Gas amount estimation device, gas processing device, transport container, gas amount estimation method, and program

Abstract

The purpose of this disclosure is to optimize the amount of CA gas injected into transport vehicles such as trucks in order to maintain the freshness of fresh produce at a certain level or above during transportation. To this end, this disclosure provides a gas quantity estimation device (5) equipped with a control unit (501), wherein the control unit (501) takes information related to the type and quantity of fresh produce stored in the CA cold storage (101) as input data, estimates the supply or processing volume of CA gas to the CA cold storage (101) at a predetermined time, and outputs this as output data. Accordingly, the freshness of fresh produce during transportation can be maintained at a certain level or above.

Description

Technical Field

[0001] This disclosure relates to a gas quantity estimation device, a gas processing device, a transport container, and a gas quantity estimation method and procedure. Background Technology

[0002] In recent years, transporting local specialties to cities and other destinations has boosted local economies. When the specialty is fresh produce (perishable goods), air transport can be used to maintain a certain level of freshness; however, due to high costs, shipping and trucking are the primary modes of transport. Furthermore, if the fresh produce is produced on remote islands without airports, it may take more than 10 days to reach its destination.

[0003] On the other hand, in order to maintain the freshness of fresh produce at a certain level or above, a technology for using refrigeration and CA gas to maintain the freshness of fresh produce at a certain level or above has been disclosed (see Patent Document 1). Therefore, if trucks or the like equipped with CA gas cold storage compartments are used to transport fresh produce, the freshness of the fresh produce can be maintained at a certain level or above even with long transportation times, and transportation costs can also be reduced.

[0004] [Cited Documents]

[0005] [Patent Documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 54-72099 Summary of the Invention

[0007] [Technical problem to be solved]

[0008] However, when injecting CA gas into trucks, it is unclear how much CA gas supply or removal is required during transportation. Therefore, if insufficient CA gas is injected, it becomes impossible to maintain the freshness of perishable goods at a certain level. Furthermore, while more CA gas can be injected, this results in an increase in the size of the gas handling equipment, such as CA cylinders, and a reduction in the amount of perishable goods that can be transported.

[0009] In view of the above problems, the purpose of this disclosure is to optimize the injection amount of CA gas.

[0010] [Technical Solution]

[0011] The first aspect of this disclosure is a gas quantity estimation device with a control unit, wherein the control unit takes information related to the type and quantity of fresh produce stored in the CA cold storage as input data, estimates the supply or processing volume of CA gas for the CA cold storage at a predetermined time, and outputs the supply or processing volume of CA gas as output data.

[0012] According to the first method, the injection amount of CA gas can be optimized.

[0013] The second aspect of this disclosure is a gas quantity estimation device as described in the first aspect, wherein the supply or processing quantity of the CA gas is calculated using the result obtained by learning the relationship between the input data and the actual supply or processing quantity of CA gas through machine learning, wherein the input data is information related to the type and quantity of fresh produce stored in the CA cold storage.

[0014] According to the second method, the injection amount of CA gas can be optimized by using the results obtained through machine learning.

[0015] The third aspect of this disclosure is a gas quantity estimation device as described in the first aspect, wherein the control unit uses information related to the type and quantity of fresh produce stored in the CA cold storage, i.e., the relationship between the input data and the actual supply or processing volume of CA gas, as table data, and uses the table data to calculate the supply or processing volume of CA gas.

[0016] According to the third method, the injection amount of CA gas can be optimized by using table data.

[0017] The fourth aspect of this disclosure is a gas quantity estimation device as described in any of the first to third aspects, wherein the input data includes the temperature or humidity inside the CA cold storage during the transportation of the fresh produce, and the control unit further estimates the supply or processing volume of the CA gas based on the temperature or humidity.

[0018] According to the fourth method, by including the temperature or humidity inside the CA cold storage during the transportation process of fresh produce in the input data, the injection volume of CA gas can be optimized with higher precision.

[0019] The fifth aspect of this disclosure is a gas quantity estimation device as described in any of the first to third aspects, wherein the control unit further estimates the supply or processing volume of the CA gas based on the transportation time of the fresh produce.

[0020] According to method 5, by taking into account the transportation time of fresh produce, the injection amount of CA gas can be optimized with higher precision even when the transportation time is long.

[0021] The sixth aspect of this disclosure is a gas quantity estimation device as described in any of the first to fifth aspects, wherein the output data includes the supply amount of CA gas supplied to the CA cold storage to maintain the CA gas in the CA cold storage at a predetermined concentration during the transportation of the fresh produce and / or the removal amount of CA gas removed from the CA cold storage to maintain the CA gas in the CA cold storage at the predetermined concentration. If the output data includes the supply amount of CA gas, the control unit estimates the supply amount of CA gas; or, if the output data includes the removal amount of CA gas, the control unit estimates the removal amount in the amount of CA gas processed.

