Artificial Intelligence-Based Control Method and Device for Refrigerated Containers

Abstract

This application provides an artificial intelligence-based control method and apparatus for refrigerated containers, relating to the field of refrigerated container technology. The method determines the required refrigeration temperature for the stacked refrigerated goods based on their type. The type, weight, and refrigeration temperature of the stacked goods are input into an operating parameter determination model to determine multiple sets of operating parameters for an intelligent refrigerated container that maintain the refrigeration temperature at various locations on the stacked goods. The refrigeration power and airflow velocity from each set of operating parameters are input into a power consumption determination model to determine the power consumption of the refrigeration equipment corresponding to each set of operating parameters. The set of operating parameters corresponding to the refrigeration equipment with the lowest power consumption is selected. Based on the refrigeration power, airflow velocity, and airflow direction of the refrigeration equipment in the selected set of operating parameters, the operation of the refrigeration equipment is controlled, and the angle between the extension direction towards the interior of the container and the horizontal direction is controlled for each electric air guide plate according to the selected operating parameters.

Description

Technical Field

[0001] This application relates to the field of refrigerated container technology, and in particular to a refrigerated container control method and device based on artificial intelligence. Background Technology

[0002] A shipping container is a large cargo container with a certain strength, rigidity, and specifications, specifically designed for repeated use. Using containers for cargo transport allows for direct loading at the shipper's warehouse and unloading at the consignee's warehouse. When changing vehicles or ships en route, the goods do not need to be removed from the container for repackaging. For goods requiring refrigerated transport (such as medical biological agents, vaccines, and refrigerated food), the goods can be packed into cargo boxes, which are then stacked into refrigerated containers. The refrigerated containers, with their fixed refrigeration capacity corresponding to the type of goods, can refrigerate the goods inside to prevent spoilage.

[0003] Currently, to save space in transport vehicles, refrigerated containers that are not fully loaded can be folded to a certain extent. However, folding refrigerated containers changes the ventilation channels inside, causing uneven heating and cooling of goods in different locations, which can still lead to spoilage of some goods. Summary of the Invention

[0004] This application provides an artificial intelligence-based refrigerated container control method and device to solve the problem in the prior art that after folding a refrigerated container, the ventilation channels inside the refrigerated container will change, causing different temperatures of goods in different locations, which in turn will still lead to the spoilage of some goods.

[0005] In a first aspect, this application provides an artificial intelligence-based refrigerated container control method, applied to the main controller of an intelligent refrigerated container. The intelligent refrigerated container includes a container body, which includes a top plate and a bottom plate arranged opposite each other, two first side panels arranged opposite each other, and two second side panels arranged opposite each other. Each first side panel is foldable towards the inside of the container body, and the folding line of each first side panel is parallel to the top or bottom plate of the container body. A first distance sensor and a second distance sensor are respectively arranged on the folding lines on the inner sides of the two first side panels. A third distance sensor is arranged on the inner side of the top plate, and a human-machine interface panel is arranged on the outer side of the top plate. Each first side panel has an electric air guide plate arranged on both sides of its folding line. A refrigeration device is arranged on the inner side of one of the second side panels. The method includes:

[0006] The system receives the type and weight of the refrigerated stacked goods to be transported inside the box, input by the user on the human-computer interaction panel, as well as the first distance value between the system and the refrigerated stacked goods collected by the first distance sensor, the second distance value between the system and the refrigerated stacked goods collected by the second distance sensor, and the third distance value between the system and the refrigerated stacked goods collected by the third distance sensor.

[0007] Subtract a preset distance threshold from the first distance value to obtain the first distance difference; subtract a preset distance threshold from the second distance value to obtain the second distance difference; subtract a preset distance threshold from the third distance value to obtain the third distance difference.

[0008] Determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively. Drive each first side panel according to the control drive motor to fold along the folding line to the smallest foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference.

[0009] Determine the required refrigeration temperature for refrigerated stacked goods based on their type;

[0010] The type, weight, and refrigeration temperature of the refrigerated stacked goods are input into a pre-trained operating parameter determination model to determine multiple sets of operating parameters for the intelligent refrigerated container that maintain the refrigeration temperature at various positions on the refrigerated stacked goods. Each set of operating parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate towards the inside of the container and the horizontal direction. The operating parameter determination model is trained by inputting multiple first training samples into the first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods, as well as the historical operating parameters of the intelligent refrigerated container that maintain the historical refrigeration temperature at various positions on the historical refrigerated stacked goods.

[0011] The cooling power and air outlet speed in each set of operating parameters are input into a pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters. The power consumption determination model is obtained by inputting multiple second training samples into a second network to be trained. Each second training sample includes the historical cooling power and historical air outlet speed in the historical operating parameters of the cooling equipment, as well as the corresponding historical power consumption.

[0012] Select the set of operating parameters corresponding to the lowest power consumption of the refrigeration equipment;

[0013] Based on the selected set of operating parameters, including the cooling power, air velocity, and air direction of the refrigeration equipment, the system controls the operation of the refrigeration equipment; and controls the rotation of each electric air guide plate so that each electric air guide plate reaches the angle between the direction extending into the box and the horizontal direction as selected in the operating parameters.

