Control device, control method, and control program for a Baumkuhen firing machine, and a Baumkuhen firing machine

Abstract

To automatically control a baumkuchen baking machine so that each layer of baumkuchen rotating in an oven is baked to an appropriate degree. [Solution] The baking machine 1 includes an oven 2, a dough container 4, and a rotating roll 3. The control device includes a computer that controls the operation of moving the rotating roll 3, on which Baumkuchen dough is layered, from a dough application position to a baking position in the oven 2, and the operation of moving it from the baking position in the oven 2 to the dough application position. The computer is configured to execute an image acquisition process that acquires, from a camera 7, a group of multiple images capturing at least one revolution of the outer periphery of the rotating dough, and a determination process that determines the timing to move the rotating roll 3 from the baking position to the dough application position based on the browning of the outer periphery of the dough shown in the group of multiple images.

Description

Technical Field

[0001] The present invention relates to a control technology for a Baumkuchen baking machine.

Background Art

[0002] The Baumkuchen baking machine rotates a rotating shaft coated with Baumkuchen dough in an oven. As a result, the outer peripheral surface of the dough is baked substantially uniformly over the entire circumference. When the outer peripheral surface is baked, the Baumkuchen baking machine further applies dough onto it and rotates it in the oven. By repeating such application of the dough and baking of the outer peripheral surface of the dough by rotation in the oven, a Baumkuchen having a layer structure like tree rings is baked.

[0003] The baking condition of Baumkuchen is important because it has a great influence on the quality. Conventionally, a person with skilled technique has operated a Baumkuchen baking machine to bake Baumkuchen with appropriate baking conditions.

[0004] For example, Japanese Patent No. 6429138 (Patent Document 1) discloses a food manufacturing apparatus capable of automatically manufacturing a food for baking a dough of cereal powder such as takoyaki into a substantially spherical shape with high quality. This food manufacturing apparatus includes a heating plate provided with a recess into which the dough is injected, a robot arm, an imaging unit, and a control unit. The control unit divides the image data into a plurality of sections for each recess, and determines the degree of completion of the dough based on the shape and / or color of the dough analyzed from the image data of the dough for each section. The control unit changes the priority for each section. The control unit operates the robot arm along the changed priority to move the dough in contact with the surface and take out the dough.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] In the prior art, it is difficult to automatically determine the baking degree of each layer of the dough of the rotating Baumkuchen in the oven. The Baumkuchen baking machine stacks the dough on a rotating roll and bakes each layer while rotating the rotating roll. With such a configuration, it is important how to control the baking of each layer of the dough. In order to bake the Baumkuchen deliciously, it was necessary to control the Baumkuchen baking machine by a person with skilled techniques.

[0007] Therefore, the present application discloses a control device, a control method, a control program, and a Baumkuchen baking machine that can automatically control the Baumkuchen baking machine so that the baking degree of each layer of the rotating Baumkuchen in the oven becomes appropriate.

Means for Solving the Problems

[0008] The control device of the Baumkuchen baking machine according to an embodiment of the present invention is a control device of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between a baking position of the oven and a dough application position for applying the dough of the dough container to the dough of the rotating roll. The control device includes a computer that controls an operation of moving the rotating roll on which the dough of the Baumkuchen is stacked from the dough application position to the baking position of the oven and an operation of moving from the baking position of the oven to the dough application position. The computer acquires a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough rotating with the rotation of the rotating roll at the baking position of the oven from a camera that photographs a part of the outer peripheral surface of the dough of the Baumkuchen stacked on the rotating roll in an image acquisition process, and based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one full rotation of the outer peripheral surface of the dough at the baking position of the oven, is configured to execute a determination process for determining the timing of moving the rotating roll from the baking position of the oven to the dough application position.

Effects of the Invention

[0009] According to the present disclosure, the Baumkuchen baking machine can be automatically controlled so that the baking degree of each layer of the rotating Baumkuchen in the oven becomes appropriate.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Embodiments for Carrying Out the Invention

[0011] (Configuration 1) The control device of the Baumkuchen baking machine according to an embodiment of the present invention is a control device of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between a baking position in the oven and a dough application position for applying the dough in the dough container to the dough on the rotating roll. The control device includes a computer that controls an operation of moving the rotating roll on which the Baumkuchen dough is laminated from the dough application position to the baking position in the oven and an operation of moving the rotating roll from the baking position in the oven to the dough application position. The computer is configured to execute an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough rotating with the rotation of the rotating roll at the baking position in the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuchen dough laminated on the rotating roll, and a determination process of determining a timing for moving the rotating roll from the baking position in the oven to the dough application position based on the baked color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one full rotation of the outer peripheral surface of the dough at the baking position in the oven.

[0012] In the above configuration 1, the computer acquires a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the Baumkuchen dough rotating at the baking position in the oven from the camera. These plurality of image groups include information over the entire circumferential direction of the outer peripheral surface of the Baumkuchen dough baked in the oven. The computer determines a timing for moving the rotating roll from the baking position in the oven to the dough application position based on the baked color of the outer peripheral surface of the dough indicated by these plurality of image groups. Thereby, when the baking adjustment over the entire circumferential direction of the outer peripheral surface of the Baumkuchen baked in the oven becomes appropriate, the rotating roll can be moved from the baking position to the dough application position to apply the dough to the outer peripheral surface. That is, the baking time is controlled so that the degree of baking of each layer becomes appropriate. Therefore, the Baumkuchen baking machine can be automatically controlled so that the baking adjustment of each layer of the Baumkuchen rotating in the oven becomes appropriate.

[0013] In the above configuration 1, in the determination process, the computer may use a learned model obtained by machine learning to determine the timing of moving the rotating roll from the baking position of the oven to the dough application position. The learned model can be generated, for example, by machine learning using, as teacher data, an image of the outer peripheral surface of the past dough and a determination result of the baking degree (baking adjustment) for the image. The learned model can be, for example, data for inputting an image of the outer peripheral surface of the dough and outputting a determination result of baking adjustment based on the baking color indicated by the image.

[0014] In the determination process, the computer may use the learned model to determine the baking adjustment from a plurality of acquired image groups. For example, the computer can sequentially determine the baking adjustment of a plurality of image groups, and determine the time when the baking adjustment determined from the image satisfies a predetermined condition as the timing of moving the rotating roll from the baking position to the dough application position. By using the learned model, the baking adjustment can be determined in the same way as the determination result of the baking adjustment for past images. Thereby, for example, the determination of the baking adjustment by a person with skilled techniques can be reproduced.