[0022] According to method 6, by estimating the supply or removal of CA gas, the injection amount of CA gas can be optimized with higher precision.

[0023] The seventh aspect of this disclosure is a gas quantity estimation device as described in any of the first to fifth aspects, wherein the control unit calculates the number of gas quantity control devices based on the supply or processing volume of the CA gas in each of the plurality of CA cold storages, and the gas quantity control devices control the gas quantity of the CA gas in each of the plurality of CA cold storages based on the type and quantity of the fresh produce.

[0024] According to the seventh method, even when multiple CA cold storage units are used for transportation, it is possible to calculate the number of gas quantity control devices used to control the amount of CA gas in each of the multiple CA cold storage units.

[0025] The eighth aspect of this disclosure is a gas quantity estimation device as described in any of the first to seventh aspects, wherein the output data is data related to oxygen, carbon dioxide, nitrogen, or ethylene.

[0026] According to Method 8, it is possible to respond even when the output data is oxygen, carbon dioxide, nitrogen, or ethylene.

[0027] The ninth aspect of this disclosure is a gas processing apparatus for processing CA gas in the CA cold storage, wherein a predetermined amount of CA gas is injected based on the supply or processing amount of the CA gas estimated by a gas quantity estimation device as described in any of the first to fifth aspects.

[0028] According to the 9th method, a gas handling device such as a CA gas cylinder is used to optimize the amount of CA gas to be injected.

[0029] The tenth aspect of this disclosure is a transport container equipped with a gas handling device as described in the ninth aspect.

[0030] According to the 10th method, a transport container with a gas handling device such as a CA gas cylinder having an optimized injection volume of CA gas can be prepared.

[0031] The 11th aspect of this disclosure is a transport container as described in the 10th aspect, further comprising a gas quantity control device for controlling the amount of CA gas in the CA cold storage according to the type and quantity of the fresh produce.

[0032] According to method 11, a gas handling device such as a CA gas cylinder is used to prepare a CA gas injection volume that is optimized according to the type and quantity of fresh produce.

[0033] The 12th aspect of this disclosure is a gas quantity estimation method, in which a computer performs the following processing: taking information related to the type and quantity of fresh produce stored in the CA cold storage as input data, estimating the supply or processing volume of CA gas for the CA cold storage at a predetermined time, and taking the supply or processing volume of CA gas as output data.

[0034] According to method 12, the injection amount of CA gas can be optimized.

[0035] The 13th aspect of this disclosure is a gas quantity estimation method as described in the 12th aspect, wherein the computer uses the result of learning the relationship between the input data and the actual supply or processing volume of CA gas through machine learning to calculate the supply or processing volume of CA gas, wherein the input data is information related to the type and quantity of fresh produce stored in the CA cold storage.

[0036] According to method 13, the injection amount of CA gas can be optimized by using the results obtained through machine learning.

[0037] The 14th aspect of this disclosure is a gas quantity estimation method as described in the 12th aspect, wherein the computer uses information related to the types and quantities of fresh produce stored in the CA cold storage, i.e., the relationship between the input data and the actual supply or processing volume of CA gas, as tabular data, and uses the tabular data to calculate the supply or processing volume of CA gas.

[0038] According to method 14, the injection amount of CA gas can be optimized by using table data.

[0039] The 15th aspect of this disclosure is a program for causing a computer to perform the method described in any of the 12th to 14th aspects.

[0040] According to method 15, the injection amount of CA gas can be optimized. Attached Figure Description

[0041] [ Figure 1 [A schematic diagram of a transportation company that has set up the gas quantity estimation device according to an embodiment of the present invention.]

[0042] [ Figure 2 [A schematic diagram of the truck in this embodiment.]

[0043] [ Figure 3 [Hardware configuration diagram of the CA refrigeration equipment in this embodiment.]

[0044] [ Figure 4 Hardware configuration diagram of the gas quantity estimation device in this embodiment.

[0045] [ Figure 5 Functional block diagram of the gas quantity estimation device during the learning phase.

[0046] [ Figure 6 Functional block diagram of the gas quantity estimation device in the estimation stage.

[0047] [ Figure 7 [] This represents a flowchart of the learning phase.

[0048] [ Figure 8 The image represents a flowchart of the estimation phase.

[0049] [ Figure 9 A schematic diagram of standard processing working in CA mode.

[0050] [ Figure 10 [A schematic diagram of a modified example of the truck according to this embodiment.] Detailed Implementation

[0051] The following is combined Figures 1 to 9 The embodiments of the present invention will be described.