[0014] In some embodiments, a non-contact temperature sensor is provided on both sides of each first side panel along its fold line, and a contact temperature sensor is provided at the geometric center of the housing. After controlling the operation of the refrigeration equipment and controlling the rotation of each electric air guide vane according to the refrigeration power, air velocity, and air direction, so that each electric air guide vane reaches a determined angle between its extension direction into the housing and the horizontal direction, the method provided in this application further includes:

[0015] Receives the temperature of refrigerated stacked goods collected by each non-contact temperature sensor and receives the temperature of refrigerated stacked goods collected by contact temperature sensors;

[0016] Determine the actual average temperature of multiple temperatures of the received refrigerated stacked goods;

[0017] Determine the temperature difference between the actual average temperature and the required refrigeration temperature for stacked refrigerated goods;

[0018] If the temperature difference is greater than the set temperature threshold, the first network parameters of the model are determined by updating the running parameters of the first reinforcement learning model until the temperature difference is lower than or equal to the set temperature threshold. Here, the temperature difference is the reward of the first reinforcement learning model, and the lower the temperature difference, the higher the reward. Updating the running parameters to determine the first network parameters of the model is the action of the first reinforcement learning model, and the first network parameters are the state of the first reinforcement learning model.

[0019] In some embodiments, when the temperature difference is lower than or equal to a set temperature threshold, the method provided in this application further includes:

[0020] Determine the variance of multiple temperatures for the received refrigerated stacked goods;

[0021] If the variance of the temperatures of multiple refrigerated stacked goods is greater than a preset variance threshold, the second network parameters of the model are determined by updating the running parameters of the second reinforcement learning model until the variance of the multiple temperatures of the refrigerated stacked goods is less than or equal to the preset variance threshold. The variance of the multiple temperatures of the refrigerated stacked goods is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods, the higher the reward. Updating the running parameters to determine the second network parameters of the model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

[0022] In some implementations, determining the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference includes:

[0023] Based on the preset first mapping relationship, the foldable angles corresponding to the first distance difference and the second distance difference are retrieved from the preset database.

[0024] Based on the preset second mapping relationship, the foldable angle corresponding to the third distance difference is searched from the preset database.

[0025] In some implementations, the first network to be trained is a neural network.

[0026] Secondly, this application also provides an artificial intelligence-based refrigerated container control device, configured in the main controller of an intelligent refrigerated container. The intelligent refrigerated container includes a container body, which includes a top plate and a bottom plate arranged opposite each other, two first side panels arranged opposite each other, and two second side panels arranged opposite each other. Each first side panel is foldable towards the inside of the container body, and the folding line of each first side panel is parallel to the top or bottom plate of the container body. A first distance sensor and a second distance sensor are respectively arranged on the folding lines on the inner sides of the two first side panels. A third distance sensor is arranged on the inner side of the top plate. A human-machine interface panel is arranged on the outer side of the top plate. Each first side panel has an electric air guide plate arranged on both sides of its folding line. A refrigeration device is arranged on the inner side of one of the second side panels. The device includes:

[0027] The data receiving unit is used to receive the type and weight of the refrigerated stacked goods to be transported in the box, which are input by the user on the human-machine interaction panel, as well as to receive the first distance value between the refrigerated stacked goods and the first distance value collected by the first distance sensor, the second distance value collected by the second distance sensor, and the third distance value collected by the third distance sensor.

[0028] The distance difference determination unit is used to subtract a preset distance threshold from a first distance value to obtain a first distance difference, subtract a preset distance threshold from a second distance value to obtain a second distance difference, and subtract a preset distance threshold from a third distance value to obtain a third distance difference.

[0029] The foldable angle determination unit is used to determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively. According to the control drive motor, each first side panel is driven to fold along the folding line to the minimum foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference.

[0030] The refrigeration temperature determination unit is used to determine the required refrigeration temperature for refrigerated stacked goods based on the type of refrigerated stacked goods.

[0031] The operation parameter determination unit is used to input the type, weight, and refrigeration temperature of the refrigerated stacked goods into the pre-trained operation parameter determination model to determine multiple sets of operation parameters of the intelligent refrigerated container that maintain the refrigeration temperature at various positions on the refrigerated stacked goods. Each set of operation parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate towards the inside of the container and the horizontal direction. The operation parameter determination model is trained by inputting multiple first training samples into the first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods, as well as the historical operation parameters of the intelligent refrigerated container that maintain the historical refrigeration temperature at various positions on the historical refrigerated stacked goods.

[0032] The power consumption determination unit is used to input the cooling power and air outlet speed in each set of operating parameters into a pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters. The power consumption determination model is obtained by inputting multiple second training samples into a second network to be trained. Each second training sample includes the historical cooling power and historical air outlet speed in the historical operating parameters of the cooling equipment, and the corresponding historical power consumption.

[0033] The operating parameter selection unit is used to select the minimum power consumption of the refrigeration equipment, corresponding to a set of operating parameters;

[0034] The control unit is used to control the operation of the refrigeration equipment according to the refrigeration power, air outlet speed and air outlet direction of the refrigeration equipment in a selected set of operating parameters; and to control the rotation of each electric air guide plate so that each electric air guide plate reaches the angle between the extension direction towards the inside of the box and the horizontal direction in the selected operating parameters.