[0015] (Configuration 2) In the above configuration 1, the computer further executes a determination estimation process for estimating the determination of the baking adjustment of the Baumkuhen dough by the operator based on the operation of the operator on the Baumkuhen baking machine, and a learning process for generating the learned model used in the determination process by machine learning using the estimated result of the operator's determination and a plurality of image groups obtained by photographing at least one round of the outer peripheral surface of the dough at the baking position of the oven during a period including the determination time as teacher data.

[0016] By performing machine learning using the judgment result of baking degree by the operator and a plurality of image groups taken during a period including the judgment time as teacher data, it is possible to learn the judgment of baking degree by the operator. By using the learned model obtained through this machine learning, it is possible to judge the baking degree for an image of the outer surface of the fabric, similar to the operator. As a result, based on an appropriate baking degree judgment, it is possible to determine the timing of the movement from the baking position to the fabric application position of the rotating roll on which the fabric is laminated.

[0017] In the judgment and estimation process, for example, the computer may estimate the judgment of the baking degree by the operator based on whether or not the operator performs an operation to move the rotating roll with the Baumkuchen fabric laminated from the baking position to the fabric application position. The operation by the operator to move the rotating roll with the Baumkuchen fabric laminated from the baking position to the fabric application position is performed when the operator determines that the baking degree of the fabric is appropriate. Therefore, the movement operation by the operator indicates the judgment result of the baking degree.

[0018] The machine learning may be, for example, deep learning using a neural network. In this case, the learned model may be, for example, a data set for inputting an image and outputting a judgment result of the baking degree (for example, a value indicating the baking degree, or whether the baking degree is appropriate or not). The data set includes, for example, parameters indicating the weights between the layers of the neural network and parameters of values adjusted by machine learning. Note that the machine learning is not limited to using a neural network. For example, a learned model may be generated by machine learning using regression analysis or a decision tree, etc. Examples of such machine learning include methods such as linear regression, support vector machine, support vector regression, Elastic Net, logistic regression, and random forest.

[0019] (Configuration 3) In the above-described configuration 1 or 2, when the computer acquires the plurality of images, the computer may further acquire at least one of the rotation speed of the Baumkuchen dough laminated on the rotating roll, the baking time of the outer surface of the Baumkuchen dough, or the temperature of the oven. In the determination process, the computer may make the determination based on at least one of the rotation speed, the baking time of the outer surface of the Baumkuchen dough, or the temperature of the oven, in addition to the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups. Thus, by using at least one of the rotation speed, the baking time, or the temperature, it becomes possible to make a determination considering the influence on the baking adjustment of at least one of the rotation speed, the baking time, or the temperature. As a result, it is possible to control the timing of moving the rotating roll from the baking position to the dough application position so that the baking adjustment becomes more appropriate.

[0020] The rotation speed may be, for example, the rotation speed of the rotating roll or the moving speed in the circumferential direction of the outer surface of the dough. The temperature of the oven may be, for example, the surface temperature of the outer surface of the dough, the temperature of the air in the oven, or the temperature of the heat source of the oven, etc. The baking time of the outer surface of the dough is the baking time of one layer of the dough. For example, the elapsed time from the time when the rotating roll moves from the dough application position to the baking position in the oven can be used as the baking time.

[0021] The Baumkuchen baking machine may include at least one of a rotation sensor that detects rotation around the axis of the rotating roll, a temperature sensor that detects the temperature of the oven, or a timer that measures the baking time. The computer may be configured to acquire at least one of the rotation speed detected by the rotation sensor, the temperature detected by the temperature sensor, or the baking time measured by the timer.

[0022] (Configuration 4) In the above-described configuration 2 or 3, in the learning process, the computer may further use at least one of the rotation speed of the Baumkuchen dough laminated on the rotating roll, the baking time of the outer surface of the Baumkuchen dough, or the temperature of the oven during the period including the time when the operation by the operator is determined, to generate the learned model. In this way, in addition to the image of the outer peripheral surface of the dough, by using at least one of the rotation speed, the baking time, or the temperature as teacher data, a learned model that enables more appropriate baking degree determination can be obtained.

[0023] (Configuration 5) In the determination process, the computer may acquire at least one of the circumferential movement speed of the outer peripheral surface of the Baumkuchen dough laminated on the rotating roll or the diameter of the outer periphery of the Baumkuchen dough laminated on the rotating roll. In the determination process, the computer may make the determination based on at least one of the acquired movement speed or the diameter, in addition to the baked color of the outer peripheral surface of the dough shown by the plurality of image groups.

[0024] When the number of layers of the dough on the rotating roll increases, the diameter of the dough also increases. When the diameter of the dough increases, even if the rotation speed of the rotating roll is the same, the circumferential movement speed of the outer peripheral surface of the dough becomes faster. By using the circumferential movement speed of the outer peripheral surface of the dough or the diameter of the outer periphery of the dough in the determination, it becomes possible to make a determination considering the difference in baking conditions due to the lamination of the dough. As a result, it is possible to control the timing of moving the rotating roll from the baking position to the dough application position so that the baking degree becomes more appropriate.

[0025] For example, the computer may calculate the circumferential movement speed of the outer peripheral surface of the dough based on the diameter of the outer periphery of the dough laminated on the rotating roll and the rotation speed of the rotating roll. The diameter of the outer periphery of the dough can be obtained, for example, by measuring the dimension of the dough in the radial direction in an image in which the entire radial direction of the dough laminated on the rotating roll is shown.

[0026] (Configuration 6) In the learning process, the computer may further use at least one of the circumferential movement speed of the outer peripheral surface of the Baumkuchen dough stacked on the rotating roll or the diameter of the outer periphery of the Baumkuchen dough during a period including the time when the operator makes the determination of baking degree to generate the learned model. Thereby, a learned model reflecting the difference in baking conditions due to the stacking of the dough can be generated.

[0027] A Baumkuchen baking machine including the control device of the above Configurations 1 to 6 is also included in the embodiments of the present invention.

[0028] (Configuration 7) The Baumkuchen baking machine according to an embodiment of the present invention includes an oven, a dough container, a rotating roll movable between the baking position of the oven and the dough container, a camera that photographs a part of the outer peripheral surface of the Baumkuchen dough stacked on the rotating roll, and a control device including a computer. The computer is a computer that controls an operation of moving the rotating roll on which the Baumkuchen dough is stacked from a dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven and an operation of moving from the baking position of the oven to the dough application position. The computer is configured to execute an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one round of the outer peripheral surface of the dough that rotates as the rotating roll rotates at the baking position of the oven from the camera, and a determination process of determining a timing for moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one round of the outer peripheral surface of the dough at the baking position of the oven.

[0029] In the above Baumkuchen baking machine, the camera may be installed so that a part in the axial direction of the outer peripheral surface of the dough stacked on the rotating roll is within the photographing range. Thereby, an image suitable for determining the baking degree of the outer peripheral surface of the rotating Baumkuchen dough can be obtained with a simple configuration.

