Information processing device, state determination method, control decision method, state determination program, and control decision program

Abstract

To enable an appropriate treatment according to a state of a content inside a hopper.SOLUTION: An information processing device (1) includes: a movement state identification unit (101) for identifying a movement state of a content positioned above a hopper among contents accommodated inside the hopper; a discharge state identification unit (102) for identifying a discharge state of the content from the hopper; and a state determination unit (105) for determining a state of the content inside the hopper based on the movement state and the discharge state.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device and the like that determines the state of contents inside a hopper. [Background technology]

[0002] A typical waste incineration facility is equipped with a funnel-shaped device called a hopper. Waste stored in a storage facility called a waste pit is picked up by a crane or other device and thrown into the hopper, from which it is sent to an incinerator for incineration. In such incineration facilities, waste thrown into the hopper can sometimes become clogged in the hopper in the form of a bridge, a phenomenon known as bridging.

[0003] When a bridge occurs, the waste above the bridge remains in the same position, so the height of the waste accumulated in the hopper (waste level) remains high. Generally, a drop in the waste level is used as a trigger for dumping waste into the hopper, so when a bridge occurs, no new waste is dumped into the hopper. On the other hand, the waste below the bridge is sent to the incinerator and incinerated one by one, so if the bridge is left unattended, the amount of waste in the incinerator will decrease, and if it is left unattended further, there will be no waste to burn in the incinerator.

[0004] When the amount of waste in an incinerator decreases or runs out, the temperature inside the incinerator drops, making it necessary to heat it with a burner or the like, and in some cases, it may become necessary to shut down the incinerator. For example, Patent Document 1 below is an example of a technology for avoiding such a situation. Patent Document 1 describes a method for detecting a bridge based on a hopper level that is periodically measured. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 10-238735 Summary of the Invention [Problem to be solved by the invention]

[0006] However, it is difficult to stably and accurately measure the hopper level. This will be explained with reference to Fig. 9. Fig. 9 is a diagram showing states (a) to (c) of hopper A. Fig. 9 also shows a diagram showing the hopper A as viewed from above and a cross-sectional view of the hopper A as viewed from the side for each of states (a) to (c). Fig. 9 also shows a dust feeder B that discharges the waste contained in hopper A to the incinerator.

[0007] In state (a) shown in Figure 9, garbage is caught on the inclined funnel-shaped surface of the hopper. In state (b), garbage is clogged at the bottom end (reduced diameter part) of the funnel-shaped part of the hopper. And in state (c), garbage is clogged near the discharge outlet of hopper A. In these states, the state of garbage inside the hopper is not reflected in the hopper level.

[0008] As described above, it is difficult to stably and accurately measure the hopper level, and the hopper level may not reflect the state of the waste inside the hopper. This makes it difficult to take appropriate measures according to the state of the waste inside the hopper. This problem is not limited to hoppers installed in waste incinerators, but is a common problem that occurs in hoppers for any purpose that store any type of waste.

[0009] An object of one aspect of the present invention is to provide an information processing device etc. that enables appropriate measures to be taken in accordance with the state of contents inside a hopper. [Means for solving the problem]

[0010] In order to solve the above problems, an information processing device according to one embodiment of the present invention includes a movement state identification unit that identifies the movement state of contents located at the top of a hopper among the contents contained inside the hopper, a discharge state identification unit that identifies the discharge state of the contents from the hopper, and a state determination unit that determines the state of the contents inside the hopper based on the movement state and the discharge state.

[0011] In order to solve the above problems, an information processing device according to another aspect of the present invention includes a movement state identification unit that identifies the movement state of contents located at the top of a hopper among the contents contained inside the hopper, a discharge state identification unit that identifies the discharge state of the contents from the hopper, and a control determination unit that determines control to maintain or improve the state of the contents inside the hopper based on the movement state and the discharge state.

[0012] In order to solve the above problems, a status determination method according to one embodiment of the present invention is a status determination method executed by one or more information processing devices, and includes a movement state determination step of determining a movement state of contents located at the top of a hopper among contents contained inside the hopper, a discharge state determination step of determining a discharge state of the contents from the hopper, and a status determination step of determining the status of the contents inside the hopper based on the movement state and the discharge state.

[0013] In order to solve the above problems, a control decision method according to one embodiment of the present invention is a control decision method executed by one or more information processing devices, and includes a movement state identification step of identifying a movement state of contents located at the upper part of a hopper among contents contained inside the hopper, a discharge state identification step of identifying a discharge state of the contents from the hopper, and a control decision step of determining control to maintain or improve the state of the contents inside the hopper based on the movement state and the discharge state. Effect of the Invention

[0014] According to one aspect of the present invention, it is possible to take appropriate measures depending on the state of the contents inside the hopper. [Brief description of the drawings]

[0015] [Figure 1] 1 is a block diagram showing an example of a configuration of a main part of an information processing device according to a first embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing an overview of a management system including the information processing device. [Diagram 3] FIG. 13 shows an example of a hopper image and motion estimation results for the hopper image. [Figure 4] FIG. 13 is a diagram showing an example of division of a hopper image. [Diagram 5] 11A and 11B are diagrams showing an example of a discharge image and the movement of garbage shown in the discharge image. [Figure 6] FIG. 13 is a diagram illustrating an example of a state prediction model. [Figure 7] 4 is a flowchart illustrating an example of a process executed by the information processing device. [Figure 8] FIG. 11 is a block diagram showing an example of a configuration of a main part of an information processing device according to a second embodiment of the present invention. [Figure 9] FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] [Embodiment 1] (System Overview) An overview of the management system 5 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an overview of the management system 5. The management system 5 is a system for managing hoppers, and includes an information processing device 1, an imaging device 2, and an imaging device 3.