[0035] In some embodiments, a non-contact temperature sensor is provided on both sides of each first side panel along its fold line, and a contact temperature sensor is provided at the geometric center of the housing.

[0036] The data receiving unit is also used to receive the temperature of the refrigerated stacked goods collected by each non-contact temperature sensor and to receive the temperature of the refrigerated stacked goods collected by the contact temperature sensor.

[0037] The apparatus provided in this application also includes:

[0038] An average temperature determination unit is used to determine the actual average temperature of multiple temperatures of the received refrigerated stacked goods.

[0039] The differential temperature determination unit is used to determine the temperature difference between the actual average temperature and the required refrigeration temperature for refrigerated stacked goods.

[0040] The parameter update unit is used to update the running parameters of the first reinforcement learning model to determine the first network parameters of the model when the difference temperature is greater than the set temperature threshold, until the difference temperature is lower than or equal to the set temperature threshold. Here, the difference temperature is the reward of the first reinforcement learning model, and the lower the difference temperature, the higher the reward. Updating the running parameters to determine the first network parameters of the model is the action of the first reinforcement learning model, and the first network parameters are the state of the first reinforcement learning model.

[0041] In some embodiments, the apparatus provided in this application further includes:

[0042] Temperature variance determination unit, used to determine the variance of multiple temperatures of received refrigerated stacked goods;

[0043] The parameter update unit is further configured to update the running parameters of the second reinforcement learning model to determine the second network parameters of the model when the variance of the temperatures of multiple refrigerated stacked goods is greater than a preset variance threshold, until the variance of the multiple temperatures of the refrigerated stacked goods is less than or equal to the preset variance threshold. Here, the variance of the multiple temperatures of the refrigerated stacked goods is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods, the higher the reward. Updating the running parameters to determine the second network parameters of the model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

[0044] In some embodiments, the foldable angle determination unit is specifically used to search for the foldable angles corresponding to the first distance difference and the second distance difference respectively from a preset database according to a preset first mapping relationship; and to search for the foldable angle corresponding to the third distance difference from a preset database according to a preset second mapping relationship.

[0045] In some implementations, the first network to be trained is a neural network.

[0046] This application provides an artificial intelligence-based refrigerated container control method and apparatus, which can stack refrigerated goods from the center of the refrigerated container outwards, while maintaining a certain distance between the stacked goods and the inner walls of the container to ensure internal air circulation. Furthermore, it can receive the type and weight of the refrigerated goods to be transported inside the container, input by the user through a human-machine interface panel, as well as the first distance values ​​between the stacked goods and the container collected by a first distance sensor, a second distance sensor, and a third distance sensor. Subtracting the preset distance threshold from the first distance value yields the first distance difference (i.e., the distance one of the first side panels can move towards the inside of the box after maintaining the distance of the air circulation channel). Subtracting the preset distance threshold from the second distance value yields the second distance difference (i.e., the distance the other first side panel can move towards the inside of the box after maintaining the distance of the air circulation channel). Subtracting the preset distance threshold from the third distance value yields the third distance difference (i.e., the distance the other first side panel can move towards the inside of the box after maintaining the distance of the air circulation channel).

[0047] The foldable angles corresponding to the first, second, and third distance differences are determined. Each first side panel is then driven by a control motor to fold along the folding line to the smallest foldable angle among the three corresponding distance differences. This ensures that after the refrigerated container is folded, the stacked refrigerated goods maintain a certain distance from the inner wall of the container.

[0048] Determine the required refrigeration temperature based on the type of refrigerated stacked goods. The required refrigeration temperature will save power while preventing the refrigerated stacked goods from spoiling.

[0049] The type, weight, and refrigeration temperature of the refrigerated stacked goods are input into a pre-trained operational parameter determination model. This model determines multiple sets of operational parameters for the intelligent refrigerated container to maintain the refrigerated temperature at various locations on the stacked goods. Each set of parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide vane into the container and the horizontal direction. This ensures that all locations on the stacked goods are at the required refrigeration temperature with uniform heating and cooling.

[0050] The cooling power and airflow velocity from each set of operating parameters are input into a pre-trained power consumption determination model to determine the power consumption of the refrigeration equipment corresponding to each set of operating parameters. The set of operating parameters corresponding to the refrigeration equipment with the lowest power consumption is selected. Based on the cooling power, airflow velocity, and airflow direction of the refrigeration equipment in the selected set of operating parameters, the operation of the refrigeration equipment is controlled; and the rotation of each electric air guide plate is controlled so that each electric air guide plate reaches the angle between the direction extending into the container and the horizontal direction in the selected operating parameters. In this way, all positions on the refrigerated stacked goods are at the required refrigeration temperature with uniform heating and cooling, while consuming the least amount of power and saving the space occupied by the refrigerated container, making it highly practical. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 A cross-sectional view of the intelligent refrigerated container provided in this application embodiment when it is in an folded state;

[0053] Figure 2 One of the flowcharts for an artificial intelligence-based refrigerated container control method provided in this application embodiment;

[0054] Figure 3 A cross-sectional view of the intelligent refrigerated container provided in this application embodiment when it is in a folded state. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments made by those skilled in the art under the guidance of these embodiments are within the scope of protection of this application.

