JP7094424B1 - Control devices, control programs, and control methods - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a control device, a control program and a control method capable of continuously supplying gas according to gas demand even when a failure occurs in gas supply. SOLUTION: In a control device 10, at least an analysis unit 12 for analyzing a gas supply status up to a specific time at each point of a gas flow path, meteorological information and construction information which may cause an obstacle related to gas supply in the gas flow path. A generation unit 15 for generating a gas supply plan capable of stably and continuously supplying gas and a control unit 16 for controlling the control equipment according to the generated gas supply plan are provided. [Selection diagram] Fig. 2

Description

The present invention relates to a control device, a control program, and a control method for controlling a gas supply amount.

Patent Document 1 discloses a gas supply method for setting a gas supply amount so as to reduce a gas production cost with respect to a predicted value of a gas demand amount.

Patent Document 2 discloses an energy demand prediction system that predicts gas demand from gas supply and meteorological factors in the same supply date and time zone in the past by using a preset prediction formula. ing.

Japanese Unexamined Patent Publication No. 2004-189998 Japanese Unexamined Patent Publication No. 2007-241360

The prior art disclosed in Patent Document 1 predicts the gas demand in consideration of meteorological factors such as weather, temperature, humidity, day, and season, and predicts the gas demand only from the actual results of the past gas demand. It is an attempt to predict gas demand more accurately than when it is done. However, the prior art disclosed in Patent Document 1 generates a gas supply plan that satisfies the gas demand under a normal state in which no abnormality is found in the gas supply equipment. Therefore, if a failure occurs in the equipment that supplies gas for some reason, there arises a problem that it becomes difficult to generate a gas supply plan that satisfies the gas demand under the failure state.

Further, the energy demand prediction system disclosed in Patent Document 2 is selected from a plurality of prediction formulas prepared in advance by the operator with reference to the past evaluation values regarding the prediction results set for each prediction formula. Predict gas demand using the forecast formula.

However, the past evaluation values regarding the prediction results set for each prediction formula are evaluation values under normal conditions in which no abnormality is found in the gas supply equipment. Therefore, if a failure occurs in the equipment that supplies gas for some reason, the operator cannot select a prediction formula that can stably supply gas even if the failure occurs, and as a result, energy demand. The problem is that the quantity prediction system makes it difficult to generate a gas supply plan that meets the gas demand under the condition of failure.

The present invention has been made in view of the above problems, and is compared with the case where a new gas supply plan is generated by using the current gas demand situation and the gas supply situation predicted from the current gas supply plan. A control device, a control program, and a control method capable of generating a gas supply plan capable of continuously supplying gas according to gas demand even when a gas supply failure occurs. The purpose is to provide.

In order to achieve the above object, the control device according to the first aspect includes a processor, and the processor acquires measurement information at each predetermined point of the gas flow path, and an obstacle related to gas supply in the gas flow path. The weather information and construction information that can be the cause of the occurrence of the gas are acquired, and the gas pressure, which is the latest gas pressure at each point of the gas flow path, is analyzed using the measurement information and the latest gas supply plan. Using the analysis result of the gas pressure and the latest gas supply plan, the gas pressure and the gas flow rate from the current time at each point of the gas flow path to N hours (N is a positive real number) are included. Using a learning model that outputs a predicted value representing the gas supply status, and when the predicted value, the weather information, and the construction information are input, a gas supply plan that can supply gas to the demand facility without any trouble is output. Then, the gas supply plan for the gas flow path to the gas flow path after N hours is generated from the predicted value, the weather information, and the construction information.

The control device according to the second aspect is the control device according to the first aspect, in which the processor generates control information for realizing gas supply according to the gas supply plan and the predicted value, and according to the control information, the said It controls the control equipment that changes the gas supply status in the gas flow path .

In the control device according to the second aspect, the control device according to the third aspect starts control of the control information, designated information for designating the control equipment to be controlled, and the control equipment to be controlled. It includes a control time and a control value representing a target value of control performed on the control equipment to be controlled.

The control device according to the fourth aspect is the control device according to any one of the first to third aspects, in which the weather information includes lightning occurrence information, rainfall amount, and sunshine in the area where the gas flow path exists. At least one of the hours is included.

The control device according to the fifth aspect is the control device according to any one of the first to fourth aspects, in which the excavation work and the construction work are performed within a predetermined range from the gas flow path in the work information. Contains information about at least one of the works.

The control device according to the sixth aspect is the control device according to any one of the first to fifth aspects, and the learning model is a plurality of the past gas supplied to the demand facility without any trouble. It is a learning model machine-learned using teacher data in which the supply plan, the predicted value used for generating the plurality of gas supply plans, and at least one of the weather information and the construction information are associated with each other. ..