[0052] [Summary of Implementation Methods]

[0053] Generally, by adjusting the composition of the air (oxygen concentration, carbon dioxide concentration, nitrogen concentration, ethylene concentration, etc.) within a cold storage room, the respiration of fresh produce such as fruits and vegetables can be inhibited, thus preventing the consumption of sugars and acids contained in the produce and significantly extending its freshness. This is called Controlled Atmosphere (CA) storage, one method of storing fresh produce. There are two types of CA: one utilizes the respiration of the fresh produce to adjust the composition of the air within the cold storage room. (Note: This is equivalent to adjusting the composition of the air inside a cold storage facility by supplying nitrogen or other gases. In this embodiment, especially for The implementation details will be explained. It should be noted that, in the following text, at least one of the gases supplied and removed to adjust the composition of the air in the cold storage will be collectively referred to as "gas" and denoted as...

[0054] Figure 1 This is a schematic diagram of a transportation company equipped with a gas quantity estimation device according to an embodiment of the present invention. Figure 1 In the middle, truck 1, used for transportation, was parked at transportation company A before departure. Truck 1 was equipped with a transport container 2 (hereinafter referred to as the transport container) for storing goods (here, fresh produce). In addition, transportation company A is equipped with a gas injection device 4 for storing CA gas to be injected into the CA gas cylinder 104a (described later) located inside container 2. Transportation company A is also equipped with a gas quantity estimation device 5. The gas quantity estimation device 5 is an example of a computer that estimates the supply and removal amounts of CA gas required to maintain the freshness of perishable goods based on the transportation time of truck 1. It should be noted that the gas quantity estimation device 5 can also estimate the supply or removal amount of CA gas.

[0055] Figure 2 This is a schematic diagram of the truck in this embodiment. Figure 2 The truck 1a shown is Figure 1 An example of truck 1a. The container 2a mounted on truck 1a contains multiple CA refrigerated compartments 101, CA refrigeration units 102, and valves 103. It should be noted that... Figure 2 For ease of explanation, only one group (CA cold storage, CA cold storage unit, and valve) is labeled. Additionally, container 2a also contains CA gas cylinder 104a and CA gas piping 105a.

[0056] CA cold storage 101 is a highly airtight and insulated cold storage facility that maintains the freshness of fresh produce at a certain level or above through refrigeration and CA gas. Different types of fresh produce can be stored in each CA cold storage 101. For example, avocados, being fresh produce, have a high respiration rate; therefore, to maintain freshness, CO2 needs to be removed from the CA cold storage 101, and nitrogen gas is supplied to replace the removed CO2. Conversely, for fruits with lower respiration rates, this treatment is not necessary. As described above, since the environment and conditions within the CA cold storage 101 for storing fresh produce vary depending on the type of fresh produce, different types of fresh produce can be stored separately in their respective CA cold storage 101s.

[0057] The CA refrigeration unit 102 is an example of a gas quantity control device that controls the temperature and humidity inside the CA cold storage 101 and controls the CA gas. The valve 103 can adjust the gas quantity of the CA gas supplied from the CA gas cylinder 104a via the CA gas pipe 105a under the drive control of the CA refrigeration unit 102.

[0058] The CA gas cylinder 104a stores a predetermined quantity of CA gas injected from the gas injection device 4 according to the supply quantity and removal quantity of the CA gas estimated by the gas quantity estimation device 5. It should be noted that the CA gas cylinder 104a may also store a predetermined quantity of CA gas injected from the gas injection device 4 according to the supply quantity or removal quantity of the CA gas estimated by the gas quantity estimation device 5. The CA gas cylinder 104a is an example of a gas processing device. The gas processing device includes a CA gas generation device for generating CA gas. The CA gas generation device can separate the air components in the atmosphere to supply CA gas. The CA gas pipe 105a is used to supply the CA gas from the CA gas cylinder 104a to the CA refrigeration unit 1OB. Figure 1 The CA gas cylinder 104a is a gas cylinder that stores a predetermined amount of CA gas injected from the gas injection device 4 according to the supply amount and removal amount of the CA gas estimated by the gas amount estimation device 5. It should be noted that the CA gas cylinder 104a may also store a predetermined amount of CA gas injected from the gas injection device 4 according to the supply amount or removal amount of the CA gas estimated by the gas amount estimation device 5. The CA gas cylinder 104a is an example of a gas processing device. The gas processing device includes a CA gas generation device for generating CA gas. The CA gas generation device can separate the air components in the atmosphere to supply CA gas. The CA gas pipe 105a is used to supply the CA gas from the CA gas cylinder 104a to the CA refrigeration unit 102.

[0059] 〔Hardware configuration〕

[0060] <Hardware configuration of the CA refrigeration equipment>

[0061] Figure 3 is the hardware configuration diagram of the CA refrigeration equipment of this embodiment. The CA refrigeration equipment 300 is provided in Figure 2 each CA refrigeration unit 102. It should be noted that the CA refrigeration equipment 300 may also be provided in the container 2a and perform processing for each CA refrigeration unit 102.