[0017] The object of management by the management system 5 in Fig. 2 is hopper A. Hopper A is a garbage hopper that stores garbage input from its top and discharges the stored garbage from its bottom. Hopper A is provided with a dust feeder B, which is a discharge device for discharging the garbage in hopper A to an incinerator. Hopper A is also provided with a bridge release device C for eliminating bridges.

[0018] The objects managed by the management system 5 are not limited to garbage hoppers. The management system 5 can manage any hopper that stores any contents and discharges the contents by any discharge device. For example, when the management system 5 is used in a garbage incineration plant, it can also manage an incineration ash hopper instead of or in addition to the garbage hopper. Of course, it is possible to manage any hopper installed outside of a garbage incineration plant. Therefore, in the following explanation, "garbage" can be read as any stored object, and "dust feeding device" can be read as any discharge device.

[0019] The imaging device 2 is disposed above the hopper A so as to overlook the inlet of the hopper A, and images the surface of the waste. Meanwhile, the imaging device 3 is disposed near the discharge outlet of the hopper A, and images the state in which the waste is discharged from the hopper A by the dust feeder B. Since the area near the discharge outlet is generally dark, it is preferable to use an IR (Infrared Radiation) camera or the like, which is capable of taking images in dark places, as the imaging device 3.

[0020] The information processing device 1 uses the images captured by the photographing device 2 and the photographing device 3 to determine the state of the contents, i.e., the garbage, inside the hopper A. This makes it possible to take appropriate measures according to the state of the garbage inside the hopper A. For example, when the information processing device 1 determines that a bridge has occurred, it can control the state bridge release device C to automatically release the bridge.

[0021] (Configuration of information processing device) The configuration of the information processing device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of a main configuration of the information processing device 1. As shown in the figure, the information processing device 1 includes a control unit 10 that controls each unit of the information processing device 1, and a storage unit 11 that stores various data used by the information processing device 1. The information processing device 1 also includes a communication unit 12 that allows the information processing device 1 to communicate with other devices, an input unit 13 that accepts input of various data to the information processing device 1, and an output unit 14 that allows the information processing device 1 to output various data.

[0022] The control unit 10 also includes a movement state specifying unit 101, a discharge state specifying unit 102, a hopper level estimating unit 103, a hopper level correcting unit 104, a state determining unit 105, a control deciding unit 106, a device control unit 107, a target content detecting unit 108, and a cause estimating unit 109. The memory unit 11 also stores a hopper image 111, a state prediction model 113, and a discharge image 112.

[0023] The hopper level estimation unit 103 and the hopper level correction unit 104 will be described later in "Hopper level estimation". The control decision unit 106 and the device control unit 107 will be described later in "Device control". The target content detection unit 108 and the cause estimation unit 109 will be described later in "Estimation of the cause of blockage".

[0024] Hopper image 111 is an image of waste located at the top of a hopper. For example, an image captured by imaging device 2 in Fig. 2 can be hopper image 111. As will be described in detail later, hopper image 111 is used to identify the movement state of waste located at the top of the hopper. For this reason, memory unit 11 stores a plurality of hopper images 111 in chronological order, which are images of waste located at the top of the hopper.

[0025] The discharge image 112 is an image of the garbage discharged from the hopper by the dust feeding device. For example, an image captured by the image capturing device 3 in Fig. 2 can be the discharge image 112. Although details will be described later, the discharge image 112 is used to identify the discharge state of the garbage from the hopper. For this reason, the memory unit 11 stores a plurality of discharge images 112 in chronological order, which are images of the garbage discharged from the hopper.

[0026] State prediction model 113 models the relationship between the state of waste movement above the hopper, the state of waste discharged from the hopper, and the state of waste inside the hopper. As will be described in detail later, by using state prediction model 113, the state of waste inside the hopper can be predicted.

[0027] The movement state specifying unit 101 specifies the movement state of the waste located at the top of the hopper among the waste stored inside the hopper. The discharge state specifying unit 102 specifies the discharge state of the waste from the hopper. The state determination unit 105 then determines the state of the waste inside the hopper based on the movement state specified by the movement state specifying unit 101 and the discharge state specified by the discharge state specifying unit 102.

[0028] The information processing device 1, having the above-mentioned configuration, can accurately determine the state of the waste inside the hopper, thereby making it possible to take appropriate measures according to the state of the waste inside the hopper.

[0029] The above configuration allows the state of the garbage inside the hopper to be accurately determined because the movement and discharge state of the garbage in the upper part of the hopper change depending on the state of the garbage inside the hopper. For example, when a bridge occurs inside the hopper, the movement speed and amount of the garbage in the upper part of the hopper decrease, while the discharge state does not change for a while after the bridge occurs, or if it does change, the change is small. Therefore, the above configuration allows the occurrence of a bridge to be accurately detected, and measures to quickly eliminate the bridge can be taken.

[0030] (How to identify the moving state) A method for identifying the state of movement of garbage above a hopper using a hopper image 111 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of a hopper image and a motion estimation result for the hopper image. Hopper images 111a and 111b shown in Fig. 3 are images in time series. In other words, the hopper shown in these images is in the state shown in hopper image 111a, and then in the state shown in hopper image 111b a predetermined time later.

[0031] The motion estimation result 31 shown in Fig. 3 shows the movement of the garbage by the motion vector (arrow) from the time when the hopper image 111a was captured to the time when the hopper image 111b was captured. The figure also shows an enlarged view 311 of a rectangular portion of the motion estimation result 31. It can be seen from the enlarged view 311 that the garbage is moving downward.

