piping 2B where the flow meter 22 is installed.

[0014] As shown in Figure 1, the prediction system 1 may include a server device 10, a sensor module 20, and client terminals 30A to 30N. Hereafter, when it is not necessary to distinguish between individual client terminals 30A to 30N, they may be referred to as "client terminal 30".

[0015] These server devices 10, sensor modules 20, and client terminals 30 may be connected to each other via any network NW. The network NW may be wired or wireless, and may be implemented using any communication technology such as internet technology, industrial communication standards, or low-power wireless communication standards for IoT (Internet of Things).

[0016] The server device 10 can provide the above-mentioned prediction service as a cloud service by running PaaS (Platform as a Service) type middleware or SaaS (Software as a Service) type application. Note that the server device 10 may be included as an example of a processing unit.

[0017] The sensor module 20 may include various sensors installed in the field piping 2B. For example, the sensor module 20 may include a fluid property sensor 21 for measuring the physical properties of the fluid flowing inside the field piping 2B, a flow meter 22 for measuring the flow rate of the fluid flowing inside the field piping 2B, etc. For example, the fluid property sensor 21 may be implemented using a density sensor for measuring the density of the fluid or a viscosity sensor for measuring the viscosity of the fluid. Also, although an electromagnetic flow meter is schematically shown in Figure 1 as an example of a flow meter 22, this is merely an example, and a flow meter of any principle may be installed. Hereafter, in order to distinguish it from a virtual flow meter reproduced in the field piping 2B in a virtual space, the flow meter actually installed in the field piping 2B may be referred to as the "field flow meter."

[0018] The client terminal 30 is a terminal device that receives the above-mentioned prediction service. As an example, the client terminal 30 may be used by all persons involved in the design, operation, and maintenance of the field piping 2B. For example, the client terminal 30 may be implemented using any computer, including personal computers, smartphones, tablet devices, and wearable devices.

[0019] Note that Figure 1 shows an example where the above prediction service is provided by a single server device 10, but the above prediction service may also be provided using multiple server devices such as a web server and a backend server.

[0020] Furthermore, while the above-mentioned forecasting service is provided as a cloud service, it is not limited to this. For example, the forecasting service may be provided on-premises. Also, while the above-mentioned forecasting service is provided as a client-server system, it is not limited to this. For example, an application running on the client terminal 30 or flow meter 22 can cause the client terminal 30 or flow meter 22 to execute processing corresponding to the forecasting function provided by the forecasting service, thereby preventing the forecasting function from being provided in a standalone form.

[0021] <One aspect of the problem> As explained in the background technology section above, the conventional technology described above calculates measurement errors under fixed piping conditions prepared as an experimental environment. Therefore, it cannot necessarily predict the effects of flow deviations that occur at the measurement point in the actual piping where the flow meter is installed, and thus there is room for improvement.

[0022] <One aspect of a problem-solving approach> Therefore, in this embodiment, a prediction function is provided that calculates the flow velocity profile at the point where the flow rate is measured by a virtual flow meter under each of two piping conditions: a first piping condition in which the dimensions of the first piping are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second piping are set. Based on the flow velocity profile for each of the two piping conditions, a predicted value of the flow rate measured by the virtual flow meter is calculated, and the result of comparing the predicted values ​​between the two piping conditions is output.

[0023] Figure 2 is a schematic diagram illustrating one aspect of the problem-solving approach. The "first piping conditions" shown in Figure 2 may include the dimensions of the ideal piping 2A reproduced in the virtual space. Here, "ideal piping" refers to piping with conditions set to be ideal for achieving high accuracy and stability in flow measurement. One aspect is that the ideal piping 2A may be set to have conditions in which the flow develops sufficiently at the measurement point where the flow rate is measured by the virtual flow meter 4 reproduced in the ideal piping 2A in the virtual space, resulting in a stable flow both temporally and spatially, for example, conditions in which flow deviation is unlikely to occur. For example, the first piping conditions may include a straight pipe with no connections of curved pipes such as bent pipes or elbow pipes, and a constant central axis within the piping, and as an example of the upstream straight pipe length of the ideal piping 2A, a sufficient upstream straight pipe length L L The upstream straight pipe length L is set. L This may be set based on design information such as performance of the flow meter 22 installed in the field piping 2B or the flow meter to be set in the field piping 2B, or it may be set based on the results of experiments or analyses.

[0024] On the other hand, the "second piping conditions" shown in Figure 2 may include the dimensions of the field piping 2B reproduced in the virtual space. As merely an example, given that various constraints may be imposed on the space and shape of the piping in the field, parameters related to the occurrence of flow deviation may be set for field piping 2B. Hereafter, parameters related to the occurrence of flow deviation may be referred to as "flow deviation parameters." For example, the second piping conditions may include, as examples of flow deviation parameters, whether or not there is an elbow pipe connection in field piping 2B, whether or not there is a deviation of the central axis in field piping 2B, and as an example of the upstream straight pipe length of field piping 2B, an upstream straight pipe length L which is not necessarily sufficient. R The following is an example of setting whether or not to connect an elbow pipe, but it is also possible to set whether or not to connect other curved pipes, such as a bent pipe. Note that Figure 2 shows only one example of flow deviation generation parameters, and other flow deviation generation parameters may be set as well.

[0025] Under each of these two piping conditions, the flow velocity profile V at the measurement site of the virtual flowmeter 4 reproduced in the virtual space L and the flow velocity profile V R are calculated. For example, in FIG. 2, the measurement site in the ideal pipe 2A is hatched with diagonally rising lines to the right, while the measurement site in the field pipe 2B is hatched with vertical lines. For example, by executing a fluid simulation that simulates the fluid flow in the three-dimensional model of the ideal pipe 2A corresponding to the first piping condition, the flow velocity distribution at the measurement site hatched with diagonally rising lines to the right in FIG. 2 is defined as the flow velocity profile V L can be obtained. On the other hand, by executing a fluid simulation that simulates the fluid flow in the three-dimensional model of the field pipe 2B corresponding to the second piping condition, the flow velocity distribution at the measurement site hatched with vertical lines in FIG. 2 can be obtained as the flow velocity profile V R can be obtained.