The control program according to the seventh aspect acquires measurement information at each predetermined point of the gas flow path from the computer, and acquires meteorological information and construction information that may cause a failure in gas supply in the gas flow path. Using the measurement information and the latest gas supply plan, the gas pressure, which is the latest gas pressure at each point of the gas flow path, is analyzed, and the analysis result of the gas pressure and the latest gas supply plan are analyzed. By using and, a predicted value indicating the gas supply status including the gas pressure and the gas flow rate from the current time at each point of the gas flow path to N hours (N is a positive real number) is output, and the predicted value is output. Using a learning model that outputs a gas supply plan that can supply gas to a demand facility without hindrance by inputting a value, the meteorological information , and the construction information, the predicted value, the meteorological information, and the meteorological information. It is a program for executing a process of generating a gas supply plan for the gas flow path from the construction information to the time after N hours .

The control method according to the eighth aspect includes a step of acquiring measurement information at each predetermined point of the gas flow path by a computer, and weather information and construction information that may cause a failure in gas supply in the gas flow path. The step to analyze the gas pressure, which is the latest gas pressure at each point of the gas flow path, using the measurement information and the latest gas supply plan, and the analysis result of the gas pressure. Predicted value representing gas supply status including gas pressure and gas flow rate from the current time to N hours (N is a positive real number) at each point of the gas flow path using the latest gas supply plan. Using a learning model that outputs a gas supply plan that can supply gas to the demand facility without hindrance by inputting the step of outputting the gas, the predicted value, the weather information , and the construction information. A step of generating a gas supply plan for the gas flow path from the predicted value, the weather information, and the construction information up to N hours later is executed.

According to the first aspect, the seventh aspect, and the eighth aspect, the comparison with the case where a new gas supply plan is generated using the current gas demand situation and the gas supply situation predicted from the current gas supply plan. Therefore, even if a failure occurs in the gas supply, there is an effect that a gas supply plan capable of continuously supplying the gas according to the gas demand can be generated.

According to the second aspect, there is an effect that the control equipment can be correctly controlled as compared with the case where the control equipment that changes the gas supply status is controlled by the operation of the operator.

According to the third aspect, there is an effect that the control timing for the control equipment and the target control value can be controlled for each control equipment.

According to the fourth aspect, there is an effect that the weather information can be used as a determination element for determining whether or not the gas supply is impaired.

According to the fifth aspect, there is an effect that the construction information can be used as a determination element for determining whether or not the gas supply is impaired.

According to the sixth aspect, there is an effect that a gas supply plan can be generated using a learning model in which machine learning has been performed in advance.

It is a figure which shows an example of a gas supply system. It is a figure which shows the functional composition example of a control device. It is a figure which shows an example of a gas supply plan. It is a figure which shows the display screen example of the measurement information. It is a figure which shows the example of the composition of the main part of the electric system in a control device. It is a flowchart which shows an example of the flow of a control process. It is a figure which shows the generation example of the gas supply plan using the gas supply plan learning model. It is a figure which shows the generation example of the control information using a control information learning model.

Hereinafter, the present embodiment will be described with reference to the drawings. The same components and the same processing are given the same reference numerals throughout the drawings, and duplicate description is omitted.

FIG. 1 is a diagram showing an example of a gas supply system 100 that supplies gas to a demand facility 5 that has a contract for gas supply with a gas company that supplies gas.

As shown in FIG. 1, the gas supply system 100 includes an LNG (Liquefied Natural Gas) base 2, a governor station 3A, a district governor 3B, a gas holder 4, a data collection / distribution device 6, a supply command center 8, and gas. It is configured to include gas equipment such as a conduit 9, and supplies gas to a factory 5A and a house 5B, which are examples of the demand facility 5.

The LNG terminal 2, the governor station 3A, the district governor 3B, the gas holder 4, and the demand facility 5 are connected by a gas conduit 9. Further, the LNG terminal 2, the governor station 3A, and the gas holder 4 are connected to the data collection / distribution device 6 by the communication line 7, and the data collection / distribution device 6 and the supply command center 8 are also connected by the communication line 7.

The LNG terminal 2 is mainly constructed on the coast, receives LNG carried by the tanker 1, and stores the LNG in a tank provided inside the LNG terminal 2. Then, the LNG terminal 2 vaporizes the LNG stored in the tank, adjusts the amount of heat, deodorizes, etc. according to the control instruction from the supply command center 8 to be described later received through the communication line 7, and is instructed by the control instruction. A large amount of gas is supplied to the gas conduit 9 at the time specified by the control instruction.

The gas supplied from the LNG terminal 2 to the gas conduit 9 is supplied at a pressure of, for example, 1 MPa or more and less than 7 MPa so that the gas can be efficiently transported over a wide area. In this embodiment, a pressure of 1 MPa or more is referred to as "high pressure".

The high-pressure gas supplied from the LNG terminal 2, that is, the high-pressure gas, is transported to the governor station (GS) 3A. The governor station 3A performs decompression adjustment to reduce the pressure of the high-pressure gas supplied from the LNG terminal 2 to a pressure of 0.1 MPa or more and less than 1 MPa. In the present embodiment, the pressure of 0.1 MPa or more and less than 1 MPa is referred to as "medium pressure".