[0032] The vector indicating the movement of the garbage can be calculated using, for example, a block matching algorithm. In this case, the movement state identification unit 101 divides each of the hopper images 111a and 111b into a plurality of blocks and identifies the corresponding blocks. Then, the movement state identification unit 101 calculates a motion vector indicating the amount of movement and the direction of movement of the corresponding blocks from the difference in position of the corresponding blocks. The movement state identification unit 101 performs such processing for each block, and calculates a motion vector indicating the amount of movement and the direction of movement of each block. The motion vector calculated in this way is displayed as an arrow at the position of each block, which is the motion estimation result 31 in FIG. 3.

[0033] The motion vector calculated from the hopper images 111a and 111b as described above indicates the movement state of the garbage in the upper part of the hopper. Therefore, the process of specifying the movement state of the garbage in the upper part of the hopper executed by the movement state specifying unit 101 may be the process of calculating this motion vector.

[0034] Furthermore, the movement state identification unit 101 may calculate another index value indicating the movement state of the garbage in the upper part of the hopper from the calculated motion vector. For example, the movement state identification unit 101 may calculate the swallowing speed at which the garbage is swallowed into the inside of the hopper as information indicating the movement state of the garbage in the upper part of the hopper. The swallowing speed calculated here is based on the hopper image 111 and is therefore a volume-based speed, that is, indicates the volume of the garbage swallowed into the inside of the hopper in a given time.

[0035] In this case, if the relationship between the motion vector and the swallowing speed is modeled in advance, the moving state identification unit 101 can calculate the swallowing speed from the motion vector using the model. This model may be, for example, a linear model such as a regression model, or a nonlinear model such as a neural network model.

[0036] For example, when using hopper images 111a and 111b, the movement state determination unit 101 may calculate the swallowing speed from the amount of movement of the garbage during the shooting time interval of those images. In this case, the movement state determination unit 101 may calculate the swallowing speed from the magnitude (absolute value) of the motion vector.

[0037] Depending on the shape of the hopper, the tendency of the amount of garbage movement may vary depending on the area on the hopper image 111. For example, garbage moves relatively more near the outer periphery of the hopper, whereas the amount of garbage movement is relatively smaller near the center of the hopper. To be precise, garbage moves toward the deeper part of the hopper near the center of the hopper, so the apparent amount of movement on the hopper image 111 is smaller.

[0038] For this reason, the movement state identification unit 101 may set multiple areas on the hopper image 111, calculate an index value for each area indicating the amount of garbage movement in that area, and calculate the swallowing speed by combining the index values ​​of each area.

[0039] For example, as shown in Fig. 4, the portion of the hopper image 111 in which the hopper is shown may be divided into nine areas in a grid pattern. Fig. 4 is a diagram showing an example of dividing the hopper image. In Fig. 4, the nine areas are indicated by dashed lines. By calculating an index value for each area, it is possible to take into account the tendency of the amount of waste movement for each area, and therefore it is possible to calculate the swallowing speed with greater accuracy than when the area is not divided.

[0040] The method of identifying the movement state of the waste located at the top of the hopper is not limited to the above example. For example, the movement state may be identified without using the hopper image 111. In this case, a laser scanner such as LiDIA may be used instead of the photographing device 2. The movement state identifying unit 101 may then identify the surface shape and position of the waste at the top of the hopper from the output value of the laser scanner, and identify the movement state from changes in the surface shape and position.

[0041] (How to identify the discharge status) A method for identifying the discharge state of garbage from a hopper using discharge image 112 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of a discharge image and the movement of garbage captured in the discharge image. More specifically, Fig. 5 shows the discharge image 112, as well as the movement of garbage in a portion of the discharge image 112 (enclosed in a dashed frame) (enlarged image 51 in the same figure). The enlarged image 51 is generated by combining a plurality of discharge images 112 captured in chronological order.

[0042] In the enlarged image 51, the contours of the pile of garbage discharged from the hopper are indicated by L1 to L3. The garbage in the hopper is pushed out from inside the hopper to outside the hopper successively by the reciprocating motion of the dust feeder, so such contours can be observed in the discharge image 112. The position of such contours moves each time new garbage is pushed out of the hopper by the dust feeder.

[0043] Enlarged image 51 in Figure 5 shows that a contour that appears at position L1 in discharge image 112 taken at a certain time appears at position L2 in discharge image 112 taken next, and at position L3 in discharge image 112 taken after that.

[0044] The discharge state identifying unit 102 may calculate the amount of movement of the pile of garbage shown in the discharge image 112 as information indicating the discharge state. For example, the discharge state identifying unit 102 may detect the above-mentioned contour line from each of the multiple time-series discharge images 112 by image analysis, a machine learning model, or the like, and calculate the movement distance of the detected contour line.

[0045] Furthermore, the discharge status determination unit 102 may calculate another index value indicating the waste discharge status from the calculated moving distance. For example, the discharge status determination unit 102 may calculate the discharge speed at which waste is discharged from the hopper as information indicating the discharge status. The discharge speed calculated here is based on the discharge image 112 and is therefore a volume-based speed, that is, indicates the volume of waste discharged from the hopper in a given time.

[0046] When calculating the discharge rate from the moving distance, the relationship between the moving distance and the discharge rate may be modeled in advance. This allows the discharge state determination unit 102 to calculate the discharge rate from the moving distance using the model. This model may be, for example, a linear model such as a regression model, or a nonlinear model such as a neural network model.

[0047] (Method of determining the condition of garbage) As described above, the state determination unit 105 determines the state of the garbage inside the hopper based on the movement state identified by the movement state identification unit 101 and the discharge state identified by the discharge state identification unit 102. This determination can be made using, for example, a state prediction model 113 as shown in Fig. 6. Fig. 6 is a diagram showing an example of the state prediction model 113.

[0048] The state prediction model 113 shown in Fig. 6 expresses the relationship between the intake speed and the discharge speed in the hopper in various states by line segments (a) to (d). In Fig. 6, (a) to (d) are straight lines, but they may be curved lines.

