Tank internal fluid amount estimating system, tank information processing device, tank internal fluid amount estimating method, and storage medium

Abstract

[Problem] To enable a person in a place remote from the location of a tank to recognize the amount of fluid in a tank in real time, without using a bulky weight measuring device or providing a sensor within the tank. [Solution] This tank internal fluid amount estimating system comprises: deformation measuring sensors 26, 27 which are provided on an outer peripheral surface of a cylindrical tank 16 capable of accommodating a prescribed upper limit amount of fluid; a wireless transmitting device which is capable of wirelessly transmitting information relating to detected values from the deformation measuring sensors; a wireless receiving device which is capable of receiving the information relating to the detected values from the deformation measuring sensors, transmitted wirelessly by the wireless transmitting device; and an estimating unit that estimates which amount among amounts having a plurality of magnitudes, including zero and the upper limit amount, corresponds to the amount of fluid in the tank, on the basis of detected-value related information including an amount of distortion of the tank based on the detected values from the deformation measuring sensors, received by the wireless receiving device.

Description

Tank fluid volume estimation system, tank information processing device, tank fluid volume estimation method, and storage medium

[0001] The present disclosure relates to a tank fluid amount estimation system, a tank information processing device, a tank fluid amount estimation method, and a storage medium.

[0002] As disclosed in Japanese Patent Application Laid-Open No. 2021-165148, a cylindrical tank capable of accommodating a predetermined upper limit amount of fluid is known. For example, an ISO tank container (UN portable tank) is known as a tank based on standards established by the International Organization for Standardization (ISO).

[0003] Conventionally, there have been weighing devices capable of measuring the weight of this type of tank. The initial weight, which is the weight of the tank when the amount of fluid in the tank is zero, is obtained in advance, and the amount of fluid in the tank can be estimated by comparing the measured value of the weighing device with the initial weight.

[0004] The above-mentioned weighing device is a large device, and it is difficult to transport the weighing device over long distances. The filling company, which fills the tank with fluid, and the user company, which uses the fluid in the tank, may be different companies, and the filling company and the user company may be located in different places. In such cases, the weighing device is generally installed at the filling company's facility. Therefore, it is often not possible to measure the weight of the tank using the weighing device at the user company's facility.

[0005] If a sensor for measuring the amount of fluid is installed inside the tank, the amount of fluid can be detected by this sensor. However, depending on the type of material the tank is filled with, regulations may prohibit the installation of a sensor inside the tank.

[0006] The filling company, receiving information about the measurement value of the weighing device and the initial weight, can estimate the amount of fluid in the tank. However, if the tank is not weighed by the weighing device, the filling company cannot estimate the amount of fluid in the tank. In other words, the filling company cannot estimate the amount of fluid in the tank in real time.

[0007] In consideration of the above, the present disclosure aims to provide a tank fluid volume estimation system, a tank information processing device, a tank fluid volume estimation method, and a storage medium that allow a person located away from the tank's location to recognize the fluid volume in the tank in real time, without using a large-scale weight measuring device or installing a sensor inside the tank.

[0008] The tank fluid volume estimation system according to the present disclosure comprises a deformation measurement sensor that detects the amount of deformation of a tank that can hold a predetermined upper limit amount of fluid, the deformation measurement sensor being provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of the tank; a wireless transmitting device that can wirelessly transmit information related to the detection value of the deformation measurement sensor; a wireless receiving device that can receive information related to the detection value of the deformation measurement sensor wirelessly transmitted by the wireless transmitting device; and an estimation unit that estimates whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information including the amount of distortion of the tank based on the detection value of the deformation measurement sensor received by the wireless receiving device.

[0009] The tank information processing device according to the present disclosure includes a wireless receiving device capable of wirelessly receiving information relating to the detection value of a deformation measurement sensor that detects the amount of deformation of a tank that can hold a predetermined upper limit amount of fluid, the deformation measurement sensor being provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of the tank, and an estimation unit that estimates whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information that includes the amount of distortion of the tank based on the detection value of the deformation measurement sensor received by the wireless receiving device.

[0010] The method for estimating the amount of fluid in a tank according to the present disclosure includes the steps of wirelessly transmitting information relating to a detection value of a deformation measurement sensor that detects the amount of deformation of the tank and is provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of the tank that can hold a predetermined upper limit amount of fluid, receiving information relating to the wirelessly transmitted detection value, and estimating whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information including the amount of distortion of the tank based on the received detection value.

[0011] The storage medium according to the present disclosure is a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, performs the following processes: wirelessly receiving information regarding the detection value of a deformation measurement sensor provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of a tank capable of containing a predetermined upper limit amount of fluid; and estimating whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information including the amount of distortion of the tank based on the received detection value.

[0012] The tank fluid volume estimation system, tank information processing device, tank fluid volume estimation method, and storage medium disclosed herein allow a person located away from the tank's location to recognize the fluid volume in the tank in real time, without using a large weight measuring device or installing a sensor in the tank.

[0013] 1 is an overall view of a tank fluid amount estimation system according to a first embodiment of the present disclosure; FIG. 2 is a schematic cross-sectional view of a lower part of a tank; FIG. 3 is a control block diagram of a control device and a server; FIG. 4 is a functional block diagram of the control device; FIG. 5 is a functional block diagram of the server; FIG. 6 is a block diagram for explaining the operation of the server; FIG. 7 is an image diagram of machine learning using random forests; FIG. 8 is a graph showing the association between each parameter and the remaining amount of high-pressure gas; FIG. 9 is a flowchart showing processing executed by a CPU of the control device; FIG. 10 is a flowchart showing processing executed by a CPU of the server; FIG. 11 is a confusion matrix when an estimated remaining amount is determined using a trained model of the first embodiment; FIG. 12 is a confusion matrix when a trained model of a first comparative example is used, which is generated without using detected values ​​and calculated values ​​of an electrothermocouple as training data; FIG. 13 is a confusion matrix when a trained model of a second comparative example is used, which is generated without using detected values ​​and calculated values ​​of a strain sensor as training data; FIG. 14 is a graph showing the association between each parameter of the second embodiment and the remaining amount of high-pressure gas; FIG. 15 is a graph showing the association between each parameter of a modified example and the remaining amount of high-pressure gas;

[0014] The following describes a tank fluid volume estimation system 10 (hereinafter referred to as system 10), a tank fluid volume estimation system, a tank information processing device, a tank fluid volume estimation method, and a storage medium according to a first embodiment. As shown in Fig. 1, the system 10 according to this embodiment includes a tank installation device group 20, a server (tank information processing device) 30, and a display device 40. The tank installation device group 20 and the server 30 are capable of wireless communication with each other via a network N.