[0026] Furthermore, for each of the two piping conditions, the flow velocity profile V L or the flow velocity profile V R the predicted flow rate value V measured by the virtual flowmeter 4 based on i and the predicted flow rate value V P are calculated. For example, according to the sensing principle of the virtual flowmeter 4, from the flow velocity profile V L or the flow velocity profile V R the physical quantity measured by the virtual flowmeter 4, for example, in the case of an electromagnetic flowmeter, the "electromotive force" is calculated, and then the predicted flow rate value V is derived from the physical quantity i or the predicted flow rate value V P are calculated.

[0027] Thereafter, the predicted flow rate value V between the two piping conditions i and the predicted flow rate value V P the result of the comparison is output to the client terminal 30 or the like. These predicted flow rate values V i and the predicted flow rate value V P As an example of the comparison result of, the predicted flow rate value V i and the predicted flow rate value V PIt can output an alert if the difference exceeds a threshold, or it can output a correction coefficient, correction amount, and corrected flow rate value used to correct the actual measured value of the flow meter installed on-site corresponding to the field piping 2B.

[0028] Therefore, according to the prediction function of this embodiment, it is possible to predict the effects of flow deviations occurring in the piping at the site where the flow meter is installed.

[0029] <Configuration of Server Device 10> Next, the functional configuration of the server device 10 that provides the above-mentioned prediction function will be described. Figure 3 is a block diagram showing an example of the functional configuration of the server device 10. Figure 3 schematically illustrates the blocks related to the prediction function that the server device 10 has.

[0030] As shown in Figure 3, the server device 10 includes a fluid information DB (Database) 11A, a flow rate value DB 11B, a piping information DB 12, a calculation information DB 13, a generation unit 14, a first calculation unit 15, a second calculation unit 16, and a comparison unit 17. Note that Figure 3 only shows a selection of the functional units related to the prediction function described above, and the server device 10 may also be equipped with functional units other than those shown.

[0031] The fluid information DB11A may be implemented as a database that stores information about the fluid flowing through the field piping 2B. As an example, the fluid information DB11A stores fluid property information used in the fluid simulation by the first calculation unit 15 described later, such as viscosity and density. For example, fluid property information may include viscosity and density. Such fluid property information may be measured values ​​obtained by the fluid property sensor 21, or input values ​​entered by the user via the client terminal 30.

[0032] The flow rate value DB11B may be implemented by a database that stores the measured flow rate in the field piping 2B. As just one example, the flow rate value DB11B may contain the measured flow rate V measured in the field piping 2B by the field flow meter 22. fThis data may be saved. Such measured flow rates may include errors caused by disturbances such as the shape and dimensions of the field piping 2B and the external environment.

[0033] The piping information DB12 may be implemented as a database that stores information about piping. As just one example, the piping information DB12 may store a first piping condition and a second piping condition. As another example, the piping information DB12 may store a 3D model of the 3D structure of ideal piping 2A modeled based on the first piping condition and a 3D model of the 3D structure of field piping 2B modeled based on the second piping condition. Hereafter, the 3D model of piping may be referred to as the "piping model".

[0034] Figure 4 is Figure (1), which shows an example of a piping model. Figure 5 is Figure (2), which shows an example of a piping model. Figure 4 shows piping model 12A, which models the three-dimensional structure of ideal piping 2A, while Figure 5 shows piping model 12B, which models the three-dimensional structure of field piping 2B. Furthermore, Figures 4 and 5 show side views of ideal piping 2A and field piping 2B, respectively. As an example, the parametric functions of design support tools such as CAD (Computer-Aided Design) can be used to generate piping model 12A shown in Figure 4 and piping model 12B shown in Figure 5. For example, piping model 12A and piping model 12B can be automatically generated by deforming the shape and dimensions of a piping model (not shown) that has been created in advance as a template, according to the parameters set in the first piping condition or the second piping condition. Here, we have given an example in which piping models 12A and 12B are generated based on the first and second piping conditions, but it goes without saying that 3D CAD data of ideal piping 2A and on-site piping 2B can also be obtained as piping models 12A and 12B.

[0035] The calculation information DB13 may be implemented as a database that stores information used for flow rate calculation by the virtual flow meter 4. As merely an example, the calculation information DB13 may store the calculation method used by the virtual flow meter 4 for flow rate calculation and the calculation data specifications used during calculation, for each sensing principle of the virtual flow meter 4. Examples of types of flow meters based on their sensing principles include ultrasonic flow meters, electromagnetic flow meters, vortex flow meters, orifice flow meters, and Coriolis flow meters. Here, the sensing principle is given as merely an example of the unit in which the calculation method and calculation data specifications are stored, but it can be further subdivided. For example, even with the same sensing principle, the calculation method and calculation data specifications may not be the same if the models are different, so the calculation method and calculation data specifications may be stored for each flow meter model. Also, the calculation method and calculation data specifications may differ depending on the pipe diameter, so the calculation method and calculation data specifications may be set for each flow meter model and pipe diameter.

[0036] The generation unit 14 has the function of generating a piping model. In one aspect, when the generation unit 14 receives the setting of first piping conditions or second piping conditions via the client terminal 30, it can generate a piping model 12A of the ideal piping 2A or a piping model 12B of the field piping 2B according to the first piping conditions or second piping conditions.

[0037] As an example, we will explain using the usage scenario in which a piping model 12B for on-site piping 2B is generated. In this case, the generation unit 14 accepts the setting of the above-mentioned flow deviation parameters as a second piping condition via the client terminal 30. Then, the generation unit 14 generates the piping model 12B for on-site piping 2B by deforming the shape and dimensions of the piping model that was previously created as a template according to the flow deviation parameters that were accepted via the client terminal 30. The piping model 12B for on-site piping 2B that is thus generated is saved in the piping information DB 12.