The gas depressurized to medium pressure, that is, the medium pressure gas is supplied to the demand facility 5 such as the factory 5A using the medium pressure gas through the gas conduit 9. A part of the medium pressure gas is stored in the gas holder (Gas Holder: GH) 4, and even if the gas supply from the LNG base 2 is interrupted due to the failure of the LNG base 2, for example, each of them is stored from the gas holder 4. It is prepared to supply gas according to each gas demand to the demand facility 5 of the above.

In addition, a part of the medium pressure gas is transported to the district governor 3B through the gas conduit 9. The district governor 3B performs decompression adjustment to reduce the pressure of the medium pressure gas to a pressure of less than 0.1 MPa. In this embodiment, the pressure of less than 0.1 MPa is referred to as "low pressure".

The gas depressurized to a low pressure, that is, the low pressure gas is supplied to the demand facility 5 such as the house 5B using the low pressure gas through the gas conduit 9.

The "governor" means a decompression device, and is installed in each of the governor station 3A and the district governor 3B. Hereinafter, the governor station 3A and the district governor 3B may be collectively referred to as "governor 3". Further, the gas conduit 9 for transporting high-pressure gas is "high-pressure gas conduit 9A", the gas conduit 9 for transporting medium-pressure gas is "medium-pressure gas conduit 9B", and the gas conduit 9 for transporting low-pressure gas is "low-pressure gas conduit 9". It may be called "9C". The gas conduit 9 is a general term for a high-pressure gas conduit 9A, a medium-pressure gas conduit 9B, and a low-pressure gas conduit 9C. The gas conduit 9 is an example of a gas flow path in the present embodiment.

In the example of the gas supply system 100 shown in FIG. 1, only one LNG terminal 2, a governor station 3A, a district governor 3B, and a gas holder 4 are shown in order to explain the configuration of the gas supply system 100 in an easy-to-understand manner. Actually, there are a plurality of each facility constituting the gas supply system 100, and they are connected by a gas conduit 9. That is, the gas conduit 9 of the gas supply system 100 forms a supply network for supplying gas from the plurality of LNG terminals 2 and the gas holder 4 to the demand facility 5, respectively.

The supply command center 8 predicts the gas supply system, that is, the gas supply status, which can stably and continuously supply the gas without the gas supply amount being insufficient for the gas demand in the demand facility 5. The facility is equipped with a control device 10 that controls the amount of gas supplied according to the predicted gas supply status. Hereinafter, the gas supply status may be referred to as "NW status".

The control instruction for controlling the gas supply status transmitted from the supply command center 8 through the communication line 7 is transmitted to the control equipment that actually controls the gas supply status in the gas flow path via the data collection / distribution device 6. To. In the example of the gas supply system 100 shown in FIG. 1, the control instruction is transmitted to the control equipment installed in the LNG terminal 2, the governor station 3A, and the gas holder 4 to which the communication line 7 is connected. Although shown, the destination of the control instruction is not limited to this. For example, a pressure regulator and district governor 3B (not shown) installed in the gas conduit 9 are also connected to the supply command center 8 by a communication line 7, and the supply command center 8 is controlled by the pressure regulator and district governor 3B (not shown). Instructions may be sent to control the gas supply status. Control equipment includes, for example, valves and pumps.

Sensors 17 (see FIG. 4) are attached to the LNG terminal 2, the governor 3, the gas holder 4, and the gas conduit 9 corresponding to the gas flow path, and each sensor 17 is a gas flow to which the sensor 17 is attached. Information indicating the gas supply status at each point on the road is measured at predetermined intervals (for example, 60 seconds). The information representing the gas supply status includes, for example, the gas pressure, the gas flow rate, and the open / closed state of the valve that adjusts the gas pressure and the flow rate. Hereinafter, the information representing the gas supply status measured by the sensor 17 will be referred to as “measurement information”.

The measurement information is once collected in the gas equipment to which each sensor 17 is attached, such as the LNG terminal 2 and the gas holder 4, and is transmitted from the gas equipment to the control device 10 installed in the supply command center 8 through the communication line 7. Will be done. If the sensor 17 can be connected to the communication line 7, the measurement information may be directly transmitted from the sensor 17 to the control device 10 without transmitting the measurement information to the gas equipment.

The acquisition interval of the measurement information in each sensor 17 can be set for each sensor 17, and the acquisition interval of the measurement information in each sensor 17 is freely set by, for example, the control device 10.

A wireless line is used for the communication line 7 of the gas supply system 100, and the communication line 7 connecting the gas equipment and the data collection / distribution device 6 and the communication line 7 connecting the data collection / distribution device 6 and the supply command center 8 are used. Are each equipped with a spare line. As a result, even if a failure occurs in the communication line 7 in use and data such as control instructions and measurement information cannot be transmitted / received, data communication can be continued using the backup line. As a matter of course, the communication line 7 may be a wired line.

FIG. 2 is a diagram showing a functional configuration example of the control device 10 installed in the supply command center 8. The control device 10 includes each functional unit of a communication unit 11, an analysis unit 12, a display unit 13, an information storage unit 14, a generation unit 15, and a control unit 16.