[0015] First, the tank device 15 in which the tank installation device group 20 is installed will be described. The tank device 15 of the first embodiment is installed within the facility of a user. Furthermore, the tank device 15 can be mounted on a vehicle (not shown) such as a four-wheeled vehicle, and can be transported to various locations using the vehicle.

[0016] As shown in FIG. 1 , the tank apparatus 15 includes a tank 16, which is a cylindrical pressure-resistant vessel extending along its central axis AX. The tank apparatus 15 further includes a heat insulating portion (not shown) provided on the outer circumferential surface of the tank 16 and a container frame (not shown) fixed to the tank 16. The tank apparatus 15 of the first embodiment is an ISO tank container. That is, the tank apparatus 15 is a portable container that can be easily moved to various locations. The tank 16 can be filled with various types of fluids. These fluids include liquids and gases. The fluid filled in the tank apparatus 15 of the first embodiment is high-pressure gas. However, most of this high-pressure gas is filled in a liquefied state in the tank apparatus 15. An inlet (not shown) for introducing high-pressure gas into the tank 16 is provided on the top surface of the tank 16.

[0017] In this specification, the cylindrical shape includes a perfect cylindrical shape and an approximately cylindrical shape. A perfect cylindrical tank 16 is a tank 16 in which both ends in the axial direction (direction along the central axis AX in FIG. 1 ) are disks made of flat plates, and the portion between these ends is cylindrical and centered on the central axis AX. An approximately cylindrical tank 16 includes, for example, a tank 16 in which both ends in the central axis AX direction are hemispherical, and the portion between these ends is cylindrical and centered on the central axis AX.

[0018] As shown in FIG. 1 , the outer peripheral surface of the tank 16 is provided with a 0% line 16L1, a 25% line 16L2, a 50% line 16L3, and a 75% line 16L4. The 0% line 16L1 is located at the same vertical position on the outer peripheral surface of the tank 16 as the lower end of the inner surface of the tank 16. Here, the volume of the entire internal space of the tank 16 is defined as V. Furthermore, the volume of the region below the 0% line 16L1 in the internal space of the tank 16 is defined as V1, the volume of the region below the 25% line 16L2 in the internal space is defined as V2, the volume of the region below the 50% line 16L3 in the internal space is defined as V3, and the volume of the region below the 75% line 16L4 in the internal space is defined as V4. In this case, V1 / V = 0, V2 / V = 0.25, V3 / V = 0.5, and V4 / V = 0.75.

[0019] 2, the 0% line 16L1 is located above the lower end of the outer circumferential surface of the tank 16. When the tank 16 is viewed along its central axis AX, the 0% line 16L1 is located above the bottom 16BP, which is the lower end of the tank 16. The bottom 16BP is the portion that comes into contact with the installation surface IF when the tank 16 is assumed to be installed directly on the horizontal installation surface IF.

[0020] 1, the tank device 15 is provided with a tank installation device group 20. The tank installation device group 20 includes thermocouples (temperature sensors) 21, 22, 23, and 24, outside air temperature sensors 25A and 25B, strain sensors 26 and 27, a control device 28, and a battery 29.

[0021] Thermocouples 21, 22, 23, and 24 are arranged vertically on the outer peripheral surface of tank 16. The vertical position of thermocouple 21 is the same as the 0% line 16L1, the vertical position of thermocouple 22 is the same as the 25% line 16L2, the vertical position of thermocouple 23 is the same as the 50% line 16L3, and the vertical position of thermocouple 24 is the same as the 75% line 16L4. Thermocouple 21 detects a 0% temperature TC1, which is the temperature of the portion of the outer circumferential surface of tank 16 where thermocouple 21 is fixed, thermocouple 22 detects a 25% temperature TC2, which is the temperature of the portion of the outer circumferential surface of tank 16 where thermocouple 22 is fixed, thermocouple 23 detects a 50% temperature TC3, which is the temperature of the portion of the outer circumferential surface of tank 16 where thermocouple 23 is fixed, and thermocouple 24 detects a 75% temperature TC4, which is the temperature of the portion of the outer circumferential surface of tank 16 where thermocouple 24 is fixed. Thermocouples 21, 22, 23, and 24 detect the 0% temperature TC1, 25% temperature TC2, 50% temperature TC3, and 75% temperature TC4, respectively, every time a predetermined time elapses.

[0022] The outside air temperature sensor 25A detects a first outside air temperature TCA, which is the air temperature around the tank 16, and the outside air temperature sensor 25B detects a second outside air temperature TCB, which is the air temperature around the tank 16. The outside air temperature sensors 25A and 25B are spaced apart from each other. For example, the outside air temperature sensors 25A and 25B are fixed to the container frame.

[0023] Strain sensors 26 and 27 are arranged vertically on the outer peripheral surface of the tank 16. In the first embodiment, the strain sensors 26 and 27 are strain gauges. The vertical position of the strain sensor 26 is the same as the 0% line 16L1, and the vertical position of the strain sensor 27 is the same as the 50% line 16L3. The strain sensors 26 and 27 detect the amount of strain at the portion of the outer peripheral surface of the tank 16 to which they are attached. This amount of strain includes axial strain, which is the amount of strain in the axial direction AD, which is a direction parallel to the central axis AX of the tank 16, and circumferential strain, which is the amount of strain in the circumferential direction CD about the central axis AX of the tank 16. That is, the strain sensor 26 detects a 0% axial strain STx1, which is the axial strain at the portion of the outer peripheral surface of the tank 16 to which the strain sensor 26 is attached, and a 0% circumferential strain STc1, which is the circumferential strain at that portion. The strain sensor 27 detects a 50% axial strain STx3, which is the axial strain at the portion of the outer circumferential surface of the tank 16 where the strain sensor 27 is fixed, and a 50% circumferential strain STc3, which is the circumferential strain at that portion.

[0024] The detection values ​​obtained by the strain sensor 26 are used to obtain the important calculated values ​​described below: 0% axial strain STx1, 0% axial strain correction value STx1-cr, and 0% circumferential strain correction value STc1-cr.