[0038] Figure 6 shows an example of setting the flow deviation generation parameters. As shown in Figure 6, the flow deviation generation parameter for the field piping 2B is set to the straight pipe length L in the field piping 2B. R Examples include whether or not elbow pipes are connected in the field piping 2B, and the amount of deviation of the central axis in the field piping 2B. For example, the straight pipe length L R The straight pipe length L shown in Figure 6 is shown. R The dimensions can be set by accepting numerical input for the corresponding dimensions. In addition, the presence or absence of elbow pipe connection can be set by accepting input via a GUI (Graphical User Interface) component that allows selection of the presence or absence of elbow pipe, such as a pull-down menu or radio buttons, as shown by the thick line in Figure 6. Furthermore, the amount of deviation of the central axis can be set by accepting numerical input for the dimension corresponding to the gap G between the central axis shown by the dashed line in Figure 6 and the central axis shown by the double dashed line in Figure 6. At this time, by entering "0" as the amount of deviation of the central axis, the setting of no axis deviation can be activated.

[0039] Note that the flow deviation generation parameters shown in Figure 6 are merely examples, and other flow deviation generation parameters can also be set. For example, the generation unit 14 can also accept settings such as the dimensions of the shrinking or expanding pipe.

[0040] The first calculation unit 15 has the function of calculating the flow velocity profile at the measurement site of the virtual flow meter. As just one example, the first calculation unit 15 can calculate the flow velocity profile by performing a fluid simulation using an analysis tool such as CAE (Computer-Aided Engineering).

[0041] In the fluid simulation described above, the piping model of either the ideal piping 2A or the field piping 2B, and the fluid flow inside the piping model, may be reproduced in virtual space based on the following input data for each ideal piping 2A and field piping 2B.

[0042] For example, in the case of a fluid simulation in on-site piping 2B, the first calculation unit 15 reproduces the on-site piping 2B in a virtual space based on the piping model 12B stored in the piping information DB 12. Then, the first calculation unit 15 defines the fluid flowing inside the on-site piping 2B based on fluid property information stored in the fluid information DB 11A, such as density and viscosity. The term "define" here may be rephrased as "clarify" or "specify". At this time, the flow rate of the fluid flowing through the on-site piping 2B is the measured flow rate V of the on-site flow meter 22 stored in the flow rate value DB 11B. f It can be decided based on this.

[0043] Subsequently, the first calculation unit 15 divides the structure including the field piping 2B and the fluid flowing inside the field piping 2B into a grid and represents it as a grid, determining the physical quantities of each grid so as to satisfy fundamental laws such as Laplace's equation and Poisson's equation. At this time, typical examples of algorithms used for fluid simulation analysis include the difference method and the finite element method. For example, in the difference method, the structure is divided into an orthogonal grid and the gradient of physical quantities between adjacent grid points is calculated. In the finite element method, the structure is divided into tetrahedra, etc., and the distribution of physical quantities inside the divided elements is interpolated with shape functions, reducing the calculation to a system of linear equations for all elements. Among the fluid simulation results obtained by such analysis, the distribution of the flow velocity in the measurement part of the virtual flow meter 4 is the flow velocity profile V R It is obtained as follows. Note that here, the flow velocity profile V of the field piping 2B R I have given an example of how this is calculated, but by replacing the piping model defined in the virtual space with piping model 12A and running the fluid simulation, the flow velocity profile V of the ideal piping 2A can be calculated. L You can obtain it.

[0044] Figures 7 and 8 are (1) and (2) showing examples of fluid simulation results. Figure 7 shows the fluid simulation results for ideal piping 2A, while Figure 8 shows the fluid simulation results for field piping 2B. Furthermore, in Figures 7 and 8, the measurement locations of the virtual flow meter 4 in ideal piping 2A and field piping 2B are indicated by hatching. Also, Figure 7 shows a side view 40A of the fluid simulation results for ideal piping 2A, and a cross-sectional view 41A taken along the AA arrow in side view 40A. Furthermore, Figure 8 shows a side view 40B of the fluid simulation results for field piping 2B, and a cross-sectional view 41B taken along the BB arrow in side view 40B.

[0045] For example, in the example shown in Figure 7, the velocity distribution in the hatched portion of the fluid simulation result 40A for ideal pipe 2A is the velocity profile V of ideal pipe 2A. L This is obtained as follows. Furthermore, in the example shown in Figure 8, the velocity distribution in the hatched portion of the fluid simulation result 40B of the field piping 2B is the velocity profile V of the field piping 2B. R It is acquired as such.

[0046] The second calculation unit 16 calculates the flow velocity profile V for each of the two piping conditions, ideal piping 2A and field piping 2B. L Or flow velocity profile V R The flow rate prediction value V is measured by the virtual flow meter 4 based on this. i and flow rate prediction value V P It has the function to calculate [something].

[0047] Here, the second calculation unit 16 calculates the flow rate prediction value V according to the sensing principle of the virtual flow meter 4. i and flow rate prediction value V PThe calculation method can be changed. In one embodiment, the second calculation unit 16 acquires the calculation method and calculation data parameters corresponding to the sensing principle of the virtual flow meter 4 to be calculated from among the calculation methods and calculation data parameters stored in the calculation information DB 13. Then, the second calculation unit 16 calculates the flow velocity profile V L Or flow velocity profile V R Using the calculation data parameters as input, the virtual flow meter 4 predicts the flow rate V of the ideal piping 2A according to the calculation method corresponding to the sensing principle of the virtual flow meter 4. i Alternatively, the predicted flow rate V of the virtual flow meter 4 of the on-site piping 2B. P Calculate.

[0048] As just one example, the second calculation unit 16 predicts the flow rate V according to the sensing principles of ultrasonic flow meters, electromagnetic flow meters, vortex flow meters, orifice flow meters, and Coriolis flow meters. i and flow rate prediction value V P It has calculation blocks 16A to 16E for calculating the following. Figure 3 shows an example where there is a calculation block for each sensing principle of the virtual flow meter 4, but there may also be a calculation block for each model of the virtual flow meter 4, or there may be a calculation block for each model of the virtual flow meter 4 and the diameter of the pipe.

[0049] (1)Ultrasonic flowmeter Calculation block 16A predicts the flow rate V according to the sensing principle of the ultrasonic flow meter. i and flow rate prediction value V P The calculation is performed. Figure 9 is a schematic diagram (1) illustrating the input and output of calculation block 16A. Figure 10 is a schematic diagram illustrating the sensing principle of the ultrasonic flow meter. As shown in Figure 9, the calculation block 16A of the ultrasonic flow meter has the flow velocity profile V calculated by the first calculation unit 15. L Or flow velocity profile V R Along with the input, ultrasonic design information is input as an example of calculation data parameters stored in the calculation information DB13.