The communication unit 11 receives measurement information in the gas flow path from each gas facility constituting the gas supply system 100 through the communication line 7, and also receives measurement information in the gas flow path to the control facility designated by the control unit 16 described later through the communication line 7. Sends a control instruction to control the gas supply status of the gas flow path.

Further, the communication unit 11 connects to the Internet, for example, and receives at least one of the weather information and the construction information.

The meteorological information received by the communication unit 11 is meteorological information that can cause a failure in gas supply in the gas flow path.

For example, if there is lightning, or if there is a possibility of lightning, a lightning strike may cause a power outage. If a power outage occurs in any area where the gas equipment that constitutes the gas supply system 100 is installed, it may not be possible to operate the gas equipment installed in that area. It can be a factor. In addition, even if a power outage does not occur, it is possible that the gas equipment will be physically destroyed by a lightning strike.

Further, for example, when it is raining, any of the gas facilities constituting the gas supply system 100 may be submerged. In particular, gas equipment installed near rivers and at a lower altitude than the surrounding area increases the risk of flooding or submersion of gas equipment due to flooding of rivers. If the gas equipment is flooded or submerged, the gas equipment may not be able to operate, which may cause a failure in gas supply.

In addition, with the spread of renewable energy, some relatively small gas facilities such as the district governor 3B operate by using the electric power generated by the solar panel. Gas equipment that uses the power generated by solar panels is equipped with storage batteries that store surplus power, but if the period of continuous rain or cloudiness and no daytime sunshine continues for a long period of time, the power stored in the storage batteries will be used. There may be situations where the gas equipment is depleted and cannot be operated.

Therefore, the meteorological information received by the communication unit 11 includes at least one of lightning generation information, rainfall amount, and sunshine duration in the area where the gas flow path exists.

Even in areas where gas channels do not exist (referred to as "other areas"), meteorological information about other areas affects the determination of the occurrence of gas supply obstacles in areas where gas channels exist. If given, the communication unit 11 may receive weather information about other areas.

For example, if it rains upstream of a river flowing through an area where a gas flow path exists, the water level of the river rises even if it is not raining in the area where the gas flow path exists, and the risk of flooding the river increases. As a result, there is an increased possibility that the gas equipment will be flooded or submerged, which may cause a failure in gas supply.

The failure related to the gas supply occurs not only due to the abnormal occurrence of the gas equipment but also when the gas demand exceeding the predicted value occurs at the demand facility 5 and the gas demand exceeds the gas supply. Such unexpected changes in gas demand tend to occur when a power outage occurs in the area where the demand facility 5 exists. For example, in a house 5B in which a household fuel cell cogeneration system is installed, gas demand in the area increases because the household fuel cell cogeneration system tries to generate electricity in the event of a power outage. Further, even in a house 5B in which a household fuel cell cogeneration system is not installed, since electricity cannot be used, the number of times of boiling water or cooking with gas increases.

Therefore, the meteorological information that can cause a failure in gas supply includes the meteorological information in the area where the demand facility 5 exists, and in particular, the meteorological information that can determine whether or not a power failure occurs in the area where the demand facility 5 exists. Information is also included. Since the ground fault of the transmission line and the collapse of the tower are one of the causes of the power outage, the information about the wind that causes the ground fault of the transmission line and the collapse of the tower, that is, the wind speed information and the tornado information, and the information about the earthquake are also gas. This is an example of meteorological information that can cause supply disruptions.

On the other hand, the construction information received by the communication unit 11 is construction information that can cause a failure related to gas supply.

For example, when excavation work is being carried out around the gas flow path, the gas conduit 9 may be accidentally destroyed. If the gas equipment constituting the gas supply system 100 is destroyed, the gas cannot be supplied as a matter of course, which may cause a failure in the gas supply.

Here, "around the gas flow path" means a range predetermined from the gas flow path defined as a range in which the gas flow path may be destroyed by excavation work.

In addition, if the gas equipment is installed on the ground, for example, in the district governor 3B, the scaffolding may collapse and the gas equipment may be destroyed even during construction work other than excavation work such as building construction work. Conceivable. Therefore, the construction information received by the communication unit 11 includes information regarding at least one of the excavation work and the construction work performed around the gas flow path.

The communication unit 11 receives measurement information, and at least one of weather information and construction information each time each information is updated. For convenience of explanation, the communication unit 11 according to the present embodiment will be described as receiving measurement information, meteorological information, and construction information, respectively.

The measurement information, the weather information, and the construction information each include time information indicating when the information is. Furthermore, the weather information includes time information indicating when or when the weather condition is notified by the weather information, and the construction information includes the construction work to be notified by the construction information. It also includes time information that indicates whether it will be used.

The measurement information received by the communication unit 11 is notified to the analysis unit 12 and the display unit 13, and the weather information and construction information received by the communication unit 11 are notified to the information storage unit 14.

When the information storage unit 14 receives the weather information and the construction information from the communication unit 11, the information storage unit 14 arranges the weather information and the construction information in the order of update and stores them in the storage device.

The analysis unit 12 includes the pressure analysis unit 12A and the NW status prediction unit 12B, and analyzes the gas supply status up to a predetermined specific time at each point of the gas flow path.