[0030] The camera may be installed, for example, so as to capture an image in which the entire radial direction of the fabric laminated on the rotating roll at the baking position is shown. The computer may acquire a partial image of the fabric in the radial direction, which is cut out from the image captured by the camera. In this case, the computer executes the determination process using the partial image of the fabric in the radial direction. By using the partial image of the fabric in the radial direction, an image of a portion where the baking condition is well represented as color among the images of the entire radial direction of the fabric can be used for the determination. As a result, a more appropriate determination becomes possible.

[0031] One camera may be provided, or a plurality of cameras may be provided. The optical axis of the camera may be arranged to intersect the axial direction of the rotating roll. The camera may be arranged, for example, outside the oven to capture the outer surface of the fabric inside the oven through the window of the oven. Further, the camera and the rotating roll may be configured such that the relative position between the optical axis of the camera and the rotating roll at the baking position of the oven is fixed. Thereby, the imaging conditions of the fabric at the baking position by the camera can be fixed. Further, the relative position of the optical axis of the camera, in addition to the rotating roll at the baking position of the oven, and the heater of the oven may be fixed.

[0032] The Baumkuhen baking machine configured as described above may include a moving mechanism that moves the rotating roll between the baking position of the oven and the fabric container. The moving mechanism may include, for example, a support member that rotatably supports the axis of the rotating roll, and an actuator that moves the axis of the rotating roll supported by the support member. The support member may be, for example, a movable arm or a guide such as a rail. The actuator can be, for example, a motor, a hydraulic cylinder, or other power source.

[0033] One end of the movable arm may be pivotally supported by a pivot shaft so as to be rotatable with respect to the Baumhauer firing machine, and the other end may be configured to rotatably support the rotation axis of the rotating roll. In this case, the actuator may include a motor that rotates the movable arm about the pivot shaft. For example, a pair of movable arms that rotatably support both axial ends of the rotating roll may be provided.

[0034] Note that the operation of moving the rotating roll from the baking position of the oven to the dough application position by the moving mechanism may be an operation of moving at least one of the rotating roll and the dough container to bring the two relatively closer. For example, the rotating roll may be moved closer to the dough container, or the dough container may be moved closer to the rotating roll.

[0035] The moving mechanism is controlled by the computer. For example, the computer can control the movement of the rotating roll between the baking position and the dough application position of the oven by controlling the drive of the actuator provided in the moving mechanism.

[0036] The control method of the Baumkuchen baking machine according to the embodiment of the present invention is a control method of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between the baking position of the oven and the dough container. The control method includes an operation in which a computer moves the rotating roll on which the Baumkuchen dough is stacked from the dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven, and an operation of moving from the baking position of the oven to the dough application position. In the control step, the computer performs an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one circumference of the outer peripheral surface of the dough rotating along with the rotation of the rotating roll at the baking position of the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuchen dough stacked on the rotating roll, and a determination process of determining the timing of moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one circumference of the outer peripheral surface of the dough at the baking position of the oven.

[0037] The control method of the Baumkuchen baking machine according to the embodiment of the present invention is a control method of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between the baking position of the oven and the dough container. The control method includes a judgment estimation step in which a computer estimates the judgment of the baking degree of the Baumkuchen dough by the operator based on the operation of the operator on the Baumkuchen baking machine, and a learning step of generating a learned model used in the determination process by machine learning using the estimated result of the operator's judgment and a plurality of image groups obtained by photographing at least one circumference of the outer peripheral surface of the dough at the baking position of the oven during a period including the judgment time as teacher data. The learned model is data used in a determination process in which a computer determines the timing of moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one circumference of the outer peripheral surface of the dough at the baking position of the oven.

[0038] The control program of the Baumkuchen baking machine in the embodiment of the present invention is a control program of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between the baking position of the oven and the dough container. The control program causes a computer to perform an operation of moving the rotating roll on which the Baumkuchen dough is stacked from the dough application position where the dough of the dough container is applied to the rotating roll to the baking position of the oven, and an operation of moving from the baking position of the oven to the dough application position. The control process includes an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough rotating with the rotation of the rotating roll at the baking position of the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuchen dough stacked on the rotating roll, and a determination process of determining the timing of moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one full rotation of the outer peripheral surface of the dough at the baking position of the oven.

[0039] The control program of the Baumkuchen baking machine in the embodiment of the present invention is a control program of a Baumkuchen baking machine including an oven, a dough container, and a rotating roll movable between the baking position of the oven and the dough container. The control program causes a computer to execute a determination estimation process for estimating a determination of the baking degree of the Baumkuchen dough by the operator based on an operation of the operator on the Baumkuchen baking machine, a learning process for generating a learned model used in the determination process by machine learning using the result of the estimated determination of the operator and a plurality of image groups obtained by photographing at least one circumference of the outer peripheral surface of the dough at the baking position of the oven during a period including the time of the determination as teacher data. The learned model is data used in a determination process for determining a timing for moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one circumference of the outer peripheral surface of the dough at the baking position of the oven. [Embodiment] Hereinafter, embodiments will be described with reference to the drawings. The same or corresponding components in the drawings are denoted by the same reference numerals, and the same description will not be repeated. In order to make the description easier to understand, in the drawings referred to below, the configuration is shown in a simplified or schematic manner, or some of the component members are omitted.

[0040] (Example of the configuration of the Baumkuchen baking machine) FIG. 1 is a front view of the Baumkuchen baking machine in the present embodiment. FIG. 2 is a side view of the Baumkuchen baking machine shown in FIG. 1. The Baumkuchen baking machine 1 shown in FIGS. 1 and 2 includes an oven 2, a rotating roll 3 that rotates while laminating the Baumkuchen dough, a dough container 4 that stores the Baumkuchen dough before baking, a moving mechanism (5, 6) that moves the rotating roll 3 between the baking position of the oven and the dough application position, and a computer 8 that constitutes a control device that controls the operation of the Baumkuchen baking machine.

[0041] The Baumkuchen baking machine 1 further includes a camera 7, a lighting 72, and various sensors (not shown in FIG. 1). The various sensors can include, for example, at least one of a temperature sensor that measures the temperature of the oven, a rotation sensor that detects the rotation speed of the Baumkuchen dough stacked on the rotating roll 3, and a timer that measures the baking time of the Baumkuchen dough.

[0042] The camera 7 is disposed at a position where a part of the outer surface of the Baumkuchen dough W stacked on the rotating roll 3 at the baking position can be photographed. The optical axis of the camera 7 intersects the outer surface of the Baumkuchen dough W. The camera 7 is supported by a support member 71. The relative position between the optical axis of the camera 7 and the rotating roll 3 at the baking position is fixed by the support member 71. The lighting 72 irradiates light on the area included in the photographing range of the camera 7.