[0050] As shown in Figure 10, in an ultrasonic flowmeter, ultrasonic sensor UW1 is positioned on the upstream side of the piping to be measured, and ultrasonic sensor UW2 is positioned on the downstream side. The transmitting and receiving units of these two ultrasonic sensors are positioned on either side of the central axis of the piping to be measured. Under this sensor configuration, the ultrasonic flowmeter outputs a flow rate value based on the time difference between the propagation time of ultrasonic waves in a first path from the upstream ultrasonic sensor UW1 to the downstream ultrasonic sensor UW2, and the propagation time of ultrasonic waves in a second path from the downstream ultrasonic sensor UW2 to the upstream ultrasonic sensor UW1. Here, a sensor configuration in which two ultrasonic sensors UW1 and UW2 are positioned at two locations, upstream and downstream, is given as an example, but it is not necessary to have two sensors. For example, an ultrasonic flowmeter may have a sensor configuration in which one ultrasonic sensor emits ultrasonic waves and receives the reflected waves, such as a Doppler type.

[0051] Given that ultrasonic flowmeters utilize such sensing principles, the ultrasonic design information may include information used to reproduce the first and second pathways described above. For example, it may include information such as the structure of the upstream and downstream ultrasonic sensors, the arrangement of each ultrasonic sensor (relative distance and size), the characteristics of the piping, and the structure of the piping. The ultrasonic design information may be obtained in advance by conducting experiments or analyses.

[0052] When these flow velocity profiles and ultrasonic design information are input, the ultrasonic flow meter calculation block 16A performs a coupled analysis of the flow velocity profile and the first and second paths that propagate the ultrasonic waves, thereby calculating the propagation time difference between the first and second paths as a physical quantity output by the ultrasonic flow meter. Then, according to the calculation method stored in the calculation information DB 13, the ultrasonic flow meter calculation block 16A calculates the flow rate prediction value for each ideal pipe 2A and field pipe 2B by multiplying the propagation time difference by the propagation coefficient.

[0053] (2) Electromagnetic flowmeter Calculation block 16B calculates the flow rate prediction value V according to the sensing principle of the electromagnetic flow meter.i and flow rate prediction value V P The calculation is performed. Figure 11 is a schematic diagram (2) illustrating the input and output of calculation block 16B. Figure 12 is a schematic diagram illustrating the sensing principle of the electromagnetic flowmeter. As shown in Figure 11, the calculation block 16B of the electromagnetic flowmeter has the flow velocity profile V calculated by the first calculation unit 15. L Or flow velocity profile V R Along with the input, the magnetic field distribution and weight function are input as examples of calculation data parameters stored in the calculation information DB13.

[0054] In other words, an electromagnetic flowmeter uses Faraday's electromagnetic induction phenomenon to measure flow rate based on the electromotive force generated by the flow of a conductive fluid through a magnetic field. Here, the electromotive force of an electromagnetic flowmeter can be calculated by multiplying the cross product of the magnetic flux density and fluid velocity distribution at each point within the measurement area of ​​the coil by a weighting function that represents the degree to which the electromotive force contributes to the electrode potential.

[0055] Given that electromagnetic flowmeters possess such sensing principles, the calculation information DB13 may store, as an example of calculation data parameters, the magnetic field distribution and weight function shown in Figure 12. For example, the magnetic field distribution can be obtained by calculating the magnetic flux density inside the measurement site using the dimensions and physical properties of the coil and magnetic material inside the flowmeter. Such magnetic flux density may be obtained by any method, such as magnetic field simulation, theory, or experiment. The weight function may be a function that represents the distance between each point inside the measurement site and the electrode. The flow velocity distribution at the measurement site can be obtained from the flow velocity profile calculated by the first calculation unit 15.

[0056] When these velocity profiles, magnetic field distributions, and weighting functions are input, the electromagnetic flowmeter calculation block 16B performs a coupled analysis of the velocity profiles, magnetic field distributions, and weighting functions. For example, the electromagnetic flowmeter calculation block 16B multiplies the cross product of the magnetic field distribution and fluid velocity distribution inside the measurement area by the coil by the weighting function, according to the calculation method stored in the calculation information DB 13. This calculates the electromotive force as a physical quantity output by the electromagnetic flowmeter. Using this electromotive force, the electromagnetic flowmeter calculation block 16B calculates the flow rate prediction value for both the ideal piping 2A and the field piping 2B.

[0057] (3) Vortex flow meter Calculation block 16C predicts the flow rate V according to the sensing principle of the vortex flowmeter. i and flow rate prediction value V P The flow velocity profile V calculated by the first calculation unit 15 is calculated. Figure 13 is a schematic diagram (3) illustrating the input and output of calculation block 16C. Figure 14 is a schematic diagram illustrating the sensing principle of the vortex flowmeter. As shown in Figure 13, the calculation block 16C of the vortex flowmeter has the flow velocity profile V calculated by the first calculation unit 15. L Or flow velocity profile V R Along with the input, the design information of the piping to be measured is entered as an example of the calculation data parameters stored in the calculation information DB13.

[0058] In other words, as shown in Figure 14, a vortex flow meter has a vortex generator installed in the pipe to be measured. As a result, when the fluid passes through the vortex generator, a Karman vortex is generated downstream of the vortex generator. Based on the principle that the frequency of such Karman vortices is proportional to the fluid velocity, the flow velocity and flow rate inside the pipe to be measured are calculated. For example, the frequency of Karman vortices can be detected by pulsing the vortex frequency through a sensor (such as a pressure sensor or ultrasonic sensor) installed inside the vortex generator or the pipe to be measured.

[0059] Given that vortex flowmeters utilize such sensing principles, the calculation information DB13 may store piping design information, such as the shape and dimensions of the vortex generator, or a piping model including the vortex generator.