[0056] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0057] This application provides an artificial intelligence-based refrigerated container control method, applied to the main controller of an intelligent refrigerated container. For example... Figure 1 As shown, the intelligent refrigerated container includes a container body with a cuboid geometry. The container body includes a top plate 101 and a bottom plate 102 arranged opposite each other, two first side panels 103 arranged opposite each other, and two second side panels (not shown in the attached figures). Each first side panel 103 is foldable towards the inside of the container body, and the folding line of each first side panel 103 is parallel to the top plate 101 or the bottom plate 102 of the container body. A first distance sensor 105 and a second distance sensor 106 are respectively arranged on the folding lines on the inner sides of the two first side panels 103. A third distance sensor 107 is arranged on the inner side of the top plate 101, and a human-machine interface panel 108 is arranged on the outer side of the top plate 101. Each first side panel 103 has an electric air guide plate 109 arranged on both sides of its folding line. A refrigeration device (not shown in the attached figures) is arranged on the inner side of one of the second side panels. Figure 2 As shown, the method provided in this application embodiment includes:

[0058] S201: Receive the type and weight of the refrigerated stacked goods 111 to be transported in the box, input by the user on the human-machine interaction panel 108, and receive the first distance value between the refrigerated stacked goods 111 collected by the first distance sensor 105, the second distance value between the refrigerated stacked goods 111 collected by the second distance sensor 106, and the third distance value between the refrigerated stacked goods 111 collected by the third distance sensor 107.

[0059] It should be noted that refrigerated stacked goods 111 can be stacked from the center of the refrigerated container outwards, and the refrigerated stacked goods 111 need to maintain a certain distance from the inner wall of the refrigerated container to ensure internal air circulation channels.

[0060] For example, the types of refrigerated stacked goods 111 can be, but are not limited to, ice cream, biological agents (such as insulin), and vaccines packaged in small cartons. Understandably, there are gaps between the various refrigerated stacked goods 111 packaged in small cartons for ventilation.

[0061] S202: Subtract a preset distance threshold from the first distance value to obtain the first distance difference; subtract a preset distance threshold from the second distance value to obtain the second distance difference; subtract a preset distance threshold from the third distance value to obtain the third distance difference.

[0062] S203: Determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively, and drive each first side panel 103 according to the control drive motor to fold along the folding line to the smallest foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference.

[0063] For example, based on a preset first mapping relationship, the foldable angles corresponding to the first distance difference and the second distance difference can be found from a preset database; based on a preset second mapping relationship, the foldable angle corresponding to the third distance difference can be found from the preset database. It should be noted that the first network to be trained mentioned above is a neural network.

[0064] in, Figure 3 This is a cross-sectional view of a smart refrigerated container after folding. The folding angle can be the included angle between the two parts of the first side panel 103 after folding.

[0065] S204: Determine the required refrigeration temperature for the refrigerated stacked goods 111 based on the type of refrigerated stacked goods 111.

[0066] For example, the required refrigeration temperature for refrigerated stacked goods 111 can be found from a preset database.

[0067] S205: Input the type, weight, and refrigeration temperature of the refrigerated stacked goods 111 into the pre-trained operating parameter determination model to determine multiple sets of operating parameters for the intelligent refrigerated container that maintain the refrigeration temperature at each position on the refrigerated stacked goods 111. Each set of operating parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate 109 toward the inside of the container and the horizontal direction.

[0068] The operating parameter determination model is obtained by inputting multiple first training samples into the first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods 111, as well as the historical operating parameters of the smart refrigerated container that keep the historical refrigeration temperature at each position on the historical refrigerated stacked goods 111.

[0069] S206: Input the cooling power and air outlet speed in each set of operating parameters into the pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters.

[0070] The power consumption determination model is obtained by inputting multiple second training samples into the second network to be trained. Each second training sample includes the historical cooling power and historical air outlet speed in the historical operating parameters of the refrigeration equipment, as well as the corresponding historical power consumption.

[0071] S207: Select the set of operating parameters corresponding to the minimum power consumption of the refrigeration equipment.

[0072] S208: Control the operation of the refrigeration equipment according to the refrigeration power, air outlet speed and air outlet direction of the refrigeration equipment in the selected set of operating parameters; and control the rotation of each electric air guide plate 109 so that each electric air guide plate 109 reaches the angle between the extension direction towards the inside of the box and the horizontal direction in the selected operating parameters.

[0073] In summary, this application provides an artificial intelligence-based refrigerated container control method that can stack refrigerated goods 111 from the center of the refrigerated container outwards, while maintaining a certain distance between the stacked goods 111 and the inner wall of the refrigerated container to ensure internal air circulation. Furthermore, it can receive the type and weight of the refrigerated goods 111 to be transported inside the container, input by the user on the human-machine interface panel 108, as well as the first distance value collected by the first distance sensor 105, the second distance sensor 106, and the third distance value collected by the third distance sensor 107. Subtracting a preset distance threshold from the first distance value yields the first distance difference (i.e., the distance by which one of the first side panels 103 can move towards the inside of the box after maintaining the distance of the air circulation channel). Subtracting a preset distance threshold from the second distance value yields the second distance difference (i.e., the distance by which the other first side panel 103 can move towards the inside of the box after maintaining the distance of the air circulation channel). Subtracting a preset distance threshold from the third distance value yields the third distance difference (i.e., the distance by which the other first side panel 103 can move towards the inside of the box after maintaining the distance of the air circulation channel).