[0049] More specifically, line (a) shows the relationship between the intake speed and discharge speed when an avalanche occurs, where garbage avalanches into a cavity that occurs inside the hopper. In line (a), the intake speed is greater than the discharge speed. In other words, line (a) is characterized by the fact that the discharge amount is small compared to the intake amount. The same relationship applies when garbage adheres to the wall of the hopper.

[0050] Line (b) shows the relationship between the intake rate and discharge rate in a hopper under normal conditions. In line (b), the intake rate and discharge rate are equal. In other words, the characteristic of line (b) is that the same amount of material is discharged as is taken in.

[0051] Line (c) shows the relationship between the intake rate and discharge rate in a hopper with a slight blockage (bridge). In line (c), the discharge rate is slightly greater than the intake rate. In other words, the discharge rate is slightly greater than the intake amount, which is a characteristic of line (c).

[0052] Line (d) shows the relationship between the intake rate and discharge rate in a hopper where a blockage (bridge) has occurred. In line (d), the discharge rate is greater than the intake rate. In other words, the characteristic of line (d) is that the discharge rate is large compared to the intake amount.

[0053] In this way, the state of the garbage inside the hopper is reflected in the relationship between the intake speed and the discharge speed. Therefore, the state determination unit 105 can determine the state of the garbage inside the hopper based on which line segment the relationship between the intake speed and the discharge speed is closest to.

[0054] For example, the state determination unit 105 may determine the state using a state prediction model 113 indicating the slopes of the line segments (a) to (d), i.e., the ratios of the ingestion speed and the excretion speed in the four states of avalanche, normal, mild obstruction, and obstruction. In this case, the movement state specification unit 101 calculates the ingestion speed, and the excretion state specification unit 102 calculates the excretion speed. Then, the state determination unit 105 calculates the ratio of the calculated ingestion speed and the excretion speed, and determines which of the ratios corresponding to the four states indicated in the state prediction model 113 the calculated ratio is closest to.

[0055] In addition, when the line segments (a) to (d) are curved, the state determination unit 105 may determine the state based on which of the curves (a) to (d) the pattern of change over time of the ingestion rate calculated by the movement state determination unit 101 and the excretion rate calculated by the excretion state determination unit 102 is closest to.

[0056] The state determination unit 105 may also make a determination based only on the line segment (b). In this case, the state determination unit 105 may determine that an avalanche may occur (or has occurred) if the ratio of the calculated intake speed to the discharge speed is greater than the slope of the line segment (b). The state determination unit 105 may determine that an avalanche may occur (or has occurred) if the ratio of the calculated intake speed to the discharge speed is smaller than the slope of the line segment (b).

[0057] Also, a state prediction model 113 showing the difference between the intake speed and the discharge speed in each state of the hopper may be used. In this case, the state determination unit 105 calculates the difference between the calculated intake speed and the discharge speed, and determines which of the differences corresponding to the states shown in the state prediction model 113 the calculated difference is closest to.

[0058] As described above, state determination unit 105 may determine the state of the waste inside the hopper using state prediction model 113, which models the relationship between the state of waste movement in the upper part of the hopper, the state of waste discharged from the hopper, and the state of waste inside the hopper. Since the state of waste movement and discharged in the upper part of the hopper change depending on the state of waste inside the hopper, this configuration makes it possible to accurately determine the state of waste inside the hopper.

[0059] As described above, the movement state specifying unit 101 may calculate the intake speed at which the garbage is taken into the inside of the hopper as information indicating the movement state of the garbage at the top of the hopper. The discharge state specifying unit 102 may calculate the discharge speed of the garbage from the hopper as information indicating the discharge state. The state determining unit 105 may then determine the state of the garbage inside the hopper from the ratio or difference between the intake speed and the discharge speed.

[0060] As described above, in a normal state where there is no blockage inside the hopper, the speed at which the garbage in the upper part of the hopper is sucked into the inside and the speed at which the garbage is discharged are roughly equal. On the other hand, when a blockage occurs inside the hopper, a difference occurs between the speed at which the garbage is sucked in and the speed at which the garbage is discharged. Therefore, with the above configuration, the state of the contents inside the hopper can be accurately determined.

[0061] A similar state prediction model can be generated using index values ​​other than the intake speed and discharge speed. For example, the sum of absolute values ​​of motion vectors generated from the time series of hopper images 111 may be used instead of the intake speed, and the movement distance of the outline of the garbage pile generated from the time series of discharge images 112 may be used instead of the discharge speed.

[0062] Furthermore, the state prediction model 113 is not limited to the above examples as long as it is a model of the relationship between the state of movement of the waste above the hopper, the state of waste discharged from the hopper, and the state of the waste inside the hopper. For example, the state prediction model 113 may be a machine-learned model generated by machine learning the above relationships.

[0063] (Confidence of the judgement result) The state determination unit 105 may calculate an index (certainty) indicating the likelihood of the determination result. For example, the state determination unit 105 may calculate the confidence of the determination result based on the degree of discrepancy between the ratio or difference between the ingestion rate and the excretion rate indicated in the state prediction model 113 and the calculated ratio or difference between the ingestion rate and the excretion rate.

[0064] For example, in the state prediction model 113, when the ratio of the swallowing rate to the excretion rate in a normal state is 1, the ratio of the swallowing rate to the excretion rate calculated by the state determination unit 105 is assumed to be 1.1. Since there is a difference of 0.1, i.e., 10%, between these ratios, in this case, the state determination unit 105 may set the confidence level of this determination result to 90%.

[0065] (Correction of state prediction model) Since the waste inside the hopper is compressed and its volume changes, the relationship between the state of waste movement above the hopper, the state of waste discharged from the hopper, and the state of waste inside the hopper also changes depending on the type of waste stored in the hopper. Therefore, the state prediction model 113 may be corrected according to the properties of the waste put into the hopper.