[0043] The camera 7 photographs a plurality of images of the outer surface during a period in which the rotating roll 3 on which the Baumkuchen dough W is stacked makes at least one full rotation. For example, the camera 7 photographs a moving image of the rotating Baumkuchen dough W. Thereby, a plurality of image groups photographing at least one full rotation of the outer peripheral surface of the Baumkuchen dough are obtained.

[0044] The oven 2 is a heating furnace, and a heater 22 is provided inside. The oven 2 has an openable and closable window 21. In front of the window 21, a dough container 4 is disposed. The dough container 4 is placed on a base 41.

[0045] In the example shown in FIGS. 1 and 2, the Baumkuchen dough stacked on the rotating roll 3 is disposed at the baking position inside the oven 2. Both ends of the rotating roll 3 are rotatably supported by a pair of arms 5. The rotating roll 3 is rotated by, for example, a motor (not shown). The computer 8 can control the rotation of the rotating roll 3 by controlling this motor.

[0046] A pair of arms 5 is rotatably attached to the Baumkuhen baking machine 1 about the pivot axis PA. An actuator 6 is connected to the arm 5. When the actuator 6 is driven, the arm 5 rotates. The actuator 6 is, for example, a motor. The drive of the actuator 6 is controlled by a computer 8. The computer 8 controls the rotation of the arm 5 by controlling the drive of the actuator 6. By controlling the rotation of the arm 5, the position of the rotating roll 3 is controlled. In this example, the arm 5 and the actuator 6 constitute a moving mechanism for the rotating roll 3.

[0047] The computer 8 moves the rotating roll 3 on which the Baumkuhen dough K is laminated between the dough application position and the baking position of the oven 2 by controlling the position of the rotating roll 3. The dough application position is the position where the dough in the dough container 4 is applied to the dough on the rotating roll 3. FIG. 3 is a diagram showing a state where the rotating roll 3 is at the dough application position. The dough application position is a position above the dough container 4. When the rotating roll 3 rotates at the dough application position, more dough is applied to the outer peripheral surface of the Baumkuhen dough K laminated on the rotating roll 3. The detection configuration of the position of the rotating roll 3 by the computer 8 is not particularly limited. For example, a position detection sensor for detecting the position of the rotating roll 3 or the arm 5 may be provided on the Baumkuhen baking machine 1. Alternatively, the computer 8 may be configured to detect the position of the rotating roll 3 based on the operation of the actuator 6.

[0048] The computer 8 applies one layer of the Baumkuhen dough K to the rotating roll 3 by rotating the rotating roll 3 at least one full turn at the dough application position. The computer 8 moves the rotating roll 3 on which the Baumkuhen dough K is applied from the dough application position to the baking position of the oven 2. Thereby, the baking of the applied one layer of dough is started.

[0049] The computer 8 acquires a plurality of image groups that photograph at least one full rotation of the outer peripheral surface of the Baumkuchen dough that rotates as the rotating roll 3 rotates at the baking position of the oven 2 from the camera 7. The computer 8 determines the baking degree based on the baking color of the outer surface of the Baumkuchen dough indicated by the plurality of image groups photographed by the camera 7. The computer 8 determines the timing to move the rotating roll 3 from the baking position of the oven 2 to the dough application position based on the determination result of the baking degree. Thereby, when it is determined that the baking degree is good, the rotating roll 3 can be moved from the baking position of the oven 2 to the dough application position. When the rotating roll 3 is moved from the baking position of the oven 2 to the dough application position, the baking is completed. That is, the computer 8 determines the baking degree of one layer of the Baumkuchen dough and controls the baking time of one layer of the dough so as to achieve an appropriate baking degree.

[0050] The computer 8 controls the position of the rotating roll 3 and repeats the operation of applying the Baumkuchen dough and baking it in the oven 2 a plurality of times. Thereby, the dough of a plurality of layers of Baumkuchen is baked. In the baking of each layer, the baking time is controlled so as to achieve an appropriate baking degree based on the image of the camera 7.

[0051] (Configuration example of the control device (computer)) FIG. 4 is a functional block diagram showing a configuration example of a control device configured by a computer 8. In the example shown in FIG. 4, the computer 8 includes a control unit 81, an image acquisition unit 82, a determination unit 83, a judgment estimation unit 84, and a learning unit 85. The control unit 81 controls a moving mechanism (arm 5 and actuator 6). Thereby, the control unit 81 moves the rotating roll 3 on which the Baumkuchen dough is laminated from the dough application position to the baking position of the oven 2 (operation to start baking), and the operation of moving from the baking position of the oven 2 to the dough application position (operation to end baking). Also, the control unit 81 controls the rotation of the rotating roll 3. In this way, the computer 8 controls the rotation of the rotating roll 3 around its axis and the movement in the direction perpendicular to the axis of the rotating roll 3. Note that the control unit 81 may control the heater 22 of the oven 2. That is, the computer 8 can also control the oven 2.

[0052] The image acquisition unit 82 acquires a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough that rotates as the rotating roll 3 rotates at the baking position of the oven 2 from the camera 7. The image acquisition unit 82 acquires, for example, a partial image group of the outer peripheral surface of the dough photographed at a predetermined period from the camera 7. Each of the acquired image groups may be an image obtained by cutting out a part of the radial direction from an image showing the entire radial direction of the dough. The determination unit 83 determines the timing to move the rotating roll 3 from the baking position of the oven 2 to the dough application position based on the baked color of the outer peripheral surface of the dough indicated by the plurality of image groups acquired by the image acquisition unit 82. The determination unit 83 can use a learned model in this determination process.

[0053] The determination unit 83 executes, for example, a process of using a learned model to input an image of the outer peripheral surface of the dough and output an evaluation value of baking degree. The learned model can be data generated by performing machine learning using the images of the outer peripheral surfaces of past doughs and the evaluation results as teacher data.

[0054] The determination and estimation unit 84 and the learning unit 85 execute machine learning using data indicating the firing operation performed by the Baumkuhen firing machine 1 and the result thereof, and generate a learned model. The determination and estimation unit 84 estimates the operator's determination of the baking degree of the Baumkuhen dough based on the operator's operation on the Baumkuhen firing machine 1. The learning unit 85 executes machine learning using the estimated result of the operator's determination and the image group of the outer peripheral surface of the dough at the time of the determination as teacher data. The image group serving as the teaching data can be a plurality of image groups obtained by photographing at least one round of the outer peripheral surface of the dough at the baking position of the oven 2 during the period including the time of the operator's determination. The learned model generated by machine learning is recorded in a recording device accessible by the computer 8.