[0025] The strain sensor 26 is provided at the same vertical position as the 0% line 16L1, rather than on the bottom 16BP. Therefore, even if the bottom 16BP of the tank 16 is installed on the installation surface IF, which is a horizontal plane, as shown in Figure 2, the strain sensor 26 is located above the installation surface IF. Therefore, it is easier to attach the strain sensor 26 to a location on the outer peripheral surface of the tank 16 at the same vertical position as the 0% line 16L1 and to remove the strain sensor 26 from this location than when the strain sensor 26 is provided on the bottom 16BP.

[0026] A control device 28 and a battery 29 are fixed to the upper part of the outer circumferential surface of the tank 16 .

[0027] 3, the control device 28 has a hardware configuration including a CPU (Central Processing Unit) (processor) 28A, a ROM (Read Only Memory) 28B, a RAM (Random Access Memory) 28C, a storage 28D, a wireless communication I / F (Interface) (wireless transmission device) 28E, and an input / output I / F 28G. The CPU 28A, ROM 28B, RAM 28C, storage 28D, wireless communication I / F 28E, and input / output I / F 28G are connected to each other via an internal bus 28Z so as to be able to communicate with each other. The CPU 28A can obtain information related to the time from a timer.

[0028] The CPU 28A is a central processing unit that executes various programs (computer programs) and controls each part. The CPU 28A reads the programs from the ROM 28B or the storage 28D and executes the programs using the RAM 28C as a work area. The CPU 28A controls each component and performs various arithmetic processing in accordance with the programs recorded in the ROM 28B or the storage 28D.

[0029] The ROM (storage medium) 28B stores various programs and various data, and the RAM 28C temporarily stores programs or data as a working area.

[0030] The storage (storage medium) 28D is configured by a storage device such as a hard disk drive (HDD) or a solid state drive (SSD), and stores various programs and various data.

[0031] The wireless communication I / F 28E is configured to include an interface for connecting to the network N. The interface uses the Sigfox (registered trademark) communication standard.

[0032] The input / output I / F 28G is connected to various devices. For example, the input / output I / F 28G is connected to thermocouples 21, 22, 23, and 24, outside air temperature sensors 25A and 25B, and strain sensors 26 and 27.

[0033] 4 is a block diagram showing an example of the functional configuration of the control device 28. The control device 28 has a communication control unit 281. The function of the communication control unit 281 is realized by the CPU 28A reading and executing a program stored in the ROM 28B or the storage 28D.

[0034] The communication control unit 281 controls the wireless communication I / F 28E. The wireless communication I / F 28E can transmit and receive various information. The wireless communication I / F 28E of the first embodiment can perform wireless communication based on the Sigfox (registered trademark) standard.

[0035] The wireless communication I / F 28E receives each detection value from the thermocouples 21, 22, 23, 24, the outside air temperature sensors 25A, 25B, and the strain sensors 26, 27 every time a predetermined time has elapsed, and wirelessly transmits information about each received detection value to the server 30 described later, while associating it with the ID information attached to the tank device 15 and information about the detection time of each detection value.

[0036] The battery 29 is a rechargeable battery. For example, the battery 29 may include a plurality of rechargeable dry cells. The battery 29 can supply power to the strain sensors 26 and 27 and the control device 28.

[0037] The server 30 of the first embodiment is installed within the premises of a filling company.

[0038] 3, the server 30 includes, as its hardware configuration, a CPU 31A, a ROM 31B, a RAM 31C, a storage 31D, a wireless communication I / F 31E (wireless receiving device), and an input / output I / F 31G. The CPU 31A, the ROM 31B, the RAM 31C, the storage 31D, the wireless communication I / F 31E, and the input / output I / F 31G are connected to each other via an internal bus 31Z so as to be able to communicate with each other. The functions of the CPU 31A, the ROM 31B, the RAM 31C, the storage 31D, the wireless communication I / F 31E, the input / output I / F 31G, and the internal bus 31Z are the same as the functions of the CPU 28A, the ROM 28B, the RAM 28C, the storage 28D, the wireless communication I / F 28E, the input / output I / F 28G, and the internal bus 28Z, respectively.

[0039] As shown in FIG. 3 , the storage 31D stores an operating system including a learning program 35 and a fluid volume determination program 36. Furthermore, the storage 31D stores learning data 37 and a trained model 38. As shown in FIG. 6 , the learning data 37 stores detection value-related information A (described later) and information regarding the actual remaining amount (fluid volume) of high-pressure gas in the tank 16. Here, the information regarding the remaining amount of high-pressure gas indicates whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the total volume V of the internal space of the tank 16 is 0% or 100% (upper limit amount). Note that this "0%" includes both exact zero% and a value that can be considered substantially zero%. Substantially zero% is, for example, 1% or less. Furthermore, "100%" includes both exact 100% and a value that can be considered substantially 100%. Substantially 100% is, for example, 99% or more. Furthermore, the information regarding the actual remaining amount of high-pressure gas in the tank 16 is referred to as "actual remaining amount information B." The tank 16 of the test tank device 15 used to acquire the learning data 37 is provided with a level gauge. The actual remaining amount information B is acquired using this level gauge. For example, if the test tank device 15 is installed at a user's facility, the actual remaining amount information B is wirelessly transmitted from the control device 28 (wireless communication I / F 28E) to the server 30 (wireless communication I / F 30E). The trained model 38 will be described later.

[0040] The wireless communication I / F 31E is configured to include an interface for connecting to the network N. The interface uses the Sigfox (registered trademark) communication standard.

[0041] The input / output I / F 31G is connected to various devices. For example, the input / output I / F 31G is connected to a display device 40.

[0042] 5 is a block diagram showing an example of the functional configuration of the server 30. The server 30 has a parameter calculation unit 310, a learning unit 311, a fluid amount determination unit (estimation unit) 312, and a display control unit 313. The functions of the parameter calculation unit 310, the learning unit 311, the fluid amount determination unit 312, and the display control unit 313 are realized by the CPU 31A reading and executing programs stored in the ROM 31B or the storage 31D. More specifically, the learning unit 311 is realized by the CPU 31A reading and executing a learning program 35 from the storage 31D, and the fluid amount determination unit 312 is realized by the CPU 31A reading and executing a fluid amount determination program 36 from the storage 31D.