[0062] A sensor group 310 for detecting the environment and conditions of the CA cold storage 101 in the same group is provided in the CA refrigeration equipment 300. As Figure 3 shown, the sensor group 310 includes, for example, an intake temperature sensor 311, a humidity sensor 312, an exhaust temperature sensor 313, an O2 (oxygen) concentration sensor, a CO2 (carbon dioxide) concentration sensor, and a gas consumption sensor 316.

[0063] The sensor group 310 includes: an inhalation temperature sensor 311 for detecting the temperature of the gas inhaled into the CA cold storage 101; a humidity sensor 312 for detecting the humidity inside the CA cold storage 101; an exhaust temperature sensor 313 for detecting the temperature of the gas exhausted from the CA cold storage 101; an O2 concentration sensor for detecting the O2 concentration inside the CA cold storage 101; a CO2 concentration sensor for detecting the CO2 concentration inside the CA cold storage 101; and a gas consumption sensor 316 for detecting the amount of CA gas consumed inside the CA cold storage 101. It should be noted that the sensor group 310 may also include a nitrogen concentration sensor for detecting the nitrogen concentration inside the CA cold storage 101 or an ethylene concentration sensor for detecting the ethylene concentration inside the CA cold storage 101.

[0064] In addition, the CA refrigeration equipment 300 is also equipped with a set value input device 321, a CA cold storage control device 322, and a display device 323.

[0065] The setpoint input device 321 is used for users (truck drivers, etc.) to input various setpoints for the environment and conditions within the CA cold storage 101. For example, such as... Figure 3 As shown, the settings include set temperature, set O2 concentration, set CO2 concentration, and set type and quantity of fresh produce. It should be noted that in the following text... Recorded as In addition, if the set values ​​include at least the set types and quantities of fresh produce, they may also include the set nitrogen concentration or the set ethylene concentration.

[0066] The CA cold storage control device 322 is a device that controls the temperature and humidity inside the CA cold storage 101 based on the set values ​​input to the set value input device 321. It should be noted that the CA cold storage control device 322 can also control the temperature or humidity inside the CA cold storage 101.

[0067] Display device 323 is a device for displaying the set values ​​input to set value input device 321 and the detection results of sensor group 310. Display device 323 is provided with a display for displaying set values ​​and detection results.

[0068] <Hardware Components of a Gas Quantity Estimation Device>

[0069] Figure 4 This is a hardware configuration diagram of the gas quantity estimation device in this embodiment. Figure 4 This is a hardware configuration diagram of a gas quantity estimation device. (Example) Figure 4As shown, the gas quantity estimation device 5 includes a control unit 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory) 503, a storage device 504, a keyboard 506, a display 507, an external device I / F 508, a network I / F 509, and a bus 510.

[0070] The control unit 501 is composed of a CPU (Central Processing Unit), but may also include a GPGPU (General-purpose computing on graphics processing unit). The control unit 501 controls the operation of the entire gas quantity estimation device 5.

[0071] ROM 502 stores the program used for processing by the control unit 501. RAM 503 serves as the working area of ​​the control unit 501.

[0072] The storage device 504 is composed of an SSD (Solid State Drive), HDD (Hard Disk Drive), or flash memory. Under the control of the control unit 501, the storage device 504 reads or writes various data, such as the program executed by the gas quantity estimation device. These various data include a machine learning data set. In this embodiment, the machine learning data set includes data related to the gas consumption during operation of the CA refrigeration unit 300, and gas quantity data representing the gas consumption during operation of the CA refrigeration unit 300. These data will be described in detail later.

[0073] Keyboard 506 is an input unit with multiple plural keys for inputting characters, numbers, various indicators, etc.

[0074] The display 507 is a type of display unit using liquid crystal and organic EL (ElectroLuminescence) for displaying data, images, and various icons.

[0075] The External Device I / F508 is an interface for connecting various external devices. In this case, external devices include, for example, an external monitor as a display unit, a mouse, keyboard, or microphone as an input unit, a printer or speaker as an output unit, and a USB (Universal Serial Bus) memory as a storage unit.

[0076] The Network I / F509 can communicate with operating terminals and servers other than the gas quantity estimation device 5 via communication networks such as the Internet.

[0077] Bus 510 is used for... Figure 5 The address bus and data bus, etc., are electrically connected to the various components of the control unit 501 shown.

[0078] [Functional Composition]

[0079] <Learning Phase>

[0080] Figure 5 This is a functional block diagram of the gas quantity estimation device during the learning phase. For example... Figure 5 As shown, the gas quantity estimation device 5 in the learning phase has an input unit 51 and a learning unit 52. Each of these functional units is based on a program generated from... Figure 4 The functions implemented by the commands of the control unit 501.