[0066] Examples of the garbage properties include the garbage type, size, shape, granularity, weight, and apparent specific gravity. The garbage properties such as the garbage type, size, shape, and granularity can be identified, for example, by analyzing the hopper image 111 or a property determination model that has been machine-learned. The weight of the garbage can be measured by the crane that dumped the garbage into the hopper, and the apparent specific gravity can be calculated by dividing the weight by the volume of the garbage dumped (the volume that can be picked up by the crane).

[0067] The correction method is not particularly limited as long as it is a method that reflects the properties of the garbage put in to the state prediction model 113. For example, a model may be created of the relationship between the properties of the garbage put in during a specified period and the correction amount when making a prediction for a hopper that contains the garbage put in during that period. In this case, the state determination unit 105 may identify the properties of the garbage put in during the specified period before making the determination, and correct the state prediction model 113 using the model.

[0068] For example, the average apparent specific gravity of garbage input during a predetermined period before making a judgment affects the degree to which the garbage in the pit is compressed, and if the degree to which the garbage is compressed changes, the ratio of the discharge amount (volume) to the intake amount (volume) also changes. Therefore, the state judgment unit 105 may correct the ratio of the intake speed and the discharge speed corresponding to each state shown in the state prediction model 113 based on the average apparent specific gravity of the garbage input during a predetermined period before making a judgment. The correction may be performed by the state judgment unit 105, or a separate processing unit that performs the correction may be provided.

[0069] As described above, the state determination unit 105 may determine the state of the waste inside the hopper using the state prediction model 113 corrected according to the properties of the waste put into the hopper during a predetermined period before determining the state of the waste inside the hopper. This makes it possible to accurately determine the state of the waste inside the hopper, taking into account the properties of the waste put into the hopper.

[0070] (Determining the state of waste taking into account actual and set waste volumes) As described above, the discharge state determination unit 102 may calculate the amount of waste discharged from the hopper as information indicating the discharge state from the time-series discharge images 112 of the waste discharged by the dust feeder. This amount of waste indicates the amount of waste actually discharged from the hopper, and is therefore hereinafter referred to as the actual discharge amount.

[0071] The discharge state determination unit 102 may also determine a set value for the discharge amount of the dust feeding device. This set value is hereinafter referred to as a set discharge amount. In this case, the state determination unit 105 may determine the state of the garbage inside the hopper based on the movement state determined by the movement state determination unit 101 and the actual discharge amount and set discharge amount determined by the discharge state determination unit 102.

[0072] When the dust feeder is operating smoothly, the set discharge amount and the actual discharge amount will be roughly the same, but if a problem occurs with the dust feeder or depending on the characteristics of the waste discharged by the dust feeder, there may be a difference between the set discharge amount and the actual discharge amount.

[0073] According to the above configuration, the set discharge amount and the actual discharge amount are calculated as information showing the discharge state of the contents, and the state of the garbage inside the hopper is judged based on both of them. Therefore, the state of the garbage inside the hopper can be accurately judged taking into account the state of the dust feeder and the properties of the garbage to be discharged.

[0074] (Another example of how to determine the condition of garbage) The state determination unit 105 may determine the state of the waste inside the hopper without using the state prediction model 113. For example, the state determination unit 105 may determine the state of the waste based on the degree of deviation between the movement state specified by the movement state specification unit 101 and the discharge state specified by the discharge state specification unit 102.

[0075] In this case, the moving state identifying unit 101 may calculate the moving speed as the information indicating the moving state, and the discharge state identifying unit 102 may calculate the discharge speed as the information indicating the discharge state. Then, the state determining unit 105 may calculate the difference or ratio between the calculated moving speed and the discharge speed as the deviation degree, and may determine that the calculated deviation degree is normal if it is within a predetermined range, and that the calculated deviation degree is abnormal if it is outside the predetermined range.

[0076] If the moving speed when it is determined that there is an abnormality is greater than the discharge speed, the state determination unit 105 may determine that (1) an avalanche has already occurred, (2) that there is a high possibility that an avalanche will occur in the near future, or (3) that garbage is attached to the wall surface of the hopper. Also, if the moving speed when it is determined that there is an abnormality is smaller than the discharge speed, the state determination unit 105 may determine that a blockage (bridge) has occurred or will occur.

[0077] Furthermore, when it is determined that garbage is attached to the wall surface of the hopper, the state determination unit 105 may also determine the location of the garbage. For example, when the hopper image 111 is divided into a plurality of areas as shown in Fig. 4 and the movement state is specified, the state determination unit 105 may determine the area where the movement state is worse than normal as the location where garbage is attached. Note that the area where the movement state is worse than normal can be determined from the result of the specification by the movement state specification unit 101 (for example, the sum of the magnitudes of the motion vectors of each area or the movement speed).

[0078] In this way, when the state determination unit 105 determines that garbage is attached to the wall surface of the hopper, the state determination unit 105 may determine the location of the garbage attachment based on the movement state identified by the movement state identification unit 101. This makes it possible to quickly take appropriate measures such as removing the garbage from that location.

[0079] (Device Control) The control decision unit 106 and the device control unit 107 shown in Fig. 1 will be described. The control decision unit 106 decides on control for maintaining or improving the state of the waste inside the hopper according to the determination result of the state determination unit 105. Then, the device control unit 107 causes a predetermined device to execute the control decided by the control decision unit 106.

[0080] The information processing device 1 is provided with a control decision unit 106, and thus can automatically decide control for maintaining or improving the state of the waste inside the hopper, which is control according to the determination result of the state determination unit 105. And, the information processing device 1 is provided with a device control unit 107, and thus can maintain or improve the state of the waste inside the hopper by automatic control without user intervention.