[0043] The parameter calculation unit 310 calculates the average outside air temperature TCav, the 0% corrected temperature TC1-cr, the 25% corrected temperature TC2-cr, the 50% corrected temperature TC3-cr, the 75% corrected temperature TC4-cr, the 0% axial distortion correction value (distortion correction value) STx1-cr, the 0% circumferential distortion correction value (distortion correction value) STc1-cr, the 50% circumferential distortion correction value (distortion correction value) STc3-cr, the 0% distortion difference amount correction value (distortion correction value) STxc1-cr, and the 50% distortion difference amount correction value (distortion correction value) STxc3-cr based on the detection values ​​of the thermocouples 21, 22, 23, 24, the outside air temperature sensors 25A, 25B, and the distortion sensors 26, 27 received by the wireless communication I / F 31E.

[0044] The parameter calculation unit 310 calculates an average outside temperature TCav, which is the average of the first outside temperature TCA and the second outside temperature TCB. That is, the average outside temperature TCav = (first outside temperature TCA + second outside temperature TCB) / 2.

[0045] Furthermore, the parameter calculation unit 310 calculates a 0% correction temperature TC1-cr, which is the value obtained by subtracting the average outside air temperature TCav from the 0% temperature TC1. That is, the 0% correction temperature TC1-cr = 0% temperature TC1 - average outside air temperature TCav.

[0046] Furthermore, the parameter calculation unit 310 calculates a 25% corrected temperature TC2-cr, which is the value obtained by subtracting the average outside air temperature TCav from the 25% temperature TC2. That is, the 25% corrected temperature TC2-cr = 25% temperature TC2 - average outside air temperature TCav.

[0047] Furthermore, the parameter calculation unit 310 calculates a 50% corrected temperature TC3-cr, which is the 50% temperature TC3 minus the average outside air temperature TCav. That is, the 50% corrected temperature TC3-cr = 50% temperature TC3 - average outside air temperature TCav.

[0048] Furthermore, the parameter calculation unit 310 calculates a 75% corrected temperature TC4-cr, which is the 75% temperature TC4 minus the average outside air temperature TCav. That is, the 75% corrected temperature TC4-cr = 75% temperature TC4 - average outside air temperature TCav.

[0049] Furthermore, the parameter calculation unit 310 calculates a 0% axial distortion correction value STx1-cr and a 0% circumferential distortion correction value STc1-cr. The 0% axial distortion correction value STx1-cr is the value obtained by subtracting the axial distortion (distortion correction amount DTx) of the entire tank 16 caused by the average outside air temperature TCav from the 0% axial distortion STx1. In other words, the 0% axial distortion correction value STx1-cr = 0% axial distortion STx1 - distortion correction amount DTx. The 0% circumferential distortion correction value STc1-cr is the value obtained by subtracting the circumferential distortion (distortion correction amount DTc) of the entire tank 16 caused by the average outside air temperature TCav from the 0% circumferential distortion STc1. In other words, the 0% circumferential distortion correction value STc1-cr = 0% circumferential distortion STc1 - distortion correction amount DTc.

[0050] Furthermore, the parameter calculation unit 310 calculates a 50% axial distortion correction value STx3-cr and a 50% circumferential distortion correction value STc3-cr. The 50% axial distortion correction value STx3-cr is the value obtained by subtracting the distortion correction amount DTx from the 50% axial distortion STx3. In other words, the 50% axial distortion correction value STx3-cr = 50% axial distortion STx3 - distortion correction amount DTx. The 50% circumferential distortion correction value STc3-cr is the value obtained by subtracting the circumferential distortion of the entire tank 16 (distortion correction amount DTc) caused by the average outside air temperature TCav from the 50% circumferential distortion STc3. In other words, the 50% circumferential distortion correction value STc3-cr = 50% circumferential distortion STc3 - distortion correction amount DTc.

[0051] Furthermore, the parameter calculation unit 310 calculates a 0% distortion difference amount correction value STxc1-cr. The 0% distortion difference amount correction value STxc1-cr is the absolute value of the difference amount between the 0% axial distortion correction value STx1-cr and the 0% circumferential distortion correction value STc1-cr. That is, the 0% distortion difference amount correction value STxc1-cr = |0% axial distortion correction value STx1-cr - 0% circumferential distortion correction value STc1-cr|.

[0052] Furthermore, the parameter calculation unit 310 calculates a 50% strain difference correction value STxc3-cr. The 50% strain difference correction value STxc3-cr is the absolute value of the difference between the 50% circumferential strain correction value STc3-cr and a value obtained by subtracting the axial strain (strain correction amount DTx) of the entire tank 16 caused by the average outside air temperature TCav from the 50% axial strain STx3. In other words, the 50% strain difference correction value STxc3-cr = |(50% axial strain STx3 - strain correction amount DTx) - 50% circumferential strain correction value STc3-cr|.

[0053] In the following description, the average outside air temperature TCav, 0% corrected temperature TC1-cr, 25% corrected temperature TC2-cr, 50% corrected temperature TC3-cr, 75% corrected temperature TC4-cr, 0% axial distortion correction value STx1-cr, 0% circumferential distortion correction value STc1-cr, 50% axial distortion correction value STx3-cr, 50% circumferential distortion correction value STc3-cr, 0% distortion difference amount correction value STxc1-cr, and 50% distortion difference amount correction value STxc3-cr calculated by the parameter calculation unit 310 may be referred to as the "calculated values."

[0054] Hereinafter, the information relating to each of the detected values ​​and the information relating to the calculated values ​​will be collectively referred to as "detected value-related information A." The detected value-related information A is recorded in storage 31D. At this time, each of the detected values ​​is recorded in storage 31D in association with the ID information and information relating to the detection time of each detected value, and the calculated values ​​are recorded in storage 31D in association with the ID information and information relating to the calculation time of each calculated value.

[0055] As shown in Figure 6, the learning unit 311 has the function of generating a learned model 38 in which the detection value related information A and the actual remaining amount information B are associated by performing machine learning while using the detection value related information A and the actual remaining amount information B contained in the learning data 37 stored in the storage 31D as training data.

[0056] The trained model 38 of the first embodiment is generated using a random forest. That is, the trained model 38 is generated by ensemble learning (e.g., bagging) using multiple decision trees (see FIG. 7 ). Estimation information A is input to these decision trees as an explanatory variable, and these decision trees output actual remaining amount information B as a response variable. That is, the response variable is information indicating whether the actual remaining amount of high-pressure gas is 0% or 100%.