[0055] The computer 8 is connected to an operation reception unit provided in the Baumkuhen firing machine 1. The operation reception unit receives an operation on the Baumkuhen firing machine 1 from the operator. The operation reception unit is composed of, for example, an operation panel 91 and operation elements such as operation buttons 92 shown in FIG. 1. The operation reception unit can receive operations from the operator, such as the operation of the rotating roll 3 and the operation of the temperature of the oven. As the operation of the rotating roll 3, the operation reception unit can receive from the operator an operation of moving the rotating roll 3 to the dough application position, an operation of moving the rotating roll 3 from the dough application position to the baking position of the oven 2 (firing start operation), an operation of moving the rotating roll 3 from the baking position to the dough application position (firing end operation), an operation of controlling the rotation speed of the rotating roll 3, and the like.

[0056] For example, when the rotating roll 3 on which the dough is laminated is rotating at the baking position of the oven 2 and the operator does not perform an operation of moving the rotating roll 3 from the baking position to the dough application position, the determination and estimation unit 84 can estimate that the operator has determined that the baking degree is insufficient, that is, the dough is not fully baked. In this case, the image of the outer peripheral surface of the dough photographed by the camera 7 during the rotation of the rotating roll 3 is recorded as teacher data in association with the result of the determination of underbaking.

[0057] Further, for example, when the operator moves the rotating roll 3 with the fabric laminated thereon from the baking position to the fabric application position while the rotating roll 3 is rotating at the baking position of the oven 2, the determination and estimation unit 84 can estimate that the operator has determined that the baking condition is good. In this case, during the period including the operation, the image of the outer peripheral surface of the fabric taken by the camera 7 while the rotating roll 3 rotates at least one turn is recorded as teaching data in association with the result of the determination of good baking.

[0058] In the example shown in FIG. 4, the computer 8 is connected to a temperature sensor, a rotation sensor, and a timer provided in the Baumkuhen baking machine. The determination unit 83 and the learning unit 85 can execute the above-described determination process or learning process using the information detected by at least one of these sensors. A specific example of the learning process will be described later.

[0059] The temperature sensor may be, for example, a thermometer that measures the temperature of the air inside the oven, a radiation thermometer that measures the temperature of the outer surface of the Baumkuhen, or one that detects the temperature from output values such as the temperature, current, and voltage of the heater 22.

[0060] The rotation sensor may include, for example, a detector that optically, magnetically, or mechanically detects the movement of a detected element that rotates together with the axis of the rotating roll 3. Alternatively, the rotation sensor may be configured to detect the rotation of the rotating roll 3 from the output value of a motor that controls the rotation of the rotating roll 3.

[0061] The timer may be, for example, a part of the computer 8. The timer can measure the baking time, for example, by measuring the elapsed time since the rotating roll 3 was placed in the baking position.

[0062] The computer 8 that constitutes the control device has a processor and a memory. The control device may be composed of two or more computers. The control process of the Baumkuchen baking machine by the computer 8 can be realized by the processor executing a predetermined program. A program for causing the computer 8 to execute the control process and a non-transitory recording medium on which the program is recorded are also included in the embodiments of the present invention. In the example shown in FIG. 1, the computer 8 is built into the Baumkuchen baking machine 1. On the other hand, the computer 8 may be communicably connected via a network to the parts of the baking machine including the oven 2, the rotating roll 3, and the moving mechanism of the Baumkuchen baking machine 1.

[0063] (Example of control process) FIG. 5 is a flowchart showing an example of the control process of the Baumkuchen baking machine 1 by the computer 8. In the example shown in FIG. 5, the computer 8 is an example in the case of causing the Baumkuchen baking machine 1 to perform an operation of applying and baking one layer of dough to the rotating roll 3. The computer 8 rotates the rotating roll 3 at the dough application position and applies one layer of dough to the outer peripheral surface of the dough laminated on the rotating roll 3 (S1). After the application, the computer 8 moves the rotating roll 3 from the dough application position to the baking position of the oven 2 (S2). Thereby, baking is started. In the baking process, at the baking position of the oven 2, the rotating roll 3 on which the Baumkuchen dough is laminated rotates.

[0064] The computer 8 acquires, from the camera 7, an image obtained by photographing the outer peripheral surface of the fabric that rotates as the rotating roll 3 rotates (S3). FIG. 6 is a diagram showing an example of an image obtained by photographing with the camera 7. In the example shown in FIG. 6, the camera 7 photographs an image of a part in the axial direction of the fabric K laminated on the rotating roll 3 and in a range where the entire radial direction is imaged. The computer 8 cuts out and acquires an image of the central portion A1 in the radial direction of the fabric K from this image. That is, an image of a region of the fabric that does not include the edge Ke in the radial direction of the fabric K shown in the image is cut out. Thereby, an image of a portion where the baking condition appears well on the outer surface of the fabric can be acquired. For example, the color of the fabric near the edge Ke in the radial direction of the fabric K shown in the image is easily affected by the light of the heater 22 or the like. By cutting out the image of the central portion A1 in the radial direction of the fabric K, an image of a portion less affected by the light of the heater 22 or the like can be acquired.

[0065] The computer 8 acquires sensor data in synchronization with the acquisition of the image (S4). The sensor data includes, for example, the surface temperature of the outer surface of the Baumkuchen detected by a temperature sensor (radiation thermometer). Also, as sensor data, the baking time measured by a timer is acquired. The baking time is the elapsed time since the start of baking.

[0066] The computer 8 determines a baking condition determination value based on the image acquired in S3 and the sensor data acquired in S4 using a learned model (S5). That is, the computer 8 determines the baking condition based on the baking color of the outer surface of the fabric shown in the image, the surface temperature of the fabric, and the baking time. The learned model can be data generated by deep learning using a neural network. That is, the computer 8 can determine the baking condition from the image and the sensor data using artificial intelligence technology using a neural network.

[0067] FIG. 7 is a diagram showing a configuration example of a neural network used for determination processing. In the example shown in FIG. 7, a portion of the Baumkuchen surface is cut out from a color camera image. The cut-out image is input to a convolutional neural network LS1. The convolutional neural network LS1 outputs 32 parameters (feature quantities). Also, as an example, the firing time and the value of the surface temperature of the Baumkuchen are input to a fully connected layer L1 with 5 units. This fully connected layer L1 outputs 5 parameters. The 32 parameters and the 5 parameters are concatenated and further input to a fully connected layer L2. The output from this fully connected layer L2 is input to the next fully connected layer L3, and a determination value (for example, 0 to 1) is output from this fully connected layer L3.