[0060] When these flow velocity profiles and piping design information are input, the vortex flowmeter calculation block 16C performs a coupled analysis of the flow velocity profile and the piping to be measured. For example, the vortex flowmeter calculation block 16C performs an unsteady fluid simulation that reproduces the structure including the vortex generator according to the calculation method stored in the calculation information DB13. This reproduces Karman vortices in a virtual space and obtains changes in fluid flow and pressure. From the fluid flow and pressure changes obtained in this way, the vortex frequency is calculated as a physical quantity output by the vortex flowmeter. Using this vortex frequency, the vortex flowmeter calculation block 16C calculates flow rate prediction values ​​for both the ideal piping 2A and the field piping 2B.

[0061] (4) Orifice flow meter Calculation block 16D predicts the flow rate V according to the sensing principle of the orifice flow meter. i and flow rate prediction value V P The following is calculated. Figure 15 is a schematic diagram (4) illustrating the input and output of calculation block 16D. Figure 16 is a schematic diagram illustrating the sensing principle of the orifice flow meter. As shown in Figure 15, the calculation block 16D of the orifice flow meter has the flow velocity profile V calculated by the first calculation unit 15. L Or flow velocity profile V R Along with the input, the design information of the orifice plate is entered as an example of the calculation data parameters stored in the calculation information DB13.

[0062] In other words, as shown in Figure 16, an orifice flow meter inserts a disc with an opening, a so-called orifice plate O1, into the piping and calculates the flow rate from the pressure difference across the orifice plate O1 according to Bernoulli's theorem. This pressure difference is detected by a pressure gauge P1 installed upstream of the orifice plate O1 and a pressure gauge P2 installed downstream of the orifice plate O1. Although Figure 16 shows an example using two pressure gauges, P1 and P2, a differential pressure gauge that detects the pressure difference across the orifice plate O1 may also be installed.

[0063] Given that orifice flow meters utilize such sensing principles, the calculation information DB13 may store piping design information, such as the piping model including the orifice plate O1 and the arrangement of pressure gauges.

[0064] When these flow velocity profiles and piping design information are input, the orifice flow meter calculation block 16D performs a coupled analysis of the flow velocity profile and the piping to be measured. For example, the orifice flow meter calculation block 16D performs a fluid simulation using the flow velocity profile as the input condition for the upstream side of the orifice plate O1. This analyzes the fluid flow inside the piping to be measured in a virtual space and reproduces the pressure distribution. The pressures corresponding to the positions of two pressure gauges from this reproduced pressure distribution are referenced. For example, the pressure difference is calculated as a physical quantity output by the orifice flow meter from the pressure observed at the position of pressure gauge P1 upstream of the orifice plate O1 and the pressure observed at the position of pressure gauge P2 downstream of the orifice plate O1. Using this pressure difference, the orifice flow meter calculation block 16D calculates the flow rate prediction value for each ideal piping 2A and field piping 2B.

[0065] (5) Coriolis flowmeter Calculation block 16E predicts the flow rate V according to the sensing principle of the Coriolis flow meter. i and flow rate prediction value V PThe following is calculated. Figure 17 is a schematic diagram (5) illustrating the input and output of the calculation block 16E. Figure 18 is a schematic diagram illustrating the sensing principle of the Coriolis flow meter. As shown in Figure 17, the calculation block 16E of the Coriolis flow meter has the flow velocity profile V calculated by the first calculation unit 15. L Or flow velocity profile V R Along with the input, the tube shape model, the exciter excitation force, and the pick-off position are input as examples of calculation data parameters stored in the calculation information DB13.

[0066] In other words, as shown in Figure 18, in a Coriolis flow meter, fluid flows in from the upstream side of the two tubes. This causes a phase difference to occur in the upstream and downstream oscillations of the two tubes, according to the Coriolis force generation principle. By detecting this phase difference with the first pickoff P1 and the second pickoff P2, the mass flow rate is calculated from this phase difference.

[0067] Given that the Coriolis flow meter employs such sensing principles, the calculation information DB13 may store, as an example of calculation data parameters, the coefficient SK of the feature function of the two tubes, the frequency of the exciter E1, and the positions of the first pick-off point P1 and the second pick-off point P2. Of these, the coefficient SK may include the tube shape of the Coriolis flow meter model, temperature, pressure influence, etc.

[0068] When these flow velocity profiles and calculation data parameters are input, the Coriolis flow meter calculation block 16E calculates the mass flow rate by multiplying the coefficient SK of the tube's feature function by the phase difference τ between the two tubes, according to the calculation method stored in the calculation information DB 13. For example, the Coriolis flow meter calculation block 16E uses the flow velocity profile as the upstream input condition and performs a coupled fluid and stress analysis in accordance with the frequency of the exciter E1. From the results of such a coupled analysis, corresponding to the positions of the first pickoff P1 and the second pickoff P2, the phase difference τ is calculated as a physical quantity output by the Coriolis flow meter. By multiplying this phase difference τ by the coefficient SK of the tube's feature function, the Coriolis flow meter calculation block 16E calculates the flow rate prediction value for each ideal piping 2A and field piping 2B.

[0069] Returning to the explanation of Figure 3, the comparison section 17 compares the flow rate prediction value V between the two piping conditions, ideal piping 2A and field piping 2B. i and flow rate prediction value V P It has a function to compare. As shown in Figure 3, the comparison unit 17 has an alert unit 17A, a first correction unit 17B, and a second correction unit 17C.

[0070] The alert unit 17A receives the flow rate prediction value V i and flow rate prediction value V P It has a function to output an alert as a result of the comparison. As just one example, the alert unit 17A outputs an alert based on the flow rate prediction value V i and flow rate prediction value V P The difference is calculated. Then, the alert unit 17A calculates the flow rate prediction value V. i and flow rate prediction value V P The system determines whether the difference, for example, the absolute value, exceeds a predetermined threshold Th. Based on this, the alert unit 17A determines whether the flow rate prediction value V i and flow rate prediction value V PIf the difference of exceeds a predetermined threshold Th, an alert is output to the client terminal 30. Such an alert may include a message or the like prompting restriction or prohibition of the use of the virtual flow meter 4 in the field pipe 2B. The above threshold Th can be system-configured or user-configured for each sensing principle or model of the virtual flow meter 4, or for each facility where the pipe is installed.