[0081] Input section 51 from Figure 3 The sensor group 310 inputs data related to gas consumption within the CA cold storage 101. This gas consumption data includes temperature, humidity, O2 concentration, and CO2 concentration data within the storage facility. It should be noted that the gas consumption data can also be at least one of the following: temperature, humidity, O2 concentration, and CO2 concentration. For example, the gas consumption data could be either O2 concentration or CO2 concentration.

[0082] In addition, the input unit 51 also inputs data from the setting value input device 321 for setting temperature, setting O2 concentration, setting CO2 concentration, and setting type and quantity of fresh produce. It should be noted that the input unit 51 can also input at least the setting type and quantity of fresh produce from the data for setting temperature, setting O2 concentration, setting CO2 concentration, and setting type and quantity of fresh produce. For example, in addition to the data for setting type and quantity of fresh produce, the input unit 51 can also input data for setting O2 concentration or setting CO2 concentration.

[0083] During the learning phase, after transportation is completed, the gas quantity estimation device 5 inputs various output data (data related to gas consumption, set temperature data, etc.) from the storage device storing the output data of the CA refrigeration equipment 300 configured on truck 1a. Alternatively, the gas quantity estimation device 5 may not be installed at the transportation company A, but rather on the truck 1a. In this case, the gas quantity estimation device 5 can directly input various output data (data related to gas consumption, set temperature data, etc.) during transportation.

[0084] The learning unit 52 has a machine learning model, which can generate a machine learning model capable of high-precision output by using machine learning algorithms such as neural networks. In this embodiment, the machine learning model is a gas consumption model 50 during the operation of the CA refrigeration equipment. For example, the learning unit 52 takes at least information related to the type and quantity of fresh produce stored in the CA refrigeration unit 101 as input data, and outputs the amount of CA gas supplied to and removed from the CA refrigeration unit 101 at predetermined times. The output data is data related to oxygen, carbon dioxide, nitrogen, or ethylene.

[0085] Furthermore, the learning unit 52 also includes a comparison and modification unit 53, which compares the gas quantity data, which is output data from the gas consumption model 50 during CA refrigeration equipment operation, with the actual gas quantity data (data on the supply or processing volume of CA gas), which is the correct answer (correct data), and can modify the model parameters of the gas consumption model 50 during CA refrigeration equipment operation based on the error. Accordingly, the learning unit 52 can perform machine learning on the gas consumption model 50 during CA refrigeration equipment operation and generate the learned (completed learning) gas consumption model 60 for CA refrigeration equipment operation, which will be described later.

[0086] <Estimation Phase>

[0087] Figure 6 This is a functional block diagram of the gas quantity estimation device during the estimation stage. For example... Figure 6 As shown, the gas quantity estimation device 5 in the estimation stage has an input unit 61, an estimation unit 62, and an output unit 64. Each of these functional units is based on a program derived from... Figure 4 The functions implemented by the commands of the control unit 501.

[0088] The gas volume estimation device 5 can acquire various data from the CA refrigeration equipment 300 via wired or wireless means before truck 1a departs from transportation company A. Before truck 1a departs from transportation company A, it begins operation via the CA refrigeration unit 101, and the input unit 51 can obtain data from... Figure 3 The sensor array 310 inputs data related to gas consumption at the start of the actuation process. This data includes temperature, humidity, O2 concentration, and CO2 concentration data within the storage facility. It should be noted that the types of data related to gas consumption at the start of the actuation process (such as temperature data) during the estimation phase are essentially the same as those during the learning phase.

[0089] In addition, the input unit 51 inputs data from the setting value input device 321 for setting temperature, setting O2 concentration, setting CO2 concentration, and setting type and quantity of fresh produce, as well as data for setting transportation time, which are set values. It should be noted that the types of setting values ​​(setting temperature, etc.) in the estimation stage are basically the same as those in the learning stage.

[0090] The estimation unit 62 has a gas consumption model 60 generated by the learning unit 52 when the CA refrigeration equipment is driven. For example, the estimation unit 62 takes at least information related to the type and quantity of fresh produce stored in the CA refrigeration unit 101 as input data, estimates the supply and removal of CA gas for the CA refrigeration unit 101 at a predetermined time, and outputs the estimated values ​​as output data. It should be noted that the estimation unit 62 can also estimate the supply or removal of CA gas. Specifically, the estimation unit 62 estimates the supply of CA gas when the output data includes the supply of CA gas, or estimates the removal of CA gas when the output data includes the removal of CA gas.