[0074] The foldable angles corresponding to the first, second, and third distance differences are determined. Each first side panel 103 is driven by a control motor to fold along the folding line to the smallest foldable angle among the first, second, and third distance differences. This ensures that after the refrigerated container is folded, the stacked refrigerated goods 111 maintain a certain distance from the inner wall of the refrigerated container.

[0075] Based on the type of refrigerated stacked goods 111, the required refrigeration temperature for refrigerated stacked goods 111 is determined. The required refrigeration temperature can save power consumption without causing the refrigerated stacked goods 111 to deteriorate.

[0076] The type, weight, and refrigeration temperature of the refrigerated stacked goods 111 are input into a pre-trained operational parameter determination model. This model determines multiple sets of operational parameters for the intelligent refrigerated container to maintain the refrigerated temperature at various locations on the refrigerated stacked goods 111. Each set of operational parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate 109 towards the inside of the container and the horizontal direction. In this way, all locations on the refrigerated stacked goods 111 can be kept at the required refrigeration temperature with uniform heating and cooling.

[0077] The cooling power and air outlet speed in each set of operating parameters are input into a pre-trained power consumption determination model to determine the power consumption of the refrigeration equipment corresponding to each set of operating parameters. The set of operating parameters corresponding to the refrigeration equipment with the lowest power consumption is selected. Based on the cooling power, air outlet speed, and air outlet direction of the refrigeration equipment in the selected set of operating parameters, the operation of the refrigeration equipment is controlled; and the rotation of each electric air guide plate 109 is controlled so that each electric air guide plate 109 reaches the angle between the extension direction towards the inside of the container and the horizontal direction in the selected operating parameters. In this way, all positions on the refrigerated stacked goods 111 can be kept at the required refrigeration temperature with uniform heating and cooling, while consuming the least amount of power and saving the space occupied by the refrigerated container, making it highly practical.

[0078] In some embodiments, a non-contact temperature sensor 110 is provided on both sides of each first side panel 103 along its fold line, and a contact temperature sensor (e.g., mounted on a bracket extending into the geometric center of the housing, not shown in the figures) is provided at the geometric center of the housing. After S208, the method provided in this application further includes:

[0079] Step 1: Receive the temperature of the refrigerated stacked goods 111 collected by each non-contact temperature sensor 110 and receive the temperature of the refrigerated stacked goods 111 collected by the contact temperature sensor.

[0080] Step 2: Determine the actual average temperature of the multiple temperatures of the received refrigerated stacked goods 111.

[0081] Step 3: Determine the temperature difference between the actual average temperature and the required refrigeration temperature for the refrigerated stacked goods 111.

[0082] Step 4: When the temperature difference is greater than the set temperature threshold, the first network parameters of the model are determined by updating the running parameters of the first reinforcement learning model until the temperature difference is lower than or equal to the set temperature threshold. Here, the temperature difference is the reward of the first reinforcement learning model, and the lower the temperature difference, the higher the reward. The first network parameters of the model are the action of the first reinforcement learning model and the state of the first reinforcement learning model.

[0083] Based on steps 1-4 above, the actual average temperature of the refrigerated stacked goods 111 can be precisely controlled to the required temperature.

[0084] In some embodiments, when the temperature difference is lower than or equal to a set temperature threshold, the method provided in this application further includes:

[0085] Step A: Determine the variance of multiple temperatures of the received refrigerated stacked goods 111.

[0086] Step B: If the variance of the temperatures of multiple refrigerated stacked goods 111 is greater than a preset variance threshold, the second network parameters of the model are determined by updating the running parameters according to the second reinforcement learning model until the variance of the multiple temperatures of the refrigerated stacked goods 111 is less than or equal to the preset variance threshold. The variance of the multiple temperatures of the refrigerated stacked goods 111 is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods 111, the higher the reward. Updating the running parameters to determine the second network parameters of the model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

[0087] As can be seen from the above, it is possible to accurately ensure that each position on the refrigerated stacked goods 111 is at the required refrigeration temperature and that the temperature is uniform.

[0088] In addition, this application also provides an artificial intelligence-based refrigerated container control device, configured in the main controller of an intelligent refrigerated container. It should be noted that the basic principle and technical effects of the artificial intelligence-based refrigerated container control device provided in this application are the same as those in the above embodiments. For the sake of brevity, any parts not mentioned in this application can be referred to the corresponding content in the above embodiments.