[0071] The first correction unit 17B is configured to calculate the flow rate predicted value V i and the flow rate predicted value V P based on the comparison result of, has a function of correcting the actual measured value of the flow rate measured by the field flow meter 22. As one aspect, the first correction unit 17B calculates the flow rate predicted value V i and the flow rate predicted value V P by executing inverse problem analysis using, to correct the actual flow rate measurement value of the field flow meter 22. Such correction can be realized by a ratio correction method or a difference correction method.

[0072] As one aspect, when the ratio correction method is used, the actual flow rate measurement value V of the field flow meter 22 is obtained according to the following formula (1) F The correction coefficient C used for the correction of V can be calculated. That is, as shown in the following formula (1), the correction coefficient C V is the flow rate predicted value V of the field pipe 2B P divided by the flow rate predicted value V of the ideal pipe 2A i can be calculated. After that, the actual flow rate measurement value V of the field flow meter 22 is obtained according to the following formula (2) F can be corrected. That is, as shown in the following formula (2), the actual flow rate measurement value V of the field flow meter 22 F divided by the correction coefficient C V , the corrected flow rate value V0 of the field flow meter 22 can be calculated.

[0073] C V =V P / V i ···(1) V0=V F / C V ···(2)

[0074] In another aspect, when the difference correction method is used, the correction amount ΔV used for correcting the actual measured flow rate value of the on-site flow meter 22 can be calculated according to the following equation (3). That is, as shown in the following equation (3), the correction amount ΔV is the flow rate predicted value V of the on-site piping 2B P minus the flow rate predicted value V of the ideal piping 2A i . That can be calculated by subtraction. Furthermore, the actual measured flow rate value V of the on-site flow meter 22 can be corrected according to the following equation (4) F . That is, as shown in the following equation (4), by subtracting the correction amount ΔV from the actual measured flow rate value V of the on-site flow meter 22 F , the corrected flow rate value V0 of the on-site flow meter 22 can be calculated.

[0075] ΔV=V P -V i ···(3) V0=V F -ΔV···(4)

[0076] The corrected flow rate value V0 of the on-site flow meter 22 calculated in this way can be output to backend services and applications, including the client terminal 30, by way of example only.

[0077] The second correction unit 17C has a function of correcting the actual measured flow rate value measured by the on-site flow meter 22, based on the flow rate predicted value V obtained by repeating the calculations by the first calculation unit 15 and the second calculation unit 16 i ' and the flow rate predicted value V P '.

[0078] In one embodiment, when the flow rate predicted value V is calculated by the second calculation unit 16 i and the flow rate predicted value V P , the second correction unit 17C uses the flow rate predicted value V obtained by the first correction unit 17B instead of the actual measured flow rate value V of the on-site flow meter 22 stored in the flow rate value DB 11B f i and the flow rate predicted value V P ​By inputting the corrected flow rate value V0 of the on-site flow meter 22, calculated using the above method, into the first calculation unit 15, the first calculation unit 15 and the second calculation unit 16 are made to perform a recalculation. This results in the predicted flow rate value V i `and flow rate prediction value V P These flow rate prediction values ​​V are obtained. i `and flow rate prediction value V P The corrected flow rate value V0 of the on-site flow meter 22, calculated using the above method, is output to the client terminal 30. This iterative calculation further improves the accuracy of the correction of the measured flow rate value of the on-site flow meter 22. The recalculations by the first calculation unit 15 and the second calculation unit 16 can be repeated any number of times.

[0079] <Processing flow> Next, the processing flow of the server device 10 according to this embodiment will be described. Here, we will first describe the (1) generation process performed by the server device 10, and then the (2) prediction process.

[0080] (1) Generation process Figure 19 is a flowchart showing the steps of the generation process. This process can be started, as an example, when a generation request is received from the client terminal 30 requesting the generation of a piping model 12B for the field piping 2B.

[0081] As shown in Figure 19, the generation unit 14 accepts the setting of the above-mentioned flow deviation generation parameters via the client terminal 30 as a second piping condition (step S101).

[0082] Then, the generation unit 14 generates a piping model 12B for the field piping 2B by deforming the shape and dimensions of a pre-created template piping model according to the flow deviation generation parameters accepted in step S101 (step S102).

[0083] Subsequently, the generation unit 14 saves the piping model 12B of the field piping 2B generated in step S102 to the piping information DB 12 (step S103), and terminates the process.

[0084] (2) Prediction processing Figure 20 is a flowchart showing the procedure for the prediction process. This process can be started, as an example, when a prediction request for the effects of flow drift is received from the client terminal 30.

[0085] As shown in Figure 20, the first calculation unit 15 acquires fluid property information of the field piping 2B from the fluid information DB 11A (step S301). Furthermore, the first calculation unit 15 acquires piping information from the piping information DB 12, including the piping model 12A of the ideal piping 2A and the piping model 12B of the field piping 2B (step S302).

[0086] Then, the first calculation unit 15 calculates the flow velocity profile (V) at the measurement point of the virtual flow meter 4 for each ideal piping 2A and field piping 2B. L ,V R ) calculate (step S303).

[0087] Next, the second calculation unit 16 acquires the calculation method and calculation data parameters from the calculation information DB 13 that correspond to the sensing principle of the virtual flow meter 4 to be calculated (step S304).

[0088] Then, the second calculation unit 16 calculates the flow velocity profile V for each of the two piping conditions, ideal piping 2A and field piping 2B. L Or flow velocity profile V R Based on this, the physical quantity output by the virtual flow meter 4 is calculated (step S305).

[0089] Then, the second calculation unit 16 calculates the flow rate prediction value V from the physical quantity calculated in step S305. i and flow rate prediction value V P The calculation is performed (step S306). Note that in steps S305 and S306, the sensing principle of the field flow meter 22 may be the subject of the calculation, or one or more arbitrary sensing principles may be the subject of the calculation.

[0090] Subsequently, the comparison unit 17 calculates the flow rate prediction value V between the two piping conditions, ideal piping 2A and field piping 2B. i and flow rate prediction value V P By comparing these, an alert can be determined, and the measured flow rate V from the on-site flow meter 22 can be used to determine the alert. F Correction coefficient C used for correction V Alternatively, the correction amount ΔV is calculated, the corrected flow rate value V0 of the on-site flow meter 22 is calculated, etc. (step S307).