[0057] The fluid amount determination unit 312 determines the "estimated remaining amount" using the generated trained model 38 and the detection value-related information A, which is different from the training data. That is, the fluid amount determination unit 312 applies the detection value-related information A to the trained model 38 to determine the estimated remaining amount at the time when the applied detection value-related information A was detected (calculated). This estimated remaining amount is information indicating whether the percentage of the remaining amount of high-pressure gas in the tank 16, estimated by the fluid amount determination unit 312, is 0% or 100%. That is, the trained model 38 in the first embodiment is a binary classification model.

[0058] Because a random forest is used to generate the trained model 38, the fluid volume determination unit 312 can recognize the importance of each parameter included in the detection value-related information A. That is, while generating the trained model 38 using a random forest, data representing the correlation (parameter importance) between each parameter and the actual remaining amount information B shown in FIG. 8 is also acquired. The hatched area on the right side of each graph in FIG. 8 represents the correlation between each parameter and a remaining amount of high-pressure gas of 0%, while the hatched area on the left side of each graph represents the correlation between each parameter and a remaining amount of high-pressure gas of 100%. The longer the graph, the stronger the correlation with the parameter. For example, the parameter 0% axial strain STx1 increases the probability that the remaining amount of high-pressure gas is predicted to be 100% by just under 0.06. As is clear from Figure 8, among the parameters, 0% axial strain STx1, 75% correction temperature TC4-cr, and 0% strain difference correction value STxc1-cr are particularly closely related to the remaining high-pressure gas amount being 0% and 100%.

[0059] The detected values ​​and the calculated values ​​obtained from the thermocouples 21 , 22 , 23 , 24 , the ambient temperature sensors 25 A, 25 B, and the strain sensors 26 , 27 are estimated to have a correlation with the remaining amount of high-pressure gas in the tank 16 .

[0060] That is, the tank 16 is deformed by the pressure exerted by the high-pressure gas on the tank 16. Therefore, the detected values ​​and calculated values ​​of the strain sensors 26, 27 are considered to have a correlation with the remaining amount of high-pressure gas in the tank 16.

[0061] Furthermore, thermal strain occurs in the tank 16, which does not have a direct correlation with the remaining amount of high-pressure gas in the tank 16. Therefore, it is necessary to eliminate the influence of this thermal strain when estimating the remaining amount of high-pressure gas in the tank 16 based on the amount of strain in the tank 16. Therefore, the detected values ​​and calculated values ​​of the thermocouples 21, 22, 23, and 24 are considered to have an indirect correlation with the remaining amount of high-pressure gas in the tank 16.

[0062] Furthermore, the detected values ​​of the outside air temperature sensors 25A and 25B also affect the thermal strain. That is, it is presumed that the detected values ​​of the outside air temperature sensors 25A and 25B also have some correlation with the remaining amount of high-pressure gas in the tank 16.

[0063] The display control unit 313 controls the display device 40 to display the estimated remaining amount acquired by the fluid amount determination unit 312 on the display device 40. For example, if the fluid amount determination unit 312 estimates that "the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0%," the display control unit 313 causes the display device 40 to display text representing this estimation result. On the other hand, if the fluid amount determination unit 312 estimates that "the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 100%," the display control unit 313 causes the display device 40 to display text representing this estimation result.

[0064] Next, the operation of the system 10 will be described. First, the operation of the CPU 28A of the control device 28 will be described with reference to the flowchart of Figure 9. The CPU 28A repeatedly executes the process of the flowchart of Figure 9 every time a predetermined time elapses.

[0065] In step S10 (hereinafter, the word "step" will be omitted), the CPU 28A determines whether or not a detection value has been acquired.

[0066] If the determination in S10 is Yes, the CPU 28A proceeds to S11 and transmits the detection value to the server 30 wirelessly.

[0067] When the process of S11 is completed or when the determination in S10 is No, the CPU 28A temporarily ends the process of the flowchart of FIG.

[0068] Next, the operation of the CPU 31A of the server 30 will be described with reference to the flowchart of Fig. 10. The CPU 31A repeatedly executes the process of the flowchart of Fig. 10 every time a predetermined time elapses.

[0069] In S20, the CPU 31A determines whether or not a detection value has been received from the control device 28.

[0070] If the determination in S20 is Yes, the CPU 31A proceeds to S21, where it obtains a calculated value using the received detected value.

[0071] After completing the process of S21, the CPU 31A proceeds to S22, where it applies the detected value related information A including the detected value and the calculated value to the trained model 38 to obtain information regarding the estimated remaining amount.

[0072] After completing the process of S22, the CPU 31A proceeds to S23 and causes the display device 40 to display information regarding the estimated remaining amount.

[0073] When the process of S23 is completed or when the determination in S20 is No, the CPU 31A temporarily ends the process of the flowchart of FIG.

[0074] As described above, the system 10 of the first embodiment estimates whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0% or 100% by using the detection value-related information A, which includes information related to the detection value received by the server 30 from the control device 28. Therefore, by using the system 10, a person at a filling company's facility located away from the user's facility can recognize in real time whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0% or 100%, without using a large weight measuring device or installing a sensor in the tank 16.

[0075] Furthermore, the system 10 uses machine learning to determine the estimated remaining amount. FIG. 11 shows a confusion matrix obtained when the estimated remaining amount is determined by applying the detection value-related information A to the trained model 38 of the first embodiment. In FIG. 11, "0" indicates that the estimated remaining amount is 0%, and "1" indicates that the estimated remaining amount is 100%. As is clear from FIG. 11, by using the trained model 38, it is possible to recognize in real time with high accuracy whether the percentage of the remaining amount of high-pressure gas in the tank 16 is 0% or 100%. Therefore, the system 10 can determine the estimated remaining amount with higher accuracy than when machine learning is not used.

[0076] 12 shows a confusion matrix obtained when a trained model 38 of a first comparative example is used, which was generated without using the detected values ​​of the thermocouples 21, 22, 23, and 24 and the outside air temperature sensors 25A and 25B or the calculated values ​​based on these detected values ​​as training data. FIG. 13 shows a confusion matrix obtained when a trained model 38 of a second comparative example is used, which was generated without using the detected values ​​of the strain sensors 26 and 27 and the outside air temperature sensors 25A and 25B or the calculated values ​​based on these detected values ​​as training data. Comparing FIG. 11 with FIG. 12 and FIG. 13 confirms that the estimation accuracy of the estimated remaining amount when the trained model 38 of the first embodiment is used is better than the estimation accuracy of the first and second comparative examples.