[0091] Furthermore, the estimation unit 62 also includes an accumulation processing unit 63. The accumulation processing unit 63 calculates an estimate of the total gas consumption for a set transportation time based on output data (gas quantity data) obtained from the learned gas consumption model 60 during CA refrigeration equipment operation and data on the set transportation time obtained from the input unit 61. The total gas consumption estimate is an estimate related to the supply and removal of CA gas. In the case of multiple CA refrigeration units 101, the accumulation processing unit 63 can calculate the total gas consumption estimate for each CA refrigeration unit. It should be noted that the total gas consumption estimate can also be an estimate related to either the supply or removal of CA gas. For example, if the output data (gas quantity data) represents the supply and removal of CA gas, the total gas consumption estimate is an estimate related to at least one of the supply and removal of CA gas. If the output data (gas quantity data) represents the supply of CA gas, the total gas consumption estimate is an estimate related to the supply of CA gas. Furthermore, when the gas quantity data presented as output data represents the amount of CA gas removed, the estimated total gas consumption is an estimate related to the amount of CA gas removed. The amount removed is an example of the throughput.

[0092] In addition, the cumulative processing unit 63 can also calculate the number of CA refrigeration units 102 that control the amount of CA gas in each of the multiple CA refrigeration units 101 according to the type and quantity of fresh produce based on the supply or processing amount of CA gas in each of the multiple CA refrigeration units 101.

[0093] The output unit 64 acquires the estimated total gas consumption calculated by the accumulation processing unit 63 and outputs it to the aforementioned external device via the display 507 or the external device I / F 508.

[0094] [Processing or actions in the implementation method]

[0095] Next, combined Figures 7 to 9 The processing or operation of this embodiment will be explained.

[0096] <Processing during the learning phase>

[0097] Figure 7 This is a flowchart representing the processing steps in the learning phase. For example... Figure 7 As shown, the input unit 51 inputs from... Figure 3 The sensor group 310 outputs data related to the gas consumption in the CA cold storage 101, and also inputs data as input data, such as the set temperature, set O2 concentration, set CO2 concentration, and set type and quantity of fresh products, output by the set value input device 321 (S11).

[0098] Then, the learning unit 52 learns the gas consumption model 50 when the CA refrigeration equipment is in operation by using machine learning algorithms such as neural networks, thereby generating the learned gas consumption model 60 when the CA refrigeration equipment is driven (S12).

[0099] Next, the learning unit 52 determines whether the machine learning has ended (S13). If it has not ended (S13; NO), it returns to step S11 above to continue processing. On the other hand, if it has ended (S13; YES), the learning phase processing ends.

[0100] <Processing during the estimation phase>

[0101] Figure 8 This is a flowchart illustrating the processing during the estimation phase. For example... Figure 9 As shown, the input unit 61 inputs from... Figure 3 The sensor group 310 outputs data related to the gas consumption in the CA cold storage 101, and also inputs data as input data output by the set value input device 321, including set temperature, set O2 concentration and set CO2 concentration, set type and quantity of fresh products, and set transportation time (S21).

[0102] Next, the estimation unit 62 uses the information related to the type and quantity of fresh products stored in the CA cold storage 101 as input data, thereby estimating the supply amount and removal amount of CA gas for the CA cold storage 101 at a predetermined time, and taking this as output data (S22). It should be noted that the estimation unit 62 may also estimate the supply amount or removal amount of CA gas.

[0103] Then, the cumulative processing unit 63 of the estimation unit 62 calculates an estimated value of the total gas consumption during the set transportation time based on the output data, that is, the gas quantity data obtained from the learned gas consumption model 60 during the operation of the CA cold storage equipment and the data of the set transportation time obtained from the input unit 61 (S23).

[0104] After that, the output unit 64 acquires the estimated value of the total gas consumption calculated by the cumulative processing unit 63 and outputs it to the above-mentioned external device via the display 507 or the external device I / F 508 (S24). Thereby, the processing in the estimation stage is completed.

[0105] By the above, as Figure 1 shown, when the user injects a predetermined amount of CA gas from the gas injection device 4 into the CA gas cylinder 104a in the container 2a, the injection of CA gas with a CA gas amount considering the transportation time can be performed according to the estimated value of the total gas consumption output in step S24. In this case, for safety reasons, the user can inject CA gas with a CA gas amount greater than the estimated value of the total gas consumption output in step S24 within the range where the CA gas cylinder 104a can be injected.

[0106] <CA Control>

[0107] Figure 9 is a schematic diagram of the standard processing in the CA mode.

[0108] When truck 1a is in transportation, as Figure 2 shown, the CA cold storage control device 322 of the CA cold storage equipment 300 converts the CA cold storage 101 in the container 2a from the atmospheric state to the oxygen concentration reduction mode and further to the air composition adjustment mode, thereby controlling the CA cold storage 101 to the target air composition.

[0109] The oxygen concentration reduction mode is an operating mode in which the O2 concentration approaches the set concentration by the supply of low-concentration oxygen and the respiration of fresh products during the period from t1 (seconds) to t2 (seconds) after the start of the CA cold storage equipment 300. It should be noted that after the CA cold storage equipment is started, it automatically transitions to the "oxygen concentration reduction mode".