[0081] For example, when the state determination unit 105 determines that the hopper is in a blocked state, if the hopper is provided with a bridge canceling device (see C in FIG. 2), the control decision unit 106 may decide to control the bridge canceling device to execute a bridge canceling operation. In this case, the device control unit 107 controls the bridge canceling device to execute the bridge canceling operation.

[0082] The bridge canceling device may be controlled by the control decision unit 106 directly communicating with the bridge canceling device, or may be controlled via another device. Also, the device control unit 107 may be omitted, in which case the control decision unit 106 may be configured to notify the user of the determined control content, and the user who receives the notification may operate the bridge canceling device to cancel the bridge.

[0083] Of course, the contents of the control for maintaining or improving the state of the garbage inside the hopper and the device for executing the control are arbitrary and are not limited to the above examples. For example, it is also possible to maintain or improve the state of the garbage inside the hopper by controlling the operation of the dust feeder. It is also possible to maintain or improve the state of the garbage inside the hopper by controlling a crane that puts garbage into the hopper and adjusting the amount and properties of the garbage put into the hopper. In this way, if a control for maintaining or improving the state of the garbage inside the hopper is associated with each state determined by the state determination unit 105, the control determination unit 106 can determine the control according to the association.

[0084] (Hopper level estimate) Because the garbage in the hopper is subject to compression by garbage put in later, the apparent specific gravity of the garbage varies depending on the position in the hopper. For this reason, it is difficult to accurately calculate the volume of the garbage in the hopper or the height of the garbage piled up in the hopper only from the weight of the garbage put into the hopper by the crane. In addition, it is difficult to measure the weight of the garbage discharged from the hopper, so it is also difficult to calculate the weight of the garbage in the hopper.

[0085] Therefore, the hopper level estimation unit 103 estimates the hopper level by the method described below. Then, the hopper level correction unit 104 corrects the hopper level estimated by the hopper level estimation unit 103. Here, the "hopper level" means the amount of garbage contained in the hopper. The hopper level may be, for example, the weight or volume of the garbage contained in the hopper, or the height of the garbage contained in the hopper. By estimating and correcting the hopper level, the amount and condition of the garbage in the hopper can be accurately grasped.

[0086] The hopper level can be estimated by a model that uses various information related to the hopper level as explanatory variables. This model may be, for example, a model of the three-dimensional waste flow in the hopper, that is, what kind of waste enters the hopper and how that waste is discharged.

[0087] Examples of the explanatory variables include the capacity of the hopper, the apparent specific gravity of the garbage put into the hopper (weight / volume of the garbage put in), the amount of garbage discharged from the hopper, the amount of garbage moving (amount ingested) at the top of the hopper, and the amount of garbage put into the hopper. The amount of garbage moving and the amount of garbage discharged can be determined by the movement state determination unit 101 and the discharge state determination unit 102, respectively. The weight of the put-in garbage can be measured by providing a weighing scale on the crane. The volume of the put-in garbage can be determined from the change in the surface shape of the garbage at the position in the garbage pit where the garbage was grabbed.

[0088] For example, the hopper level estimation unit 103 may estimate the hopper level using the following relational expression. Note that the terms in parentheses on the right-hand side are variables of the function f. There is a correlation between the rate of change of the hopper level and the volume of waste dumped into the hopper, and there is also a correlation between the rate of change of the hopper level and the amount of waste discharged from the hopper (dust feeding speed). In addition, the increase in the hopper level can be estimated from the weight and apparent specific gravity of the waste dumped into the hopper. Therefore, when the quality of the waste contained in the hopper and the waste dumped into it fluctuates within a certain range, the hopper level (or the average value of the fluctuation trend of the hopper level) can be estimated using this function f.

[0089] (Hopper level) = f (hopper capacity, apparent specific gravity, discharge amount, input amount, adjustment coefficient) However, as described above, the garbage in the hopper is compressed and the volume changes, so it is difficult to accurately estimate the hopper level. Therefore, the information processing device 1 is provided with a hopper level correction unit 104. As described above, the hopper level correction unit 104 corrects the hopper level estimated by the hopper level estimation unit 103.

[0090] For the correction of the hopper level, for example, a model obtained by machine learning the relationship between the error of the hopper level estimated by the hopper level estimating unit 103 and various information related to the error may be used. In this case, the hopper level correcting unit 104 inputs various information related to the error into the model to predict the error, and corrects the hopper level estimated by the hopper level estimating unit 103 so as to cancel the error. Examples of information related to the error include characteristics specific to the hopper and information indicating the properties of the waste put into the hopper.

[0091] In order to calculate the above error, various objects can be used for comparison with the hopper level estimated by the hopper level estimation unit 103. For example, the above error may be the difference between the hopper level measured by a sensor such as an ultrasonic level meter, or the hopper level calculated by analyzing a hopper image 111 captured inside the hopper, and the hopper level estimated by the hopper level estimation unit 103. Note that since the height of the garbage may vary along the inner wall of the hopper, the average height of the garbage along the inner wall may be used as the hopper level.

[0092] Also, for example, the hopper level correction unit 104 may statistically predict what kind of error will occur in the hopper level estimated by the hopper level estimation unit 103, based on the tendency of errors in the hopper level estimated by the hopper level estimation unit 103 in past cases. In this case, the hopper level correction unit 104 may correct the hopper level estimated by the hopper level estimation unit 103 so as to cancel the predicted error.

[0093] In addition, the hopper level estimation unit 103 can also estimate the time it takes for garbage placed in the hopper to be discharged from the hopper and the time it takes for the garbage to be incinerated, using a method similar to that used for estimating the hopper level described above.