[0077] Furthermore, as is clear from FIG. 8 , the 0% axial strain STx1, the 75% corrected temperature TC4-cr, the 0% strain difference amount correction value STxc1-cr, the 0% circumferential strain correction value STc1-cr, and the average ambient temperature TCav are important parameters for estimating whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0% or 100%. In particular, the 0% axial strain STx1, the 75% corrected temperature TC4-cr, and the 0% strain difference amount correction value STxc1-cr are extremely important information. In other words, the detection value of the strain sensor 26 is extremely important information. The system 10 uses this information to calculate the estimated remaining amount. Therefore, the system 10 can estimate the estimated remaining amount with high accuracy.

[0078] Providing the strain sensor 26 at the 0% line 16L1, the thermocouple 24 at the 75% line 16L4, and providing the outside air temperature sensors 25A and 25B are closely related to the ability to obtain the extremely important parameters of 0% axial strain STx1, 75% correction temperature TC4-cr, and 0% strain difference correction value STxc1-cr.

[0079] For example, if a binary classification trained model is created using only the 0% axial strain STx1, the 75% correction temperature TC4-cr, and the 0% axial strain correction value STx1-cr, and the estimated remaining amount is calculated using this trained model, the computational load on the CPU 31 can be reduced.

[0080] Furthermore, by using a combination of the 0% axial strain STx1, the 75% correction temperature TC4-cr, and the 0% strain difference correction value STxc1-cr, it is possible to estimate the remaining amount with high accuracy.

[0081] Furthermore, the control device 28 provided in the tank device 15 uses the power of a battery 29 provided in the tank device 15 to wirelessly transmit the detected value to the server 30. Therefore, anyone at the filling company's facility can recognize the estimated remaining amount regardless of the location of the tank device 15. Furthermore, because the control device 28 and the wireless communication I / F 31E communicate in accordance with the Sigfox (registered trademark) standard, the control device 28 can wirelessly communicate with the server 30 (wireless communication I / F 31E) located a long distance away from the control device 28 with little power consumption.

[0082] Next, a second embodiment of the present disclosure will be described with reference to Fig. 14. Note that the same components as those in the first embodiment are denoted by the same reference numerals, and detailed description thereof will be omitted.

[0083] The feature of the second embodiment is that the learning unit 311 performs machine learning using the detection value related information A and actual remaining amount information B contained in the learning data 37 stored in the storage 31D, thereby generating a learned model 38 of a four-value classification model in which the detection value related information A and the actual remaining amount information B are associated with each other.

[0084] The trained model 38 of the second embodiment is also generated using a random forest, i.e., the trained model 38 is generated by ensemble learning using bagging with multiple decision trees.

[0085] The fluid amount determination unit 312 of the second embodiment also calculates an "estimated remaining amount" using the generated trained model 38 and detection value-related information A, which is different from the training data. This estimated remaining amount is information indicating whether the percentage of the remaining amount of high-pressure gas in the tank 16 estimated by the fluid amount determination unit 312 is 0%, 25%, 75%, or 100%. As described above, 0% includes amounts that can be said to be strictly 0% and substantially 0%, and 100% includes amounts that can be said to be strictly 100% and substantially 100%. Furthermore, 25% includes amounts that can be said to be strictly 25% and substantially 25%. Substantially 25% is, for example, 24% or more and 26% or less. Furthermore, 75% includes amounts that can be said to be strictly 75% and substantially 75%. Substantially 75% is, for example, 74% or more and 76% or less.

[0086] In the second embodiment, random forest is also used to generate the trained model 38, allowing the fluid volume determination unit 312 to recognize the importance of each parameter included in the detection value-related information A. That is, while generating the trained model 38 using random forest, data representing the correlation between each parameter and the actual remaining amount information B shown in FIG. 14 is acquired. The hatched area second from the right of each graph in FIG. 14 represents the correlation between each parameter and a remaining amount of high-pressure gas of 0%, while the hatched area on the leftmost side of each graph represents the correlation between each parameter and a remaining amount of high-pressure gas of 100%. The white area on the rightmost side of each graph represents the correlation between each parameter and a remaining amount of high-pressure gas of 25%. The polka-dot area second from the left of each graph represents the correlation between each parameter and a remaining amount of high-pressure gas of 75%. The longer the graph, the stronger the correlation with the parameter. As is clear from Figure 14, among the parameters, 0% axial strain STx1, 75% correction temperature TC4-cr, and 0% strain difference correction value STxc1-cr are particularly closely related to the remaining high-pressure gas amount being 0%, 25%, 75%, and 100%.

[0087] The display control unit 313 causes the display device 40 to display the estimated remaining amount acquired by the fluid amount determination unit 312. For example, if the fluid amount determination unit 312 estimates that "the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 25%," the display control unit 313 causes the display device 40 to display text representing this estimation result. Also, if the fluid amount determination unit 312 estimates that "the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 75%," the display control unit 313 causes the display device 40 to display text representing this estimation result.

[0088] As described above, the system 10 of the second embodiment uses the detection value-related information A, which includes information related to the detection value received by the server 30 from the control device 28, to estimate whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0%, 25%, 75%, or 100%. Therefore, a person at the filling company's facility can recognize in real time whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0%, 25%, 75%, or 100%, without using a large-scale weight measuring device or installing a sensor in the tank 16.

[0089] Therefore, anyone at the filling company's facility who sees the display device 40 displaying "The remaining amount of high-pressure gas in the tank 16 is 25% of the volume V of the tank 16" will realize that the tank 16 will soon need to be refilled with high-pressure gas.

[0090] Furthermore, anyone at the filling company's facility who sees the display device 40 displaying the message "The remaining amount of high-pressure gas in tank 16 is 75% of the volume V of tank 16" can recognize that there is little need to refill tank 16 with high-pressure gas at this time.

[0091] Although the confusion matrix is ​​omitted, by using the trained model 38 of the second embodiment, it is possible to recognize with high accuracy in real time whether the percentage of the remaining amount of high-pressure gas in the tank 16 is 0% or 25%. Therefore, the system 10 can estimate the remaining amount with high accuracy compared to when machine learning is not used. Note that although the confusion matrix is ​​not shown, it was confirmed that it is also possible to estimate with high accuracy whether the percentage of the remaining amount of high-pressure gas in the tank 16 is 75% or 100%.