[0110] The air composition adjustment mode is a working mode that adjusts the O2 and CO2 concentrations starting from t2 (seconds) through ventilation based on low-concentration oxygen supply and external air supply, as well as the respiration of fresh produce. It should be noted that once the O2 concentration reaches the set concentration, it automatically transitions to the "air composition adjustment mode".

[0111] [Variation Example]

[0112] Figure 10 This is a schematic diagram of a modified truck according to this embodiment.

[0113] Figure 10 The truck 1b shown is Figure 1 An example of truck 1b. The container 2b mounted on truck 1b contains multiple CA refrigerated compartments 101, CA refrigerated units 102, CA gas cylinders 104b, and CA gas piping 105b. It should be noted that... Figure 10 For ease of explanation, only one group (CA cold storage 101, CA cold storage unit 102, CA gas cylinder 104b and CA gas piping 105b) is given a symbol.

[0114] As for CA cold storage 101 and CA cold storage unit 102, since they have already been described in the above embodiments, detailed descriptions are omitted here.

[0115] CA gas cylinder 104b is Figure 2 The CA gas cylinder 104a is a miniaturized version of the original. It should be noted that the CA gas cylinder 104b is an example of a gas processing device. The CA gas piping 105b is... Figure 2 The CA gas piping 105a is a shorter piping used to supply CA gas from the CA gas cylinder 104b to the CA refrigeration unit 102.

[0116] In this modified example, the gas quantity estimation device 5 estimates the total gas consumption of each of the multiple CA gas cylinders 104b.

[0117] [Main Effects of the Implementation Method]

[0118] As described above, according to the first method of this disclosure, it has the effect of optimizing the injection amount of CA gas.

[0119] According to the second method, the injection amount of CA gas can be optimized by using the results obtained through machine learning.

[0120] According to the third method, the injection amount of CA gas can be optimized by using table data.

[0121] According to the fourth method, by including the temperature or humidity inside the CA cold storage during the transportation process of fresh produce in the input data, the injection volume of CA gas can be optimized with higher precision.

[0122] According to method 5, by taking into account the transportation time of fresh produce, the injection amount of CA gas can be optimized with higher precision even when the transportation time is long.

[0123] According to method 6, by estimating the supply or removal of CA gas, the injection amount of CA gas can be optimized with higher precision.

[0124] According to the seventh method, even when multiple CA cold storage units are used for transportation, it is possible to calculate the number of gas quantity control devices used to control the amount of CA gas in each of the multiple CA cold storage units.

[0125] According to Method 8, it is possible to respond even when the output data is oxygen, carbon dioxide, nitrogen, or ethylene.

[0126] According to the 9th method, a gas handling device such as a CA gas cylinder is used to optimize the amount of CA gas to be injected.

[0127] According to the 10th method, a transport container with a gas handling device such as a CA gas cylinder having an optimized injection volume of CA gas can be prepared.

[0128] According to method 11, a gas handling device such as a CA gas cylinder can be prepared, which optimizes the injection volume of CA gas according to the type and quantity of fresh produce.

[0129] According to method 12, the injection volume of CA gas can be optimized. According to method 2, by including the temperature or humidity inside the CA cold storage during the transportation of fresh produce in the input data, the injection volume of CA gas can be optimized with higher precision.

[0130] According to method 13, the injection amount of CA gas can be optimized by using the results obtained through machine learning.

[0131] According to method 14, the injection amount of CA gas can be optimized by using table data.

[0132] According to method 15, the injection amount of CA gas can be optimized.

[0133] 〔Replenish〕

[0134] The present invention is not limited to the above-described embodiments and modifications, and may also be configured or processed (operations) as described below.

[0135] In the above embodiment, the control unit 501 calculates the supply or processing volume of CA gas using the results obtained by learning the relationship between input data (information related to the types and quantities of fresh produce stored in the CA cold storage 101) and the actual supply or processing volume of CA gas through machine learning. However, this is not a limitation. For example, the control unit 501 may also use the relationship between input data (information related to the types and quantities of fresh produce stored in the CA cold storage 101) and the actual supply or processing volume of CA gas as table data, and use the table data to calculate the supply or processing volume of CA gas. In this case, the information related to the types and quantities of fresh produce stored in the CA cold storage 101 and the information related to the actual supply or processing volume of CA gas are managed in a way that they are related to each other in the table data.

[0136] In the above embodiment, the CA cold storage 101 is installed inside the container 2 mounted on the truck 1, but it is not limited to this. For example, the CA cold storage 101 can also be a CA refrigerated delivery box. In addition, the CA cold storage 101 can also be installed on a CA truck trailer equipped with refrigeration equipment.

[0137] Container 2 also includes shipping containers. In this case, shipping containers can be transported by ship instead of truck 1.