[0094] As described above, the information processing device 1 may include a hopper level estimation unit 103 (amount estimation unit) that estimates the amount of garbage contained in the hopper based on the discharge state identified by the discharge state identification unit 102 and the amount of garbage thrown into the hopper. Since the amount of garbage thrown into the hopper and the discharge state of the garbage from the hopper are highly correlated with the amount of garbage contained in the hopper, the above configuration makes it possible to estimate the amount of garbage contained in the hopper. Furthermore, if it is desired to further improve the estimation accuracy, correction can be performed by the hopper level correction unit 104 as described above.

[0095] (Estimation of cause of blockage) The target object detection unit 108 and the cause estimation unit 109 shown in Fig. 1 will be described. The target object detection unit 108 detects a specific target object that may cause a blockage in the hopper. Examples of the target object include garbage that is likely to get tangled, such as string-like garbage or garbage with a long, thin shape like a branch, garbage that is large in size, garbage with a light apparent specific gravity, and garbage that is highly elastic or sticky.

[0096] The shape, color, size, etc. of the garbage can be identified by, for example, analyzing the hopper image 111. The type and properties of the garbage can be identified using a model constructed by machine learning using images of garbage with known types and properties as training data. The target item detection unit 108 may perform detection using a method appropriate for the target item.

[0097] If the state determination unit 105 determines that the blockage state is present within a predetermined period of time after the target item detection unit 108 detects the target item, the cause estimation unit 109 estimates that the cause of the blockage state is the target item. The predetermined period of time may be appropriately set based on the standard time it takes for waste thrown into the hopper to cause a blockage in the hopper.

[0098] For states other than blockage, the cause of the state can be estimated by the same process. In this case, a target object that may be the cause of the state of the hopper to be estimated may be detected. For example, when estimating the cause of a wall adhesion state in which garbage adheres to the wall of the hopper, the target object detection unit 108 may detect highly sticky garbage as the target object.

[0099] As described above, the information processing device 1 may include a target item detection unit 108 that detects a predetermined target item that may cause the hopper to enter a predetermined state, and a cause estimation unit 109 that, if the state determination unit 105 determines that the state of the hopper is a predetermined state within a predetermined period after the target item detection unit 108 detects the target item, estimates that the cause of the state is the target item. This makes it possible to quickly apply a countermeasure according to the estimated target waste to eliminate the predetermined state. It also makes it possible to take measures such as preventing the same target waste from being put into the hopper next time onwards.

[0100] (Processing flow) The flow of the process (state determination method) executed by the information processing device 1 will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the process executed by the information processing device 1. Note that this process is performed continuously during the operation of the waste incineration facility.

[0101] In S11 (movement state identification step), the movement state identification unit 101 identifies the movement state of the garbage in the upper part of the hopper among the garbage contained inside the hopper. For example, the movement state identification unit 101 may identify the movement state based on a plurality of hopper images 111 in time series taken from above the hopper.

[0102] In S12 (discharge state identification step), the discharge state identification unit 102 identifies the discharge state of the waste from the hopper. For example, the discharge state identification unit 102 may identify the discharge state based on a plurality of discharge images 112 in time series that capture the waste discharged by the dust feeder.

[0103] In S13 (state determination step), the state determination unit 105 determines the state of the waste inside the hopper based on the movement state specified in S11 and the discharge state specified in S12. The state determination unit 105 may perform the determination in S13 using, for example, a state prediction model 113 as described with reference to FIG.

[0104] In S14, the control decision unit 106 decides whether or not to control the equipment in the waste incineration facility based on the judgment result of S13. For example, the control decision unit 106 decides to control when a state other than a normal state (for example, an abnormal state such as a blockage) is judged in S13. If the judgment in S14 is YES, the process proceeds to S15. On the other hand, if the judgment in S14 is NO, the process returns to S11.

[0105] In S15, the control decision unit 106 decides on control to maintain or improve the state of the waste inside the hopper depending on the result of the determination in S13. For example, if a blocked state is determined in S13, the control decision unit 106 may decide on control to improve the blocked state or to prevent it from worsening (for example, executing a bridge release operation).

[0106] In S16, the device control unit 107 causes a predetermined device to execute the control determined in S15. For example, if the control to execute the bridge canceling operation is determined in S15, the device control unit 107 controls the bridge canceling device to execute the bridge canceling operation. After this, the process returns to S11.

[0107] As described above, the state determination method according to this embodiment includes a movement state determination step (S11) for determining the movement state of the waste located at the top of the hopper among the waste stored inside the hopper, a discharge state determination step (S12) for determining the discharge state of the waste from the hopper, and a state determination step (S13) for determining the state of the waste inside the hopper based on the determined movement state and discharge state. This makes it possible to take appropriate measures according to the state of the waste inside the hopper.

[0108] [Embodiment 2] Other embodiments of the present invention will be described below. For ease of explanation, the same reference numerals are given to members having the same functions as those described in the above embodiment, and the description thereof will not be repeated.

[0109] The configuration of the information processing device 1A according to this embodiment will be described with reference to Fig. 8. Fig. 8 is a block diagram showing an example of the main configuration of the information processing device 1A according to the second embodiment of the present invention. The information processing device 1A differs from the information processing device 1 shown in Fig. 1 in that it does not include the state determination unit 105, that it includes a control decision unit 106A instead of the control decision unit 106, and that a control prediction model 113A is stored in the storage unit 11 instead of the state prediction model 113. Note that although Fig. 8 does not show the hopper level estimation unit 103, the hopper level correction unit 104, the target content detection unit 108, and the cause estimation unit 109, the information processing device 1A may include these configurations.

[0110] The control determination unit 106A determines control for maintaining or improving the state of the waste inside the hopper based on the movement state identified by the movement state identification unit 101 and the discharge state identified by the discharge state identification unit 102. The control determination unit 106A can determine the control using, for example, a control prediction model 113A.