[0089] like Figure 1As shown, the intelligent refrigerated container includes a container body, which includes a top plate 101 and a bottom plate 102 arranged opposite to each other, two first side panels 103 arranged opposite to each other, and two second side panels arranged opposite to each other. Each first side panel 103 is foldable towards the inside of the container body, and the folding line of each first side panel 103 is parallel to the top plate 101 or the bottom plate 102 of the container body. A first distance sensor 105 and a second distance sensor 106 are respectively arranged on the folding lines on the inner sides of the two first side panels 103. A third distance sensor 107 is arranged on the inner side of the top plate 101. A human-machine interface panel 108 is arranged on the outer side of the top plate 101. Each first side panel 103 has an electric air guide plate 109 arranged on both sides of its folding line. A refrigeration device is arranged on the inner side of one of the second side panels. The device provided in the embodiments of this application includes:

[0090] The data receiving unit is used to receive the type and weight of the refrigerated stacked goods 111 to be transported in the box, which are input by the user in the human-machine interaction panel 108, as well as to receive the first distance value between the refrigerated stacked goods 111 collected by the first distance sensor 105, the second distance value between the refrigerated stacked goods 111 collected by the second distance sensor 106, and the third distance value between the refrigerated stacked goods 111 collected by the third distance sensor 107.

[0091] The distance difference determination unit is used to subtract a preset distance threshold from a first distance value to obtain a first distance difference, subtract a preset distance threshold from a second distance value to obtain a second distance difference, and subtract a preset distance threshold from a third distance value to obtain a third distance difference.

[0092] The foldable angle determination unit is used to determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively. According to the control drive motor, each first side panel 103 is driven to fold along the folding line to the minimum foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference.

[0093] The refrigeration temperature determination unit is used to determine the required refrigeration temperature of the refrigerated stacked goods 111 according to the type of refrigerated stacked goods 111;

[0094] The operation parameter determination unit is used to input the type, weight, and refrigeration temperature of the refrigerated stacked goods 111 into the pre-trained operation parameter determination model to determine multiple sets of operation parameters of the intelligent refrigerated container that maintain the refrigeration temperature at each position on the refrigerated stacked goods 111. Each set of operation parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate 109 towards the inside of the container and the horizontal direction. The operation parameter determination model is trained by inputting multiple first training samples into the first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods 111, as well as the historical operation parameters of the intelligent refrigerated container that maintain the historical refrigeration temperature at each position on the historical refrigerated stacked goods 111.

[0095] The power consumption determination unit is used to input the cooling power and air outlet speed in each set of operating parameters into the pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters.

[0096] The operating parameter selection unit is used to select the minimum power consumption of the refrigeration equipment, corresponding to a set of operating parameters;

[0097] The control unit is used to control the operation of the refrigeration equipment according to the refrigeration power, air outlet speed and air outlet direction of the refrigeration equipment in a selected set of operating parameters; and to control the rotation of each electric air guide plate 109 so that each electric air guide plate 109 reaches the angle between the extension direction towards the inside of the box and the horizontal direction in the selected operating parameters.

[0098] In some embodiments, each first side panel 103 is provided with a non-contact temperature sensor 110 on both sides of its fold line, and a contact temperature sensor is provided at the geometric center of the housing.

[0099] The data receiving unit is also used to receive the temperature of the refrigerated stacked goods 111 collected by each non-contact temperature sensor 110 and to receive the temperature of the refrigerated stacked goods 111 collected by the contact temperature sensor.

[0100] The apparatus provided in this application embodiment also includes:

[0101] An average temperature determination unit is used to determine the actual average temperature of multiple temperatures of the received refrigerated stacked goods 111.

[0102] The differential temperature determination unit is used to determine the temperature difference between the actual average temperature and the required refrigeration temperature of the refrigerated stacked goods 111.

[0103] The parameter update unit is used to update the running parameters of the first reinforcement learning model to determine the first network parameters of the model when the difference temperature is greater than the set temperature threshold, until the difference temperature is lower than or equal to the set temperature threshold. Here, the difference temperature is the reward of the first reinforcement learning model, and the lower the difference temperature, the higher the reward. Updating the running parameters to determine the first network parameters of the model is the action of the first reinforcement learning model, and the first network parameters are the state of the first reinforcement learning model.

[0104] In some embodiments, the apparatus provided in this application further includes:

[0105] Temperature variance determination unit, used to determine the variance of multiple temperatures of the received refrigerated stacked goods 111;

[0106] The parameter update unit is further configured to update the running parameters of the second reinforcement learning model to determine the second network parameters of the model when the variance of the temperatures of the multiple refrigerated stacked goods 111 is greater than a preset variance threshold, until the variance of the multiple temperatures of the refrigerated stacked goods 111 is less than or equal to the preset variance threshold. The variance of the multiple temperatures of the refrigerated stacked goods 111 is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods 111, the higher the reward. Updating the running parameters to determine the second network parameters of the model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

[0107] In some embodiments, the foldable angle determination unit is specifically used to search for the foldable angles corresponding to the first distance difference and the second distance difference respectively from a preset database according to a preset first mapping relationship; and to search for the foldable angle corresponding to the third distance difference from a preset database according to a preset second mapping relationship.