Therefore, the pressure analysis unit 12A uses the measurement information at each point of the gas flow path measured by each sensor 17 and the gas supply plan 19 generated by the generation unit 15, which will be described later, in various places in the gas flow path. Analyze the latest gas pressure at a point, that is, the gas pressure. The pressure analysis unit 12A notifies the NW situation prediction unit 12B of the analysis result of the gas pressure.

The gas supply plan 19 is a plan that stipulates in chronological order how much gas should be supplied from which LNG terminal 2 or gas holder 4 to meet the gas demand of each demand facility 5. That is. Since the amount of gas demand fluctuates depending on the time zone of the day and the change of seasons, such a gas supply plan 19 is necessary. The gas supply plan 19 determines the amount of gas supplied from each LNG terminal 2 and each gas holder 4 at each time.

FIG. 3 is a diagram showing an example of the gas supply plan 19. In FIG. 3, the vertical axis of the gas supply plan 19 represents the gas supply amount, and the horizontal axis represents time. Further, the graphs 19A to 19F in FIG. 3 represent, for example, the time change of the gas supply amount in each LNG terminal 2 when the six LNG terminals 2 included in the gas supply system 100 are represented by the bases A to F, respectively.

When the NW situation prediction unit 12B receives the gas pressure analysis result from the pressure analysis unit 12A, the NW situation prediction unit 12B uses the gas pressure analysis result and the gas supply plan 19 to N hours (N) from the current time at each point of the gas flow path. Is a positive real number) and predicts the gas supply status including the gas pressure and gas flow rate. The current time is a reference time for predicting the gas supply status, for example, the reception time of the measurement information in the communication unit 11, the prediction start time of the gas supply status by the NW status prediction unit 12B, and the like. Can be set according to. The time N hours after the current time is an example of the specific time according to the present embodiment.

The NW status prediction unit 12B notifies the generation unit 15 of the gas supply status up to N hours later as NW prediction data.

The analysis unit 12 that outputs the measurement information and the NW prediction data from the gas supply plan 19 in this way is realized by using a known unsteady flow simulation application capable of tracking analysis of the gas supply status in the gas flow path.

On the other hand, when the display unit 13 receives the measurement information from the communication unit 11, the display unit 13 displays the measurement information on the display device installed in the supply command center 8 in association with the measurement point of each measurement information.

FIG. 4 is a diagram showing an example of a display screen of measurement information by the display unit 13. As shown in FIG. 4, on the measurement information display screen, the name of the district to which the sensor 17 is attached and the value of the measurement information in the district are displayed in association with each other. The display screen of FIG. 4 shows an example in which the gas pressure in each district is displayed as measurement information, but if the measurement information includes other measurement values such as gas flow rate, each measurement value is shown. Is displayed in association with the name of the district.

Further, on the display screen of FIG. 4, the connection of gas flow paths in each district is schematically displayed as a link 18. Therefore, the operator who monitors the gas supply status in the gas supply system 100 at the supply command center 8 can grasp what kind of situation the gas supply status is in which district by checking the display screen.

When the generation unit 15 receives the NW prediction data from the analysis unit 12, the generation unit 15 uses the NW prediction data and the weather information and construction information stored in the storage device in the information storage unit 14 to supply gas until after N hours. Generate plan 19.

The gas supply plan 19 generated by the generation unit 15 is referred to by the analysis unit 12. Therefore, in the control device 10, the analysis unit 12 uses the latest gas supply plan 19 and the latest measurement information to output the NW prediction data predicted until after N hours, whereby the generation unit 15 outputs the forecast data until after N hours. The generation cycle of generating the gas supply plan 19 is continuously performed.

Further, the generation unit 15 has control information indicating how to control the gas flow in the gas flow path in order to realize the gas supply status indicated by the NW prediction data according to the generated gas supply plan 19. To generate. That is, the generation unit 15 generates control information for realizing gas supply according to the gas supply plan 19 and NW prediction data.

The control information represents the designated information for designating the control equipment to be controlled, the control time for starting the control for the control equipment to be controlled, and the target value of the control to be performed for the control equipment to be controlled. Contains control values. The generation unit 15 notifies the control unit 16 of the generated control information.

Upon receiving the control information from the generation unit 15, the control unit 16 generates a control instruction instructing the control equipment designated as the control target to change the gas supply status in the gas flow path according to the control information. Notify the communication unit 11 of the generated control instruction. That is, the control unit 16 controls the control equipment.

As described above, when the communication unit 11 receives the control instruction from the control unit 16, the communication unit 11 transmits the control instruction to the gas equipment including the control equipment to be controlled through the communication line 7. The gas equipment that receives the control instruction controls the control equipment designated as the control target according to the control instruction.

The control device 10 as shown in FIG. 2 is configured by using the computer 20. FIG. 5 is a diagram showing an example of a main part configuration of an electric system in a control device 10 configured by using a computer 20.