[0092] Furthermore, as is clear from FIG. 14 , the 0% axial strain STx1, the 75% corrected temperature TC4-cr, the 0% strain difference amount correction value STxc1-cr, the 0% circumferential strain correction value STc1-cr, and the average ambient temperature TCav are important parameters for estimating whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16 is 0%, 25%, 75%, or 100%. In particular, the 0% axial strain STx1, the 75% corrected temperature TC4-cr, and the 0% strain difference amount correction value STxc1-cr are extremely important information. In other words, the detection value of the strain sensor 26 is extremely important information. The system 10 uses this information to calculate the estimated remaining amount. Therefore, the system 10 can estimate the estimated remaining amount with high accuracy.

[0093] For example, if a trained model for a four-value classification is created using only the 0% axial strain STx1, the 75% correction temperature TC4-cr, and the 0% axial strain correction value STx1-cr, and the estimated remaining amount is calculated using this trained model, the computational load on the CPU 31 can be reduced.

[0094] The first and second embodiments described above are examples of the content of the present disclosure, and may be combined with other known technologies, or some of the configuration may be omitted or modified within the scope of the gist of the present disclosure.

[0095] For example, although the systems 10 of the first and second embodiments perform binary and four-value classification, the systems 10 may perform three-value classification or classification with five or more values. For example, the system 10 may perform three-value classification to estimate whether the ratio of the amount of high-pressure gas remaining in the tank 16 to the volume V of the tank 16 is 0%, 50%, or 100%.

[0096] Alternatively, the detection value-related information A may contain only information related to the detection values ​​of the strain sensors 26 and 27. In this case, the learning unit 311 performs machine learning using the detection value-related information A (detection values ​​of the strain sensors 26 and 27) and the actual remaining amount information B included in the learning data 37 stored in the storage 31D as training data, thereby generating a trained model 38 in which the detection value-related information A and the actual remaining amount information B are associated. FIG. 15 shows data representing the association between each parameter and the actual remaining amount information B, acquired simultaneously with the generation of the trained model 38 for binary classification using a random forest. As is clear from FIG. 12, even when this trained model 38 for binary classification is used, it is possible to recognize in real time with relatively high accuracy whether the percentage of high-pressure gas remaining in the tank 16 is 0% or 100%. However, compared to the first embodiment, the estimation accuracy of the remaining amount of high-pressure gas in this modified example is slightly lower.

[0097] Alternatively, the CPU 31A (fluid amount determination unit 312) of the server 30 may obtain the estimated remaining amount based on the detected value-related information A without using machine learning (trained model 38). For example, a map (not shown) defining the relationship between the 0% axial strain STx1, which is the most important parameter for determining whether the ratio of the remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16, and the ratio of the actual remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16, may be stored in the ROM 31B or the storage 31D, and the CPU 31A may obtain the estimated remaining amount based on this map and the 0% axial strain STx1. Alternatively, detected value-related information A other than the 0% axial strain STx1 may be used as an argument for the map. For example, the estimated remaining amount may be obtained by applying the 75% correction temperature TC4-cr and the 0% distortion difference correction value STxc1-cr to a map that uses as arguments the 75% correction temperature TC4-cr, the 0% distortion difference correction value STxc1-cr, and the ratio of the actual remaining amount of high-pressure gas in the tank 16 to the volume V of the tank 16.

[0098] As described above, the 0% axial strain STx1 is the most important parameter. Therefore, whether the CPU 31A uses machine learning or a map, it is preferable that the CPU 31A obtain the estimated remaining amount using the 0% axial strain STx1.

[0099] Furthermore, the learning unit 311 of the second embodiment may generate a regression model (trained model) using training data for generating the trained model 38 of the second embodiment. FIG. 16 shows continuous predicted values ​​(dotted line) obtained by applying the detection value-related information A to this regression model, and continuous actual remaining amounts of high-pressure gas in the tank 16 (solid line). The horizontal axis of the graph in FIG. 16 represents time, and the vertical axis represents the percentage (%) of the remaining amount of high-pressure gas in the tank 16. In this case, the MRSE (Root Mean Squared Error) for the predicted values ​​and the actual remaining amounts was 1.31, the MAE (Mean Absolute Error) was 0.20, and the R2 (R-Square: coefficient of determination) was 0.94. As is clear from the analysis results, by utilizing this regression model, the specific percentage of the remaining amount of high-pressure gas in tank 16 at a specified time can be estimated with high accuracy using detection value-related information A at that specified time.

[0100] The lines set on the outer peripheral surface of the tank 16 may be lines different from the 0% line 16L1, the 25% line 16L2, the 50% line 16L3, and the 75% line 16L4. For example, in addition to the 0% line 16L1, a 30% line, a 60% line, and a 90% line may be set on the outer peripheral surface of the tank 16. In this case, thermocouples are provided at the same vertical positions as the 0% line 16L1, the 30% line, the 60% line, and the 90% line, respectively. In this case, for example, a trained model can be used to perform four-value classification to estimate whether the proportion of the remaining amount of high-pressure gas in the tank 16 relative to the volume V of the tank 16 is 0%, 30%, 60%, or 90%.

[0101] The fluid may be a liquid or may include a liquid and a gas.

[0102] A deep neural network may be applied as the trained model, and a backpropagation algorithm may be used to generate the trained model.

[0103] The communication standard for wireless communication of the system 10 may be a communication standard different from Sigfox (registered trademark).

[0104] In addition, the processing performed by the CPU after reading the software (program) in each of the above embodiments may be performed by various processors other than the CPU. Examples of processors in this case include PLDs (Programmable Logic Devices) whose circuit configuration can be changed after manufacture, such as FPGAs (Field-Programmable Gate Arrays), and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which are processors having a circuit configuration designed specifically to perform specific processing. Furthermore, the processing may be performed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, a combination of a CPU and an FPGA, etc.). Alternatively, the multiple operations performed by specific processors in each of the above embodiments may be partially or completely integrated and executed by a single processor. Furthermore, the hardware structure of these various processors is, more specifically, an electric circuit that combines circuit elements such as semiconductor elements. Furthermore, in the above embodiments, the processing program is pre-stored (installed) in storage, but this is not limiting. The program may be provided in a form stored on a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. Furthermore, the program may be downloaded from an external device via a network.