[0108] In some implementations, the first network to be trained is a neural network.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A refrigerated container control method based on artificial intelligence, characterized in that, A main controller for an intelligent refrigerated container, the intelligent refrigerated container including a container body, the container body including a top plate and a bottom plate arranged opposite each other, two first side panels arranged opposite each other, and two second side panels arranged opposite each other, each first side panel being foldable towards the inside of the container body, and the folding line of each first side panel being parallel to the top plate or the bottom plate of the container body; a first distance sensor and a second distance sensor are respectively arranged on the folding lines on the inner sides of the two first side panels, a third distance sensor is arranged on the inner side of the top plate, and a human-machine interface panel is arranged on the outer side of the top plate; each first side panel is provided with an electric air guide plate on both sides along its folding line, and a refrigeration device is arranged on the inner side of one of the second side panels, the method including: The system receives the type and weight of the refrigerated stacked goods to be transported inside the box, input by the user on the human-computer interaction panel, and receives the first distance value between the refrigerated stacked goods and the first distance sensor, the second distance value between the refrigerated stacked goods and the second distance sensor, and the third distance value between the refrigerated stacked goods and the third distance sensor. Subtract a preset distance threshold from the first distance value to obtain a first distance difference; subtract the preset distance threshold from the second distance value to obtain a second distance difference; and subtract the preset distance threshold from the third distance value to obtain a third distance difference. Determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively. Drive each first side panel according to the control drive motor to fold along the folding line to the smallest foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference. The foldable angle is the included angle between the two parts of the first side panel after folding. Determine the required refrigeration temperature for the refrigerated stacked goods based on their type. The type, weight, and refrigeration temperature of the refrigerated stacked goods are input into a pre-trained operating parameter determination model to determine multiple sets of operating parameters for the smart refrigerated container that maintain the refrigeration temperature at various positions on the refrigerated stacked goods. Each set of operating parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate towards the interior of the container and the horizontal direction. The operating parameter determination model is obtained by inputting multiple first training samples into a first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods, as well as the historical operating parameters of the smart refrigerated container that maintain the historical refrigeration temperature at various positions on the historical refrigerated stacked goods. The cooling power and air outlet speed in each set of operating parameters are input into a pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters; wherein, the power consumption determination model is obtained by inputting multiple second training samples into a second network to be trained, and each second training sample includes the historical cooling power and historical air outlet speed in the historical operating parameters of the cooling equipment, and the corresponding historical power consumption; Select the set of operating parameters corresponding to the lowest power consumption of the refrigeration equipment; The operation of the refrigeration equipment is controlled according to the refrigeration power, air outlet speed and air outlet direction of the selected set of operating parameters; and the rotation of each of the electric air guide vanes is controlled so that each of the electric air guide vanes reaches the angle between the extension direction toward the inside of the box and the horizontal direction in the selected operating parameters.

2. The method according to claim 1, characterized in that, Each of the first side panels is provided with a non-contact temperature sensor on both sides of its fold line, and a contact temperature sensor is provided at the geometric center of the housing. After controlling the operation of the refrigeration equipment according to its refrigeration power, air velocity, and air direction, and controlling the rotation of each of the electric air guide vanes to achieve a determined angle between the extension direction toward the interior of the housing and the horizontal direction, the method further includes: Receive the temperature of the refrigerated stacked goods collected by each of the non-contact temperature sensors and receive the temperature of the refrigerated stacked goods collected by the contact temperature sensor; Determine the actual average temperature of the multiple temperatures of the received refrigerated stacked goods; Determine the temperature difference between the actual average temperature and the required refrigeration temperature for the refrigerated stacked goods; When the temperature difference is greater than a set temperature threshold, the first network parameters of the model are determined by updating the running parameters according to the first reinforcement learning model until the temperature difference is lower than or equal to the set temperature threshold. The temperature difference is the reward of the first reinforcement learning model, and the lower the temperature difference, the higher the reward. The first network parameters of the model are updated to determine the action of the first reinforcement learning model, and the first network parameters are the state of the first reinforcement learning model.

3. The method according to claim 2, characterized in that, If the temperature difference is lower than or equal to a set temperature threshold, the method further includes: Determine the variance of multiple temperatures of the received refrigerated stacked goods; If the variance of the temperatures of multiple refrigerated stacked goods is greater than a preset variance threshold, the second network parameters of the model are updated according to the second reinforcement learning model until the variance of the temperatures of the multiple refrigerated stacked goods is less than or equal to the preset variance threshold. Here, the variance of the temperatures of the multiple refrigerated stacked goods is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods, the higher the reward. Updating the second network parameters of the model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

4. The method according to claim 1, characterized in that, Determining the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference includes: Based on the preset first mapping relationship, the foldable angles corresponding to the first distance difference and the second distance difference are retrieved from the preset database. Based on the preset second mapping relationship, the foldable angle corresponding to the third distance difference is searched from the preset database.