The computer 20 is used as a temporary work area of a CPU (Central Processing Unit) 21 that bears each functional unit of the control device 10 shown in FIG. 2, a ROM (Read Only Memory) 22 that stores a control program, and a CPU 21. It includes a RAM (Random Access Memory) 23, a non-volatile memory 24, and an input / output interface (I / O) 25. The CPU 21, ROM 22, RAM 23, non-volatile memory 24, and I / O 25 are each connected via the bus 26.

The non-volatile memory 24 is an example of a storage device in which the stored information is maintained even if the power supplied to the non-volatile memory 24 is cut off. For example, a semiconductor memory is used, but a hard disk may be used. The non-volatile memory 24 does not necessarily have to be built in the computer 20, and may be a storage device attached to and detached from the computer 20 such as a memory card. The non-volatile memory 24 stores, for example, weather information and construction information stored by the information storage unit 14, and a gas supply plan 19 generated by the generation unit 15.

For example, a communication unit 27, an input unit 28, and a display unit 29 are connected to the I / O 25.

The communication unit 27 includes a communication protocol connected to the communication line 7 and the Internet, and performs data communication with an external device connected to the Internet and a gas facility connected to the communication line 7 constituting the gas supply system 100. ..

The input unit 28 is a device that receives an operation from the operator of the control device 10 and notifies the CPU 21. For example, an input device such as a button, a touch panel, a keyboard, a pointing device, and a mouse is used.

The display unit 29 is a device that displays information processed by the CPU 21 so that it can be grasped through the eyes of an operator. Such display devices are used. As an example, the display unit 29 displays the measurement information display screen shown in FIG.

The control device 10 does not necessarily have to include a unit connected to the I / O 25 illustrated in FIG. 5, but may include a necessary unit depending on the situation. Further, the control device 10 connects another unit such as an image forming unit that forms an image on paper to the I / O 25, and displays a measurement information display screen shown in FIG. 4 showing a gas supply status in the gas flow path. The contents of may be formed on paper.

Next, the operation of the control device 10 according to the present embodiment will be described in detail.

FIG. 6 is a flowchart showing an example of a flow of control processing executed by the CPU 21 when the control device 10 starts controlling the gas supply status in the gas supply system 100. The control program that defines the control process is stored in advance in, for example, the ROM 22 of the control device 10. The CPU 21 of the control device 10 reads the control program stored in the ROM 22 and executes the control process.

It is assumed that the gas supply plan 19 and the weather information and construction information received through the Internet are stored in the non-volatile memory 24. If the generation unit 15 of the control device 10 has never generated the gas supply plan 19, the default value of the gas supply plan 19 prepared in advance is stored in the non-volatile memory 24.

In step S10, the CPU 21 acquires the measurement information measured by each sensor attached to the gas flow path through the communication unit 27.

In step S20, the CPU 21 acquires the gas supply plan 19 previously generated from the non-volatile memory 24, that is, the latest gas supply plan 19.

In step S30, the CPU 21 uses the measurement information acquired in step S10 and the gas supply plan 19 acquired in step S20 to generate NW prediction data up to N hours later, and the generated NW prediction data is stored in the RAM 23. Remember. A known unsteady timber draft simulation application is used to generate NW prediction data.

In step S40, the CPU 21 acquires weather information representing the weather condition from the non-volatile memory 24 to N hours later.

In step S50, the CPU 21 acquires construction information indicating the construction status from the non-volatile memory 24 to N hours later.

In step S60, the CPU 21 generates the gas supply plan 19 up to N hours later by using the NW prediction data generated in step S30, the weather information acquired in step S40, and the construction information acquired in step S50.

Specifically, the CPU 21 generates a gas supply plan 19 from NW prediction data, meteorological information, and construction information using a gas supply plan learning model 30 using artificial intelligence.

The gas supply plan learning model 30 includes a plurality of past gas supply plans 19 in which gas is supplied without any trouble, and NW prediction data, weather information, and construction information used for generating each of these gas supply plans 19. When the NW prediction data, the weather information, and the construction information included in the teacher data are input using the teacher data associated with the above, the machine learning is performed so as to output the corresponding gas supply plan 19. That is, the gas supply plan learning model 30 is an example of a learning model according to the present embodiment in which the association of NW prediction data, gas supply plan 19, meteorological information, and construction information when gas supply is performed without any trouble is learned. be.

For example, a neural network is used for machine learning of the gas supply plan learning model 30.

FIG. 7 is a diagram showing an example of generation of a gas supply plan 19 using the gas supply plan learning model 30.

As shown in FIG. 7, the CPU 21 represents the NW prediction data at each time generated in step S30 and the weather condition at each time acquired in step S40 in the gas supply plan learning model 30 while shifting the time until after N hours. The gas supply plan 19 is generated by inputting the weather information and the construction information representing the construction status at each time acquired in step S50.

The machine learning of the gas supply plan learning model 30 does not necessarily have to be executed by the control device 10, and the CPU 21 may use, for example, the gas supply plan learning model 30 in which machine learning is performed by an external device connected to the Internet. ..