[0138] Furthermore, the program used to realize the function of the gas quantity estimation device 3 can be distributed via storage media such as DVD (Digital Versatile Disc) or widely provided via communication networks such as the Internet.

[0139] In addition, the control unit 501 may also be composed of multiple CPUs.

[0140] This application claims priority based on Japanese Patent Application No. 2021-160698, filed on September 30, 2021, the entire contents of which are incorporated herein by reference.

[0141] [Industrial Applicability]

[0142] As described above, this disclosure is applicable to the technical fields of gas quantity estimation devices, gas processing devices, transport containers, gas quantity estimation methods and procedures.

[0143] [Explanation of reference numerals in the attached figures]

[0144] 1 truck

[0145] 2 containers

[0146] 4. Gas injection device

[0147] 5. Gas quantity estimation device

[0148] Gas consumption model when 50 CA refrigeration equipment is driven

[0149] 51 Input Section

[0150] 52 Study Department

[0151] 53 Comparison and Change Department

[0152] 60. Gas consumption model for CA refrigeration equipment driven by existing knowledge

[0153] 61 Input Section

[0154] 62. Estimation Department

[0155] 63 Cumulative Processing Department

[0156] 64 Output Section

[0157] 101 CA Cold Storage

[0158] 102 CA Refrigeration Unit (An Example of a Gas Quantity Control Device)

[0159] 103 Valve

[0160] 104a CA gas cylinder (an example of a gas handling device)

[0161] 104b CA gas cylinder (an example of a gas handling device)

[0162] 105a CA Gas Piping

[0163] 105b CA Gas Piping

[0164] 501 Control Department.

Claims

1. A gas quantity estimation device (5) having a control unit (501), wherein, Before the CA cold storage (101) is transported, the control unit takes information related to the type and quantity of fresh produce stored in the CA cold storage (101) and information on the temperature or humidity inside the CA cold storage as input data. Using machine learning to learn the relationship between the information related to the type and quantity of fresh produce to be stored in the CA cold storage, the information on the temperature or humidity inside the cold storage, and the supply or processing volume of CA gas for the CA cold storage, the control unit estimates the supply or processing volume of CA gas for the CA cold storage at a predetermined time and outputs it as output data. Based on the transportation time of the fresh produce, the control unit outputs an estimate of the total gas consumption of the gas processing devices (104a, 104b), which are transported together with the CA cold storage for processing the CA gas for the CA cold storage.

2. The gas quantity estimation device as described in claim 1, wherein, The output data includes: The amount of CA gas supplied to the CA cold storage facility during the transportation of the fresh produce in order to maintain the CA gas at a predetermined concentration; or The amount of CA gas removed from the CA cold storage during the transportation of the fresh produce in order to maintain the CA gas at the predetermined concentration. Wherein, if the output data includes the supply amount of the CA gas, the control unit estimates the supply amount of the CA gas; or, if the output data includes the removal amount of the CA gas, the control unit estimates the removal amount in the processing amount of the CA gas.

3. The gas quantity estimation device as described in claim 1 or 2, wherein, The control unit calculates the number of gas quantity control devices (102) based on the supply or processing volume of CA gas in each of the multiple CA cold storage units. The gas quantity control devices (102) control the amount of CA gas in each of the multiple CA cold storage units according to the type and quantity of the fresh produce.

4. The gas quantity estimation device as described in claim 1, wherein, The output data is related to oxygen, carbon dioxide, nitrogen, or ethylene.

5. A gas processing apparatus (104a, 104b) for processing CA gas in the CA cold storage, wherein, A predetermined amount of CA gas was injected based on the supply or processing volume of the CA gas estimated by the gas volume estimation device as described in any one of claims 1 to 4.

6. A transport container (2) comprising the gas handling apparatus as described in claim 5.

7. The transport container as described in claim 6, further comprising: A gas quantity control device controls the amount of CA gas in the CA cold storage according to the type and quantity of the fresh produce.

8. A gas quantity estimation method, wherein a computer performs the following processing: Before the CA cold storage (101) is transported, information related to the type and quantity of fresh produce stored in the CA cold storage, as well as information on the temperature or humidity inside the CA cold storage, are used as input data. The results obtained by learning the relationship between the information related to the type and quantity of fresh produce to be stored in the CA cold storage, the information on the temperature or humidity inside the cold storage, and the supply or processing volume of CA gas for the CA cold storage are used to estimate the supply or processing volume of CA gas for the CA cold storage at a predetermined time and output data. The total gas consumption estimate of the gas processing device (104a, 104b) is output based on the transportation time of the fresh produce. The gas processing device is transported together with the CA cold storage for processing the CA gas for the CA cold storage.

9. A program product comprising a computer program, characterized in that, The computer program is executed by a processor to implement the method of claim 8.

Images