[0091] And the predicted flow rate value V i and flow rate prediction value V P If the difference exceeds a predetermined threshold Th (step S308: Yes), the comparison unit 17 outputs an alert to the client terminal 30 (step S309). Note that the flow rate prediction value V i and flow rate prediction value V P If the difference does not exceed a predetermined threshold Th (step S308: No), the processing in step S309 is skipped.

[0092] Subsequently, the comparison unit 17 uses the correction coefficient C calculated in step S307. V The correction amount ΔV and the corrected flow rate value V0 from the on-site flow meter 22 are output to the client terminal 30 (step S310), and the process ends.

[0093] <Summary> As described above, the server device 10 according to this embodiment calculates the flow velocity profile at the point where the flow rate is measured by a virtual flow meter under each of two piping conditions: a first piping condition in which the dimensions of the first pipe are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set. Based on the flow velocity profile for each of the two piping conditions, it calculates a predicted value of the flow rate measured by the virtual flow meter and outputs the result of comparing the predicted values ​​between the two piping conditions. Therefore, according to the server device 10 according to this embodiment, it is possible to predict the effect of flow deviation occurring in the field piping where the flow meter is installed.

[0094] <Embodiment 2> Now, while embodiments of this disclosure have been described, various applications are possible, and furthermore, it may be implemented in various different forms other than those described above.

[0095] <Surrogate AI> In the above embodiment 1, an example was given in which the flow velocity profile of the measurement site of the virtual flow meter is calculated by fluid simulation, but it is also possible to calculate the flow velocity profile of the measurement site of the virtual flow meter 4 using a surrogate AI model. Figure 21 is a schematic diagram (1) showing an example of a surrogate AI model. As shown in Figure 21, at least one of the following data can be input as explanatory variables to the input layer of the surrogate AI model: fluid physical property information, measured flow rate of the field flow meter 22, diameter information of the virtual flow meter 4, and piping information of piping model 12A or piping model 12B. The surrogate AI model with such explanatory variables input has the flow velocity profile V of the measurement site of the virtual flow meter 4 as the objective variable. L Or flow velocity profile V R This is output from the output layer. Such a surrogate AI model can reduce the amount of computation compared to when the velocity profile is calculated using fluid simulation with analysis tools such as CAE.

[0096] The objective variable of such a surrogate AI model is not limited to the flow velocity profile of the measurement site of the virtual flowmeter 4, but may also be the flow rate predicted value of the virtual flowmeter. Figure 22 is a schematic diagram (2) showing an example of a surrogate AI model. As shown in Figure 22, the input layer of the surrogate AI model can be input as explanatory variables at least one of the following: fluid physical property information, measured flow rate of the field flowmeter 22, diameter information of the virtual flowmeter 4, piping information of piping model 12A or piping model 12B, model information of the virtual flowmeter 4, and external influences of the field flowmeter 22 (such as vibration). In a surrogate AI model with such explanatory variables input, the objective variable is the flow rate predicted value V of the virtual flowmeter 4. i Or the predicted flow rate V PThe output layer outputs the following. Such a surrogate AI model can achieve a further reduction in computational load compared to when the velocity profile and flow rate prediction values ​​of a virtual flow meter are calculated using fluid simulation with analysis tools such as CAE. Note that the surrogate AI models shown in Figures 21 and 22 are merely examples of AI models and may be implemented using machine learning models other than neural networks.

[0097] <Exhibiting creative abilities> The matters described in the above embodiment, such as the sensing principle of the virtual flow meter 4 and its specific examples, are merely examples and can be modified. Furthermore, the flowchart described in the embodiment can also be modified in terms of processing order, provided it is consistent with the original design.

[0098] <System> The processing procedures, control procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed at will unless otherwise specified. For example, one or more of the functional units of the server device 10, such as the generation unit 14, the first calculation unit 15, the second calculation unit 16, and the comparison unit 17, may be configured as separate devices.

[0099] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown. That is, all or part of them can be functionally or physically distributed and integrated in any units according to various loads and usage conditions. Note that each configuration may also be a physical configuration.

[0100] Furthermore, each processing function performed by each device may be implemented, in whole or in part, by a CPU (Central Processing Unit) and a program executed by that CPU, or by wired logic hardware.

[0101] <Hardware> Next, an example of the computer hardware configuration described in the above embodiment will be explained. Figure 23 is a diagram showing an example of the hardware configuration. As shown in Figure 23, the server device 10 has a communication device 10a, a storage device 10b, memory 10c, and a processor 10d. Note that the parts shown in Figure 23 may be interconnected by a bus or the like.

[0102] The communication device 10a is a network interface card, etc. The storage device 10b is a storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). For example, the storage device 10b stores programs and databases that operate the functions shown in Figure 3.

[0103] The processor 10d runs a process that performs the same processing as the processing unit shown in Figure 3 by reading a program from the storage device 10b or the like and loading it into memory 10c.

[0104] Such a process implements functions similar to those of the processing unit in the server device 10. For example, the processor 10d reads a program having functions similar to those of the generation unit 14, the first calculation unit 15, the second calculation unit 16, and the comparison unit 17 from the storage device 10b or the like. Then, the processor 10d executes a process that performs the same processing as the generation unit 14, the first calculation unit 15, the second calculation unit 16, and the comparison unit 17.

[0105] Thus, the server device 10 operates as an information processing device that executes a prediction method by reading and executing a program. Furthermore, the server device 10 can also achieve the same functionality as the embodiment described above by reading the program from a recording medium using a media reader and executing the read program. It should be noted that the program referred to in this other embodiment is not limited to being executed by the server device 10. For example, the present invention can be similarly applied when another computer or server executes the program, or when they collaborate to execute the program.

[0106] The above program can be distributed via a network such as the Internet. Furthermore, the program can be recorded on any storage medium and executed by reading it from the medium by a computer. For example, the storage medium can be a hard disk, flexible disk (FD), CD-ROM, MO (Magneto-Optical disk), DVD (Digital Versatile Disc), etc.

[0107] <Other> Some examples of the combinations of technical features that will be disclosed are listed below.