Here, as an example, an example of generating the gas supply plan 19 using the gas supply plan learning model 30 has been described, but the method of generating the gas supply plan 19 is not limited to this. For example, the gas supply plan 19 may be generated by using a prediction function using NW prediction data, meteorological information, and construction information as explanatory variables and gas supply plan 19 as an objective variable. Further, the gas supply plan 19 may be generated by performing a cluster analysis on a combination of NW prediction data, meteorological information, and construction information.

For convenience of explanation, both meteorological information and construction information were used to generate the gas supply plan 19, but as already described, at least one of the meteorological information and the construction information may be used to generate the gas supply plan 19. The process of step S60 is an example of a generation step for generating a gas supply plan.

In step S70, the CPU 21 uses the NW prediction data generated in step S30 and the gas supply plan 19 generated in step S60 to generate control information up to after N hours.

Specifically, the CPU 21 generates control information from the NW prediction data and the gas supply plan 19 by using the control information learning model 40 using artificial intelligence.

The control information learning model 40 actually performs according to a plurality of past gas supply plans 19 in which gas supply was performed without hindrance, NW prediction data used for generating each of these gas supply plans 19, and gas supply plan 19. When the NW prediction data and the gas supply plan 19 included in the teacher data are input using the teacher data associated with the control information indicating the controlled content, machine learning is performed so as to output the corresponding control information. It is generated by. That is, the control information learning model 40 has learned the association between the NW prediction data, the gas supply plan 19, and the control information when the gas is supplied without any trouble.

For machine learning of the control information learning model 40, for example, a neural network is used as in the machine learning of the gas supply plan learning model 30.

FIG. 8 is a diagram showing an example of generating control information using the control information learning model 40.

As shown in FIG. 8, the CPU 21 shifts the time until after N hours, and feeds the control information learning model 40 the NW prediction data at each time generated in step S30 and the gas supply plan 19 at each time generated in step S60. By inputting, control information at each time is generated. The control time of the control information at each time is set to the corresponding time so that the control of the control equipment is started at that time.

As a result, NW prediction data and control information for realizing gas supply according to the gas supply plan 19 are generated.

The machine learning of the control information learning model 40 does not necessarily have to be executed by the control device 10, and the CPU 21 may use, for example, the control information learning model 40 in which machine learning is performed by an external device connected to the Internet.

Here, as an example, an example of generating control information using the control information learning model 40 has been described, but the method of generating control information is not limited to this. For example, control information may be generated using a prediction function using NW prediction data and gas supply plan 19 as explanatory variables and control information as an objective variable. Further, control information may be generated by performing cluster analysis on the combination of NW prediction data and gas supply plan 19.

In step S80, the CPU 21 controls the communication unit 27, transmits a control instruction to the control equipment designated by the designated information included in the control information generated in step S70, and ends the control process shown in FIG. ..

As described above, the control equipment to be controlled performs control for setting the physical quantity (for example, gas pressure) representing the gas supply status to the control value specified in the control information during the control time included in the control information.

The gas supply plan 19 generated by the control device 10 is a gas supply plan 19 generated by using at least one of the meteorological information and the construction information, in consideration of whether or not a failure will occur in the gas supply in the future. Therefore, even if a failure actually occurs in the gas supply, the control information generated according to the gas supply plan 19 controls the gas flow path in consideration of the occurrence of the failure in advance, so that the gas flow path can be controlled according to the gas demand. Gas will continue to be supplied.
Further, in the control device 10, since the operator's operation is not required for the control of the gas flow path, the gas flow path is not controlled due to the operator's erroneous operation or judgment error. In particular, when a failure occurs, it becomes difficult for the operator to make a calm judgment quickly as compared with the normal state, so that an erroneous operation is likely to occur. Can be carried out without.

Although one aspect of the control device 10 has been described above using the embodiment, the disclosed mode of the control device 10 is an example, and the mode of the control device 10 is not limited to the range described in the embodiment. Various changes or improvements may be made to the embodiments without departing from the gist of the present disclosure, and the modified or improved forms are also included in the technical scope of the disclosure. For example, the order of the control processes shown in FIG. 6 may be changed without departing from the gist of the present disclosure.

Further, in the present disclosure, as an example, a mode in which control processing is realized by software has been described. However, the same processing as the flowchart shown in FIG. 6 is implemented in, for example, ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or PLD (Programmable Logic Device). May be good. In this case, the processing speed can be increased as compared with the case where the control processing is realized by software.

In this way, the CPU 21 of the control device 10 may be replaced with a dedicated processor specialized for a specific process such as an ASIC, FPGA, PLD, GPU (Graphics Processing Unit), and FPU (Floating Point Unit).

Further, the control process of the control device 10 is executed by a combination of two or more processors of the same type or different types, such as a plurality of CPU 21, or a combination of the CPU 21 and the FPGA, in addition to the form realized by one CPU 21. You may. Further, the control process of the control device 10 may be realized by cooperation with a processor located outside the housing of the control device 10 and located at a physically distant place.