[0105] The control device 28 may transmit the above-described detected values ​​to a cloud server, and the cloud server may have a parameter calculation unit 310, a learning unit 311, and a fluid amount determination unit 312. Furthermore, the cloud server may transmit information related to the estimated remaining amount determined by the fluid amount determination unit 312 to the server 30 via wireless communication.

[0106] The tank (ISO tank container, UN portable tank) of the present disclosure is preferably used as a container for using and preserving (including storing) refrigerants used in refrigeration devices, etc. This system is particularly useful in the case of large containers such as ISO tank containers.

[0107] A deformation measurement sensor different from the strain sensor may be used to acquire the amount of strain (axial strain, circumferential strain) at a predetermined portion of the tank 16. An example of such a deformation measurement sensor is a camera. The image of the outer circumferential surface of the tank 16 acquired by the camera may be analyzed to acquire the amount of strain at the predetermined portion of the tank 16.

[0108] One of two different servers (devices) (computers, CPUs) may have a learning unit as a functional configuration, and the other may have a fluid amount determination unit (estimation unit) as a functional configuration. That is, the other server may use the learned model and detection value-related information A acquired by the other server to determine the estimated remaining amount.

[0109] The program of the present disclosure can be provided as a program product. The program product includes all manner of products for providing the program. For example, the program product includes a program provided over a network such as the Internet, and a non-transitory computer-readable recording medium such as a CD-ROM or DVD on which the program is stored.

[0110] The disclosure of Japanese Patent Application No. 2023-187200, filed on October 31, 2023, is incorporated herein by reference in its entirety. All documents, patent applications, and technical standards mentioned herein are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.

[0111] 10 Tank fluid volume estimation system (system) 16 Tank 21 22 23 24 Thermocouple (temperature sensor) 26 27 Strain sensor 28E Wireless communication I / F (wireless transmitting device) 29 Battery 30 Server (tank information processing device) 31E Wireless communication I / F (wireless receiving device) 312 Fluid volume determination unit (estimation unit) 38 Trained model STx1-cr 0% axial distortion correction value (distortion correction value) STc1-cr 0% circumferential distortion correction value (distortion correction value) STc3-cr 50% circumferential distortion correction value (distortion correction value) STxc1-cr 0% distortion difference amount correction value (distortion correction value) STxc3-cr 50% distortion difference amount correction value (distortion correction value)

Claims

1. A system for estimating the amount of fluid in a tank, comprising: a deformation measuring sensor that detects the amount of deformation of a tank capable of containing a predetermined upper limit amount of fluid, the deformation measuring sensor being provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of the tank; a wireless transmitting device that is capable of wirelessly transmitting information related to the detection value of the deformation measuring sensor; a wireless receiving device that is capable of receiving information related to the detection value of the deformation measuring sensor wirelessly transmitted by the wireless transmitting device; and an estimation unit that estimates whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount, based on detection value related information including the amount of distortion of the tank based on the detection value of the deformation measuring sensor received by the wireless receiving device.

2. A system for estimating the amount of fluid in a tank as described in claim 1, comprising a temperature sensor provided on the outer peripheral surface of the tank, the wireless transmitting device being capable of wirelessly transmitting information regarding the detection value of the temperature sensor, the wireless receiving device being capable of receiving information regarding the detection value of the temperature sensor wirelessly transmitted by the wireless transmitting device, and the estimation unit estimating the amount of fluid in the tank based on the detection value related information including the temperature of the tank and the amount of distortion based on the detection value of the temperature sensor received by the wireless receiving device.

3. The system for estimating the amount of fluid in a tank as described in claim 2, wherein the detection value related information includes a distortion correction value obtained by subtracting a distortion correction amount, which is the amount of distortion of the tank caused by the outside air temperature around the tank, from the amount of distortion.

4. A system for estimating the amount of fluid in a tank as described in any one of claims 1 to 3, wherein the estimation unit inputs the detection value related information received by the wireless receiving device into a learned model generated based on the detection value related information and the actual amount of fluid in the tank, and estimates the amount of fluid in the tank.

5. A system for estimating the amount of fluid in a tank as set forth in claim 4, wherein the deformation measuring sensor is provided at the same vertical position on the outer peripheral surface of the tank as the lower end position of the inner surface of the tank.

6. A system for estimating the amount of fluid in a tank as described in claim 4, wherein the detection value related information includes 0% axial strain, which is the axial strain of the tank detected by the deformation measuring sensor provided at the same vertical position as the lower end position of the inner surface of the tank.

7. A system for estimating the amount of fluid in a tank as claimed in any one of claims 1 to 3, wherein the wireless transmitting device operates using power from a battery provided in the tank.

8. A system for estimating the amount of fluid in a tank as described in any one of claims 1 to 3, wherein the estimation unit estimates whether the amount of fluid in the tank is zero, the upper limit amount, 25% of the upper limit amount, or 75% of the upper limit amount.

9. A tank information processing device comprising: a wireless receiving device capable of wirelessly receiving information relating to detection values ​​of a deformation measuring sensor that detects the amount of deformation of a tank capable of containing a predetermined upper limit amount of fluid, the deformation measuring sensor being attached to the outer peripheral surface of a cylindrical shape centered on a predetermined axis line of the tank; and an estimation unit that estimates whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value related information including the amount of distortion of the tank based on the detection value of the deformation measuring sensor received by the wireless receiving device.

10. A method for estimating the amount of fluid in a tank, comprising the steps of: wirelessly transmitting information relating to a detection value of a deformation measuring sensor that detects the amount of deformation of a tank capable of containing a predetermined upper limit amount of fluid, the deformation measuring sensor being attached to the outer peripheral surface of a cylindrical shape centered on a predetermined axis line of the tank; receiving information relating to the detection value that has been wirelessly transmitted; and estimating whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information including the amount of distortion of the tank based on the received detection value.

11. A computer-readable storage medium storing a computer program, which, when executed by a processor, performs the following processes: wirelessly receiving information relating to detection values ​​of a deformation measuring sensor provided on the outer peripheral surface of a cylindrical shape centered on a predetermined axis of a tank capable of containing a predetermined upper limit amount of fluid; and estimating whether the amount of fluid in the tank is zero or one of a plurality of amounts including the upper limit amount based on detection value-related information including the amount of distortion of the tank based on the received detection value.

Images