[0108] (1) Equipped with a processor, The aforementioned processor, The process involves calculating the flow velocity profile at a point where the flow rate is measured by a flow meter under two piping conditions: a first piping condition in which the dimensions of the first pipe are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set. For each of the two aforementioned piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile, Outputting the results of comparing the predicted values ​​between the two aforementioned piping conditions, A processing unit that executes this process.

[0109] (2) The processing apparatus according to (1), wherein the processor calculates the flow velocity profile by performing a fluid simulation that reproduces a piping model in which the three-dimensional structure of the first piping or the second piping is modeled in a virtual space and the fluid flow inside the piping model.

[0110] (3) The processing apparatus according to (1) or (2), wherein the processor uses at least one of the following as explanatory variables: piping conditions relating to the piping, physical properties of the fluid flowing inside the piping, measured values ​​of the flow rate in the piping, the diameter of the flow meter, the model of the flow meter, and the external environment of the piping, and inputs the first piping conditions or the second piping conditions to an AI model which has either a flow velocity profile or a predicted value of the flow rate as the objective variable, thereby causing the AI ​​model to output the flow velocity profile or the predicted value of the flow rate.

[0111] (4) The processing apparatus according to (2) or (3), wherein the processor further performs the process of generating the piping model by deforming the shape and dimensions of a three-dimensional model created in advance as a template, according to the parameters set in the first piping conditions or the second piping conditions.

[0112] (5) The processing apparatus according to any one of (1) to (4), wherein the processor accepts the setting of at least one parameter from among the straight pipe length upstream of the second pipe, whether or not a curved pipe is connected in the second pipe, and the amount of deviation of the central axis in the second pipe as parameters related to the occurrence of the flow deviation.

[0113] (6) The processing device according to any one of (1) to (5), wherein the processor changes the method of calculating the predicted value of the flow rate measured by the flow meter according to the sensing principle of the flow meter.

[0114] (7) The processing device according to any one of (1) to (6), wherein the processor outputs an alert when the difference between the predicted values ​​between the two piping conditions is greater than or equal to a predetermined threshold.

[0115] (8) The processing apparatus according to any one of (1) to (7), wherein the processor corrects the measured flow rate measured in the second pipe based on the result of comparing the predicted values ​​between the two piping conditions.

[0116] (9) Computers Under each of two piping conditions, a first piping condition in which the dimensions of the first pipe are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set, the flow velocity profile is calculated at the point where the flow rate is measured by a flow meter. For each of the two piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile. Output the result of comparing the predicted values ​​between the two piping conditions. How to execute the process.

[0117] (10) To the computer, Under each of two piping conditions, a first piping condition in which the dimensions of the first pipe are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second pipe are set, the flow velocity profile is calculated at the point where the flow rate is measured by a flow meter. For each of the two piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile. Output the result of comparing the predicted values ​​between the two piping conditions. A program that executes a process. [Explanation of Symbols]

[0118] 1. Prediction System 2A ideal piping 2B On-site piping 4. Virtual flow meter 10 Server devices 11A Fluid information DB 11B Flow Rate Value DB 12 Piping Information Database 13. Calculation Information Database 14 Generation part 15. First Calculation Unit 16 Second Calculation Unit 16A~16D Calculation Blocks 17. Comparison Section 17A Alert Section 17B First Correction Unit 17C Second Correction Section 20 Sensor Modules 21 Fluid Properties Sensor 22 Field flow meter 30 client terminals

Claims

1. Equipped with a processor, The aforementioned processor, The process involves calculating the flow velocity profile at a point where the flow rate is measured by a flow meter under two piping conditions: a first piping condition in which the dimensions of the first piping are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second piping are set. For each of the two aforementioned piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile, Outputting the results of comparing the predicted values ​​between the two piping conditions, A processing unit that executes this process.

2. The processing apparatus according to claim 1, wherein the processor calculates the flow velocity profile by performing a fluid simulation that reproduces a piping model in which the three-dimensional structure of the first piping or the second piping is modeled in a virtual space, and the fluid flow inside the piping model.

3. The processing apparatus according to claim 1, wherein the processor uses at least one of the following as explanatory variables: piping conditions relating to the piping, physical properties of the fluid flowing inside the piping, measured flow rate in the piping, diameter of the flow meter, model of the flow meter, and external environment of the piping, and inputs the first piping conditions or the second piping conditions to an AI model that uses either a flow velocity profile or a predicted flow rate as an objective variable, thereby causing the AI ​​model to output the flow velocity profile or the predicted flow rate.

4. The processing apparatus according to claim 2, wherein the processor further performs a process to generate the piping model by deforming the shape and dimensions of a three-dimensional model created in advance as a template, according to the parameters set in the first piping conditions or the second piping conditions.

5. The processing apparatus according to any one of claims 1 to 4, wherein the processor accepts the setting of at least one parameter among the following as parameters related to the occurrence of the flow deviation: the length of the straight pipe upstream of the second pipe, whether or not a curved pipe is connected in the second pipe, and the amount of deviation of the central axis in the second pipe.

6. The processing apparatus according to any one of claims 1 to 4, wherein the processor changes the method for calculating the predicted value of the flow rate measured by the flow meter according to the sensing principle of the flow meter.

7. The processing apparatus according to any one of claims 1 to 4, wherein the processor outputs an alert when the difference between the predicted values ​​between the two piping conditions is greater than or equal to a predetermined threshold.

8. The processing apparatus according to any one of claims 1 to 4, wherein the processor corrects the measured flow rate measured in the second pipe based on the result of comparing the predicted values ​​between the two piping conditions.

9. Computers Under each of two piping conditions, a first piping condition in which the dimensions of the first piping are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second piping are set, the flow velocity profile is calculated at the point where the flow rate is measured by a flow meter. For each of the two piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile. The system outputs the result of comparing the predicted values ​​between the two piping conditions. How to execute the process.

10. On the computer, Under each of two piping conditions, a first piping condition in which the dimensions of the first piping are set, and a second piping condition in which parameters related to the occurrence of flow deviation in the second piping are set, the flow velocity profile is calculated at the point where the flow rate is measured by a flow meter. For each of the two piping conditions, the predicted flow rate measured by the flow meter is calculated based on the flow velocity profile. The system outputs the result of comparing the predicted values ​​between the two piping conditions. A program that executes a process.

Images