5. The method according to claim 1, characterized in that, The first network to be trained is a neural network.

6. A refrigerated container control device based on artificial intelligence, characterized in that, A main controller is configured in an intelligent refrigerated container. The intelligent refrigerated container includes a container body, which includes a top plate and a bottom plate arranged opposite each other, two first side panels arranged opposite each other, and two second side panels arranged opposite each other. Each first side panel is foldable towards the inside of the container body, and the fold line of each first side panel is parallel to the top or bottom plate of the container body. A first distance sensor and a second distance sensor are respectively arranged on the fold lines on the inner sides of the two first side panels. A third distance sensor is arranged on the inner side of the top plate. A human-machine interface panel is arranged on the outer side of the top plate. Each first side panel has an electric air guide plate arranged on both sides of its fold line. A refrigeration device is arranged on the inner side of one of the second side panels. The device includes: The data receiving unit is used to receive the type and weight of the refrigerated stacked goods to be transported in the box, which are input by the user on the human-machine interaction panel, and to receive the first distance value between the refrigerated stacked goods and the first distance sensor, the second distance value between the refrigerated stacked goods and the second distance sensor, and the third distance value between the refrigerated stacked goods and the third distance sensor. The distance difference determination unit is used to subtract a preset distance threshold from the first distance value to obtain a first distance difference, subtract the preset distance threshold from the second distance value to obtain a second distance difference, and subtract the preset distance threshold from the third distance value to obtain a third distance difference; A foldable angle determination unit is used to determine the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference, respectively. According to the control drive motor, each first side panel is driven to fold along the folding line to the minimum foldable angle among the foldable angles corresponding to the first distance difference, the second distance difference, and the third distance difference. The foldable angle is the included angle between the two parts of the first side panel after folding. A refrigeration temperature determination unit is used to determine the required refrigeration temperature of the refrigerated stacked goods based on the type of the refrigerated stacked goods. The operating parameter determination unit is used to input the type, weight, and refrigeration temperature of the refrigerated stacked goods into a pre-trained operating parameter determination model to determine multiple sets of operating parameters of the smart refrigerated container that maintain the refrigeration temperature at various positions on the refrigerated stacked goods. Each set of operating parameters includes the refrigeration power, air outlet speed, and air outlet direction of the refrigeration equipment, as well as the angle between the extension direction of each electric air guide plate towards the interior of the container and the horizontal direction. The operating parameter determination model is obtained by inputting multiple first training samples into a first network to be trained. Each first training sample includes the historical type, historical weight, and historical refrigeration temperature of the historical refrigerated stacked goods, as well as the historical operating parameters of the smart refrigerated container that maintain the historical refrigeration temperature at various positions on the historical refrigerated stacked goods. The power consumption determination unit is used to input the cooling power and air outlet speed in each set of operating parameters into a pre-trained power consumption determination model to determine the power consumption of the cooling equipment corresponding to each set of operating parameters. The power consumption determination model is obtained by inputting multiple second training samples into a second network to be trained. Each second training sample includes the historical cooling power and historical air outlet speed in the historical operating parameters of the cooling equipment, and the corresponding historical power consumption. The operating parameter selection unit is used to select the minimum power consumption of the refrigeration equipment, corresponding to a set of operating parameters; The control unit is used to control the operation of the refrigeration equipment according to the refrigeration power, air outlet speed and air outlet direction of the refrigeration equipment selected from a set of operating parameters; and to control the rotation of each of the electric air guide vanes so that each of the electric air guide vanes reaches the angle between the extension direction toward the inside of the box and the horizontal direction in the selected operating parameters.

7. The apparatus according to claim 6, characterized in that, Each of the first side panels has a non-contact temperature sensor on both sides of its fold line, while a contact temperature sensor is located at the geometric center of the housing. The data receiving unit is also used to receive the temperature of the refrigerated stacked goods collected by each of the non-contact temperature sensors and to receive the temperature of the refrigerated stacked goods collected by the contact temperature sensors. The device further includes: An average temperature determination unit is used to determine the actual average temperature of multiple temperatures of the received refrigerated stacked goods; The differential temperature determination unit is used to determine the temperature difference between the actual average temperature and the required refrigeration temperature of the refrigerated stacked goods. The parameter update unit is used to update the first network parameters of the running parameter determination model according to the first reinforcement learning model when the difference temperature is greater than a set temperature threshold, until the difference temperature is lower than or equal to the set temperature threshold, wherein the difference temperature is the reward of the first reinforcement learning model, and the lower the difference temperature, the higher the reward; updating the first network parameters of the running parameter determination model is the action of the first reinforcement learning model, and the first network parameters are the state of the first reinforcement learning model.

8. The apparatus according to claim 7, characterized in that, The device further includes: A temperature variance determination unit is used to determine the variance of multiple temperatures of the received refrigerated stacked goods; The parameter update unit is further configured to update the second network parameters of the running parameter determination model according to the second reinforcement learning model when the variance of the temperatures of the multiple refrigerated stacked goods is greater than a preset variance threshold, until the variance of the multiple temperatures of the refrigerated stacked goods is less than or equal to the preset variance threshold. The variance of the multiple temperatures of the refrigerated stacked goods is the reward of the second reinforcement learning model, and the smaller the variance of the temperatures of the multiple refrigerated stacked goods, the higher the reward. Updating the second network parameters of the running parameter determination model is the action of the second reinforcement learning model, and the second network parameters are the state of the second reinforcement learning model.

9. The apparatus according to claim 6, characterized in that, The foldable angle determination unit is specifically used to search for the foldable angles corresponding to the first distance difference and the second distance difference respectively from a preset database according to a preset first mapping relationship; and to search for the foldable angle corresponding to the third distance difference from a preset database according to a preset second mapping relationship.

10. The apparatus according to claim 6, characterized in that, The first network to be trained is a neural network.

Images