In the embodiment, an example in which the control program is stored in the ROM 22 of the control device 10 has been described, but the storage destination of the control program is not limited to the ROM 22. The control program of the present disclosure can also be provided in the form recorded on a storage medium readable by the computer 20. For example, the control program may be provided in the form of being recorded on an optical disk such as a CD-ROM (Compact Disk Read Only Memory) and a DVD-ROM (Digital Versaille Disc Read Only Memory). Further, the operation training program may be provided in the form of being recorded in a portable semiconductor memory such as a USB (Universal Serial Bus) memory and a memory card. The ROM 22, the non-volatile memory 24, the CD-ROM, the DVD-ROM, the USB, and the memory card are examples of non-transitory storage media.

Further, the control device 10 may download a control program from an external device through the communication unit 27 and store the downloaded control program in, for example, the non-volatile memory 24. In this case, the CPU 21 of the control device 10 reads the control program downloaded from the external device and executes the control process.

1 tanker, 2 LNG base, 3 governor, 3A governor station, 3B district governor, 4 gas holder, 5 demand facility, 5A factory, 5B housing, 6 data collection and distribution equipment, 7 communication lines, 8 supply command center, 9 gas conduit , 9A high pressure gas conduit, 9B medium pressure gas conduit, 9C low pressure gas conduit, 10 control device, 11 communication unit, 12 analysis unit, 12A pressure analysis unit, 12B NW status prediction unit, 13 display unit, 14 information storage unit, 15 Generator, 16 controls, 17 sensors, 18 links, 19 gas supply plans, 19A (gas supply plan) graphs, 20 computers, 21 CPUs, 22 ROMs, 23 RAMs, 24 non-volatile memories, 25 I / O, 26 Bus, 27 communication unit, 28 input unit, 29 display unit, 30 gas supply plan learning model, 40 control information learning model, 100 gas supply system

Claims (8)

Equipped with a processor
The processor
Acquire measurement information at each predetermined point of the gas flow path,
Acquire weather information and construction information that can cause obstacles to gas supply in the gas flow path.
Using the measurement information and the latest gas supply plan, the gas pressure, which is the latest gas pressure at each of the points in the gas flow path, is analyzed.
Using the analysis result of the gas pressure and the latest gas supply plan, the gas pressure and the gas flow rate from the current time at each point of the gas flow path to N hours (N is a positive real number) are included. Outputs the predicted value that shows the gas supply status,
Using a learning model that outputs a gas supply plan that can supply gas to a demand facility without hindrance by inputting the predicted value, the meteorological information, and the construction information, the predicted value, the meteorological information, and the construction information are used. A control device that generates a gas supply plan for the gas flow path from the construction information up to the N hours later . The processor generates control information that realizes gas supply according to the gas supply plan and the predicted value.
The control device according to claim 1, wherein the control equipment that changes the gas supply status in the gas flow path is controlled according to the control information. The control information includes designated information for designating the control equipment to be controlled, a control time for starting control for the control equipment to be controlled, and a control target for the control equipment to be controlled. The control device according to claim 2, wherein a control value representing a value is included. The control device according to any one of claims 1 to 3, wherein the meteorological information includes at least one of lightning generation information, rainfall amount, and sunshine duration in an area where the gas flow path exists. The control device according to any one of claims 1 to 4, wherein the construction information includes information on at least one of excavation work and construction work performed within a predetermined range from the gas flow path. .. The learning model includes a plurality of past gas supply plans in which gas was supplied without hindrance to the demand facility, the predicted values used to generate the plurality of gas supply plans, and the meteorological information and construction work. The control device according to any one of claims 1 to 5, which is a learning model machine-learned using teacher data associated with at least one of information. On the computer
Acquire measurement information at each predetermined point of the gas flow path,
Acquire weather information and construction information that can cause obstacles to gas supply in the gas flow path.
Using the measurement information and the latest gas supply plan, the gas pressure, which is the latest gas pressure at each of the points in the gas flow path, is analyzed.
Using the analysis result of the gas pressure and the latest gas supply plan, the gas pressure and the gas flow rate from the current time at each point of the gas flow path to N hours (N is a positive real number) are included. Outputs the predicted value that shows the gas supply status,
By inputting the predicted value, the meteorological information , and the construction information, the predicted value and the meteorological information are used by using a learning model that outputs a gas supply plan capable of supplying gas to the demand facility without any trouble. , And a control program for executing a process of generating a gas supply plan for the gas flow path from the construction information up to after N hours . By computer
Steps to acquire measurement information at each predetermined point in the gas flow path,
Steps to acquire weather information and construction information that can cause obstacles to gas supply in the gas flow path, and
Using the measurement information and the latest gas supply plan, a step of analyzing the gas pressure, which is the latest gas pressure at each of the points in the gas flow path, and
Using the analysis result of the gas pressure and the latest gas supply plan, the gas pressure and the gas flow rate from the current time at each point of the gas flow path to N hours (N is a positive real number) are included. A step to output a predicted value indicating the gas supply status, and
By inputting the predicted value, the meteorological information , and the construction information, the predicted value and the meteorological information are used by using a learning model that outputs a gas supply plan capable of supplying gas to the demand facility without any trouble. , And the step of generating a gas supply plan for the gas flow path from the construction information up to after N hours .
Control method to execute.

Images