[0068] In the example shown in FIG. 7, the camera image is input to a convolutional neural network, and the sensor data is input to a fully connected layer. The image feature quantity obtained through the convolutional neural network and the parameters of the sensor data obtained through the fully connected layer are concatenated and further input to a fully connected layer. Through this fully connected layer and other fully connected layers, a determination value for baking degree is output. In this way, the machine learning model can be configured to include a convolutional neural network that converts the input image into feature quantities, a first input layer for inputting sensor data, a second input layer for inputting the combined parameters of the image feature quantity and the output of the input layer of the sensor data, and a layer for further converting the output of the second input layer. By using the configuration of the neural network that combines the image and the sensor data in this way, it is possible to determine the baking degree based on the image and the sensor data. Note that the configuration of the neural network used in the determination processing is not limited to the example shown in FIG. 7. For example, the number of layers of the fully connected layer and the number of parameters can be appropriately set as needed. Also, the sensor data input to the fully connected layer L1 is not limited to the example in FIG. 7. For example, at least one value of the rotation speed of the rotary roll 3, the temperature of the oven, or the firing time may be input to the fully connected layer L1.

[0069] When the baking determination value determined in S5 satisfies a predetermined condition (YES in S6), the computer 8 moves the rotating roll 3 from the baking position in the oven 2 to the dough application position and finishes baking. For example, when the determination value is equal to or greater than a predetermined threshold value, the computer 8 determines that the baking is completed and causes the transfer mechanism to perform an operation of taking out the Baumkuchen from the oven.

[0070] When the baking determination value determined in S5 does not satisfy a predetermined condition (NO in S6), the computer 8 returns to S3, acquires an image, and repeats the processes of S4 to S6. In the example shown in FIG. 5, the baking determination process is executed for each of a plurality of image groups. Thereby, for a plurality of image groups captured while the rotating roll 3 makes at least one full rotation, the baking determination and the determination process for finishing baking based on the determination are executed.

[0071] FIG. 8 is a diagram showing an example of an image group acquired by the computer 8 from the start to the end of baking. For example, after the start of baking, one image is captured by the camera 7 at a predetermined cycle (for example, every 0.5 seconds). The computer 8 sequentially acquires the images captured by the camera 7. In the example shown in FIG. 8, n images G1 to Gn are acquired. In the images G1 to G(n - 1), the baking determination value does not satisfy the condition, and in the nth image Gn, the baking determination value satisfies the condition. When the nth image Gn is acquired, the baking is finished.

[0072] In the above example, the baking determination and the baking end determination are executed for each image, but the baking and the baking end may be determined for a plurality of images.

[0073] Also, in the above example, firing time and temperature are acquired as sensor data. The computer 8 may acquire, as sensor data, the rotation speed of the Baumkuchen dough laminated on the rotating roll. In S4 of FIG. 5, the computer 8 can acquire the rotation speed of the rotating roll 3 detected by the rotation sensor. The computer 8 may determine baking degree based on the image and the rotation speed. Also, the computer 8 can acquire the circumferential movement speed of the outer peripheral surface of the Baumkuchen dough from the image of the camera 7 and the rotation speed.

[0074] For example, from the image shown in FIG. 6, the outer diameter D1 of the dough laminated on the rotating roll 3 can be measured. Using the diameter D1 obtained from the image and the rotation speed of the rotating roll 3 obtained from the rotation sensor, the circumferential movement speed of the outer peripheral surface of the dough can be calculated. The computer 8 may determine baking degree using the circumferential movement speed of the outer peripheral surface of the dough and the image. Thereby, it becomes possible to make a determination taking into account the change in the firing conditions due to the laminated amount of the dough. Also, the computer 8 may perform baking degree determination using the diameter D1 and the image. Also in this case, it becomes possible to make a determination taking into account the change in the firing conditions due to the laminated amount of the dough.

[0075] (Example of learning process) FIG. 9 is a flowchart showing an example of a process for collecting teacher data for learning processing based on the firing operation of the Baumkuchen baking machine 1. In the example shown in FIG. 9, it is an example in the case where the Baumkuchen baking machine 1 applies and bakes one layer of dough on the rotating roll 3 according to the operation of the operator. The Baumkuchen baking machine 1 rotates the rotating roll 3 at the dough application position according to the operation of the operator, and applies one layer of dough to the outer peripheral surface of the dough laminated on the rotating roll 3 (S11). After the application, the rotating roll 3 moves from the dough application position to the baking position of the oven 2 by the operation of the operator (S12). Thereby, baking is started. In the baking process, at the baking position of the oven 2, the rotating roll 3 with the Baumkuchen dough laminated thereon rotates.

[0076] The computer 8 acquires, from the camera 7, an image of the outer peripheral surface of the fabric that rotates as the rotary roll 3 rotates (S13). The image acquisition process can be executed in the same manner as S3 in FIG. 5, for example. The computer 8 acquires sensor data in synchronization with the acquisition of the image (S14). The sensor data is the data of the same sensor as the data acquired in S5 of FIG. 5.

[0077] The Baumkuhen baking machine 1 receives an operation to end baking during the baking of Baumkuhen (S15). Specifically, during the period when the rotary roll 3 with the fabric laminated thereon is rotating at the baking position in the oven 2, the operator can always perform an operation on the Baumkuhen baking machine 1 to move the rotary roll 3 from the baking position to the fabric application position. When the operator performs an operation to move the rotary roll 3 from the baking position to the fabric application position, the baking ends.

[0078] During baking, if there is no operation to end baking from the operator for a certain period (NO in S16), the computer 8 presumes that the operator has determined it to be underbaked. In this case, the computer 8 associates the underbaked determination result, the image acquired in S13, and the sensor data acquired in S14, and records them in the recording device as teaching data. After that, the computer 8 executes the image acquisition process of S13 again, and repeats the processes of S14 to S16. For example, the processes of S13 to S16 are executed for each of a plurality of image groups taken during the period when the rotary roll 3 rotates at least one full turn.

[0079] During baking, if there is an operation to end baking from the operator (YES in S16), the computer 8 presumes that the operator has determined it to be properly baked. In this case, the computer 8 associates the properly baked determination result, the image acquired in S13, and the sensor data acquired in S14, and records them in the recording device as teaching data. The operation to end baking is an operation to move the rotary roll 3 from the baking position to the fabric application position. When the rotary roll 3 moves from the baking position, the baking ends (S18).

[0080] By the process shown in FIG. 9, a plurality of image groups for at least one round of the outer surface of the fabric laminated and rotated on the rotary roll 3 are recorded in association with the determination results of baking degree. The learning unit 85 of the computer 8 executes machine learning using the determination results of baking degree associated with the plurality of image groups as teacher data to generate a learned model. The machine learning is not limited to this, but for example, it can be executed by deep learning using a neural network having the configuration shown in FIG. 7.

[0081] For example, a learning process example when using a neural network model will be described. The learning unit 85 collates the output (determination result) of the pre-learning model obtained by inputting the image of the teacher data and the sensor data to the pre-learning model, and the determination result of the teacher data, and adjusts the weighting between layers so that the degree of coincidence becomes higher. For example, in the case of the model having the configuration shown in FIG. 7, the image recorded as teacher data is input to the convolutional neural network LS1, and the sensor data (for example, baking time and surface temperature) recorded in association with the image is input to the fully connected layer L1. The output result (determination value) of the model for this input is collated with the determination result of the teacher data associated with the input image. The weighting parameters between the layers of the neural network are adjusted so that the degree of coincidence between the output of the model and the teacher data becomes higher. A learning process for adjusting the weighting parameters of the model is executed using the teacher data of a large number of images. The model whose weights are adjusted by the learning process becomes a learned model.

[0082] Note that the learning process of the computer 8 is not limited to machine learning using a neural network. For example, other machine learning using regression analysis or decision trees may be used.

[0083] For example, when a skilled craftsman operates the Baumkuchen baking machine 1 to bake Baumkuchen, the computer 8 can record, as teacher data, the determination result estimated from the operation, the image at the time of determination, and the sensor data in association with each other. By performing machine learning using the teacher data recorded for baking by such an operation of the craftsman, a learned model that enables control of the same baking time as that of this craftsman can be generated.

[0084] (Other Variations) In the above example, the control target based on the determination of the baking degree using the image of the camera 7 is the baking time (the timing of movement from the baking position of the rotating roll), but the control target of the computer 8 is not limited to this. For example, based on a plurality of image groups of at least one circumference of the outer peripheral surface of the Baumkuchen dough at the baking position of the oven photographed by the camera 7, at least one of the rotation speed of the rotating roll 3 or the temperature of the oven can be controlled. In this case, the computer 8 can determine the control of at least one of the rotation speed or the oven temperature based on the plurality of image groups using the learned model generated by machine learning. The learned model may be, for example, a data set for executing a process that takes an image of the outer peripheral surface of the dough as an input and outputs control information of at least one of the rotation speed or the oven temperature. The computer 8 can generate the above learning model using, as teacher data, at least one of the rotation speed or the oven temperature detected during baking by the operation of the operator's Baumkuchen baking machine and the image of the camera 7.

[0085] For example, the computer 8 may adjust the rotation speed of the rotating roll 3 according to the change in the diameter of the dough indicated by the image photographed by the camera 7 over time, or the change in the diameter in the axial direction (the uneven shape of the outer peripheral surface). Alternatively, the computer 8 may adjust the heating power of the heater 22 of the oven 2 according to the baking degree determined based on the image.

[0086] In addition to a plurality of image groups, the computer 8 may determine the control of at least one of the rotation speed, firing time, or oven temperature acquired during the acquisition of the image group. For this determination process, as a learned model, a data set for outputting control information may be used with at least one of the rotation speed, firing time, or oven temperature and an image of the outer surface of the fabric as inputs. Further, the computer 8 may generate such a learned model based on the operation of the operator's Baumkuhen firing machine. The computer 8 can detect, for example, at least one operation of the rotation speed and the oven temperature by the operator, and use the image group of the outer peripheral surface of the fabric taken during the period including the detection time of the operation and the detected operation as teacher data to generate a learned model. Examples of the operation to be detected include, for example, an operation of adjusting the rotation speed of the rotation roll 3 or an operation of adjusting the temperature of the oven 2.

[0087] Further, the sensor data used by the computer 8 for the determination process is not limited to the rotation speed, oven temperature, and firing time listed in the above examples. One or two of these may be used for the determination process. Also, sensor data other than these may be used for the determination process. For example, by executing the determination process using the rotation speed of the rotation roll 3 in addition to the image of the camera 7, it becomes possible to make a determination considering the change in the firing conditions due to the rotation speed. Also, by executing the determination process using the oven temperature in addition to the image of the camera 7, it becomes possible to make a determination considering the change in the firing conditions due to the oven temperature. Also, by executing the determination process using the firing time in addition to the image of the camera 7, it becomes possible to make a determination considering the change in the firing time.

[0088] Further, fabric information regarding the Baumkuchen fabric may be used in the determination process. The fabric information may include, for example, at least one of the temperature of the fabric in the fabric container before coating, the type of fabric (e.g., plain, chocolate, matcha, coffee, strawberry, etc., including the type by the contents of the fabric), the fabric weight, the fabric volume, or the fabric density. For example, when the computer 8 acquires a plurality of images of the outer surface of the fabric from the camera 7, the computer 8 may further acquire fabric information regarding the fabric. In this case, in the determination process, the computer 8 determines the timing to move the rotary roll 3 from the baking position in the oven to the fabric coating position based on the acquired fabric information in addition to the baking color of the outer peripheral surface of the fabric indicated by the plurality of image groups.

[0089] A learned model may be used for this determination process. The learning model can be, for example, data for inputting an image of the outer peripheral surface of the fabric and outputting a determination result of baking adjustment based on the baking color indicated by the image. The computer 8 uses, as teacher data, the result of the operator's baking adjustment determination estimated based on the operator's operation on the Baumkuchen baking machine, the fabric information, and a plurality of image groups that capture at least one round of the outer peripheral surface of the fabric at the baking position in the oven during a period including the determination time, and can generate a learned model through machine learning.

[0090] The Baumkuchen baking machine 1 may be provided with an input unit or sensor for acquiring fabric information. The computer 8 can acquire fabric information from the input unit or sensor. For example, at least one of a weight sensor for measuring the weight of the fabric in the fabric container 4, a fabric temperature sensor for measuring the temperature of the fabric in the fabric container 4, and a volume sensor for measuring the volume of the fabric in the fabric container 4 may be provided in the Baumkuchen baking machine 1. Alternatively, an input unit, which is an interface for receiving an input of fabric information from the operator, may be provided in the Baumkuchen baking machine 1.

[0091] As described above, embodiments of the present invention have been described, but the present invention is not limited to the above embodiments.

Explanation of Reference Numerals

[0092] 1: Baumkuchen baking machine, 2: Oven, 3: Rotating roll, 4: Dough container, 5: Arm, 6: Actuator, 7: Camera

Claims

1. A control device for a Baumkuhen baking machine, comprising an oven, a dough container, and a rotating roll movable between a baking position of the oven and the dough container, a computer for controlling an operation of moving the rotating roll on which the Baumkuhen dough is laminated from a dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven, and an operation of moving from the baking position of the oven to the dough application position, wherein the computer, a process of moving the rotating roll on which the Baumkuhen dough is laminated from a dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven, an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one circumference of the outer peripheral surface of the dough rotating with the rotation of the rotating roll at the baking position of the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuhen dough laminated on the rotating roll, a determination process of determining a timing for moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one circumference of the outer peripheral surface of the dough at the baking position of the oven, a process of moving the rotating roll from the baking position of the oven to the dough application position at the determined timing, rotating it at the dough application position, and applying one layer of dough, is configured to repeatedly execute the above a plurality of times, in the determination process, the computer determines a timing for moving the rotating roll from the baking position of the oven to the dough application position using a learned model obtained by machine learning, and the learned model is data for inputting an image of the outer peripheral surface of the dough and outputting a determination result of baking adjustment based on the baking color indicated by the image, The learned model is a learned model generated by machine learning using, as teacher data, the result of the operator's baking adjustment determination estimated based on the operator's operation on the Baumkuhen baking machine and a plurality of image groups obtained by photographing at least one circumference of the outer peripheral surface of the dough at the baking position of the oven during a period including the determination time. A control device for a Baumkuhen baking machine.

2. The computer, When acquiring the plurality of image groups, at least one of the rotation speed of the Baumkuchen dough laminated on the rotating roll, the baking time of the outer surface of the Baumkuchen dough, or the temperature of the oven is further acquired. The control device of the Baumkuchen baking machine according to claim 1, wherein, in the determination process, the determination is made based on at least one of the acquired rotation speed, the baking time of the outer surface of the Baumkuchen dough, or the temperature of the oven, in addition to the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups.

3. In the determination process, the computer acquires at least one of the circumferential movement speed of the outer peripheral surface of the Baumkuchen dough laminated on the rotating roll or the diameter of the outer peripheral surface of the Baumkuchen dough laminated on the rotating roll. The control device of the Baumkuchen baking machine according to claim 1 or 2, wherein, in the determination process, the determination is made based on at least one of the acquired movement speed or the diameter, in addition to the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups.

4. An oven, A dough container, A rotating roll movable between the baking position of the oven and the dough container, A camera that photographs a part of the outer peripheral surface of the Baumkuchen dough laminated on the rotating roll, A control device including a computer, The computer, Is a computer that controls the operation of moving the rotating roll on which the Baumkuchen dough is laminated from the dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven and the operation of moving from the baking position of the oven to the dough application position. The computer, A process of moving the rotating roll on which the Baumkuchen dough is laminated from the dough application position where the dough in the dough container is applied to the dough on the rotating roll to the baking position of the oven, An image acquisition process of acquiring, from the camera, a plurality of image groups that photograph at least one round of the outer peripheral surface of the dough that rotates as the rotating roll rotates at the baking position of the oven, A determination process of determining the timing of moving the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one round of the outer peripheral surface of the dough at the baking position of the oven. At the determined time, move the rotating roll from the baking position in the oven to the dough application position, rotate it at the dough application position, and perform a process of applying dough for one layer. It is configured to repeatedly execute the process a plurality of times. In the determination process, the computer determines the timing to move the rotating roll from the baking position in the oven to the dough application position by using a learned model obtained by machine learning. The learned model is data for inputting an image of the outer peripheral surface of the dough and outputting a determination result of baking adjustment based on the baking color indicated by the image. The learned model is a learned model generated by machine learning using, as teacher data, the result of the operator's determination of baking adjustment estimated based on the operator's operation on the Baumkuhen baking machine and a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough at the baking position in the oven during a period including the determination time. The Baumkuhen baking machine.

5. A control method for a Baumkuhen baking machine including an oven, a dough container, and a rotating roll movable between the baking position in the oven and the dough container, wherein a computer has a control step of controlling an operation of moving the rotating roll on which the Baumkuhen dough is stacked from the dough application position for applying the dough in the dough container to the dough on the rotating roll to the baking position in the oven and an operation of moving it from the baking position in the oven to the dough application position. The computer is in the control step, a process of moving the rotating roll on which the Baumkuhen dough is stacked from the dough application position for applying the dough in the dough container to the dough on the rotating roll to the baking position in the oven, an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough that rotates as the rotating roll rotates at the baking position in the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuhen dough stacked on the rotating roll, a determination process of determining the timing to move the rotating roll from the baking position in the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one full rotation of the outer peripheral surface of the dough at the baking position in the oven. At the determined time, move the rotating roll from the baking position of the oven to the dough application position, rotate it at the dough application position, and perform a process of applying one layer of dough. Execute it repeatedly a plurality of times. In the determination process, the computer uses a learned model obtained by machine learning to determine the time to move the rotating roll from the baking position of the oven to the dough application position. The learned model is data for inputting an image of the outer peripheral surface of the dough and outputting a determination result of baking adjustment based on the baking color indicated by the image. The learned model is a learned model generated by machine learning using, as teacher data, the result of the operator's baking adjustment determination estimated based on the operator's operation on the Baumkuhen baking machine and a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough at the baking position of the oven during the period including the determination time. A control method for a Baumkuhen baking machine.

6. A control program for a Baumkuhen baking machine including an oven, a dough container, and a rotating roll movable between the baking position of the oven and the dough container, causing a computer to execute a control process for controlling an operation of moving the rotating roll on which the Baumkuhen dough is stacked from the dough application position for applying the dough of the dough container to the rotating roll to the baking position of the oven and an operation of moving from the baking position of the oven to the dough application position, The control process is a process of moving the rotating roll on which the Baumkuhen dough is stacked from the dough application position for applying the dough of the dough container to the dough of the rotating roll to the baking position of the oven, an image acquisition process of acquiring a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough that rotates as the rotating roll rotates at the baking position of the oven from a camera that photographs a part of the outer peripheral surface of the Baumkuhen dough stacked on the rotating roll, a determination process of determining the time to move the rotating roll from the baking position of the oven to the dough application position based on the baking color of the outer peripheral surface of the dough indicated by the plurality of image groups of at least one full rotation of the outer peripheral surface of the dough at the baking position of the oven, At the determined time, move the rotating roll from the baking position of the oven to the dough application position, rotate it at the dough application position, and perform a process of applying one layer of dough. including a process that is repeatedly executed multiple times, In the determination process, the computer uses a learned model obtained by machine learning to determine the timing of moving the rotating roll from the baking position of the oven to the dough application position. The learned model is data for inputting an image of the outer peripheral surface of the dough and outputting a determination result of baking adjustment based on the baking color indicated by the image. The learned model is a control program for a Baumkuhen baking machine, which is a learned model generated by machine learning using, as teacher data, the result of the operator's baking adjustment determination estimated based on the operator's operation on the Baumkuhen baking machine and a plurality of image groups obtained by photographing at least one full rotation of the outer peripheral surface of the dough at the baking position of the oven during a period including the determination time.

Images