[0111] The control prediction model 113A is a model of the relationship between the movement state of the garbage in the upper part of the hopper, the discharge state of the garbage from the hopper, and the control to be executed during the movement state and the discharge state. This control is for maintaining or improving the state of the garbage inside the hopper. Therefore, by using the control prediction model 113A, the control determination unit 106A can determine the control for maintaining or improving the state of the garbage inside the hopper from the movement state specified by the movement state specification unit 101 and the discharge state specified by the discharge state specification unit 102.

[0112] The control prediction model 113A may be constructed by machine learning or by a method utilizing statistics, and may be table data or the like that associates the garbage movement state at the top of the hopper and the garbage discharge state from the hopper with the control that should be executed during that movement state and that discharge state.

[0113] For example, the control prediction model 113A may be a model in which control to be executed is associated with control to eliminate avalanche when the waste discharge speed is slower than the waste intake speed. Since avalanche occurs when waste is excessively supplied on the drying stage, the control to eliminate avalanche may be, for example, control to slow down the dust supply speed.

[0114] The control prediction model 113A may be a model in which control to be executed is associated with control to eliminate blockage when the waste discharge speed is faster than the waste intake speed. Whether the waste discharge speed is faster or slower than the waste intake speed may be determined by comparing the difference or ratio between the intake speed and the discharge speed with a threshold value, etc. Examples of control to eliminate blockage include operating the bridge release device C, or loading new waste into the hopper to apply a load from above the blockage.

[0115] In addition, the control prediction model 113A may be a trained model that predicts the control to be performed from explanatory variables indicating the state of waste movement above the hopper and explanatory variables indicating the state of waste discharged from the hopper. Such a model can be constructed based on cases in which the state of waste inside the hopper was maintained or improved by control performed on the hopper.

[0116] As described above, the information processing device 1A includes the movement state specifying unit 101 and the discharge state specifying unit 102, similar to the information processing device 1. The information processing device 1A also includes a control determination unit 106A that determines control for maintaining or improving the state of the garbage inside the hopper, based on the movement state specified by the movement state specifying unit 101 and the discharge state specified by the discharge state specifying unit 102.

[0117] As described above, the state of movement of the waste in the upper part of the hopper and the state of discharge of the waste from the hopper change according to the state of the waste inside the hopper. Therefore, according to the above-mentioned configuration in which control is determined based on the state of movement and the state of discharge, appropriate control according to the state of the waste inside the hopper can be performed.

[0118] The control decision method according to this embodiment has the same flow as that shown in FIG. 7. The difference from FIG. 7 is that the control decision unit 106A performs processing to decide control in S13, and the processing of S15 is omitted. That is, the control decision method according to this embodiment includes a movement state specifying step of specifying the movement state of the waste located at the top of the hopper, a discharge state specifying step of specifying the discharge state of the waste from the hopper, and a control decision step of determining control for maintaining or improving the state of the waste inside the hopper based on the movement state and the discharge state. According to this control decision method, appropriate control can be performed according to the state of the waste inside the hopper.

[0119] [Modifications] The execution subject of each process described in each of the above-mentioned embodiments is arbitrary and is not limited to the above-mentioned examples. In other words, as long as each process described in each of the above-mentioned embodiments can be executed, the devices constituting the management system 5 can be changed as appropriate. For example, among the processes shown in FIG. 7, the processes of S11 and S12 may be executed by one information processing device, and the process of S13 may be executed by another information processing device. In this way, the execution subject of each process described in each of the above-mentioned embodiments may be one information processing device or multiple information processing devices.

[0120] [Software implementation example] The functions of the information processing devices 1 and 1A (hereinafter referred to as the "devices") can be realized by a program for causing a computer to function as the device, and a program (state determination program / control decision program) for causing a computer to function as each control block of the device (particularly each part included in the control unit 10 or 10A).

[0121] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program to realize each function described in each of the above embodiments.

[0122] The program may be non-transitory and may be recorded in one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be provided to the device via any wired or wireless transmission medium.

[0123] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0124] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0125] 1, 1A Information processing device 101 Moving state determination unit 102 Discharge status identification unit 103 Hopper level estimation unit (capacity estimation unit) 105 Status determination unit 106, 106A Control decision unit 108 Target Content Detection Unit 109 Cause estimation section 113 State Prediction Model

Claims

1. a movement state determination unit that determines a movement state of an item located at an upper portion of the hopper among the items contained inside the hopper; A discharge state determination unit that determines a discharge state of the stored contents from the hopper; a state determination unit that determines a state of the contents inside the hopper based on the moving state and the discharging state, The state determination unit is an information processing device that determines the state of the contents inside the hopper using a state prediction model that models the relationship between the movement state of the contents in the upper part of the hopper and the discharge state of the contents from the hopper, and the state of the contents inside the hopper.

2. The information processing device according to claim 1 , wherein the state determination unit determines the state of the contents inside the hopper using the state prediction model corrected according to the properties of the contents placed in the hopper during a predetermined period prior to making the determination.

3. A movement state determination unit that determines a movement state of an object located at an upper portion of the hopper among the objects contained inside the hopper; A discharge state determination unit that determines a discharge state of the stored contents from the hopper; a state determination unit that determines a state of the contents inside the hopper based on the moving state and the discharging state, The movement state determination unit calculates a speed at which the contents are swallowed into the interior of the hopper as information indicating a movement state of the contents in the upper part of the hopper, The discharge state determination unit calculates a discharge speed of the stored contents from the hopper as information indicating the discharge state, The state determination unit determines the state of the contents inside the hopper from the ratio or difference between the intake speed and the discharge speed.

4. A movement state determination unit that determines a movement state of an object located at an upper portion of the hopper among the objects contained inside the hopper; A discharge state determination unit that determines a discharge state of the stored contents from the hopper; a state determination unit that determines a state of the contents inside the hopper based on the moving state and the discharging state, The discharge state determination unit calculates an actual discharge amount, which is the amount of the contents actually discharged from the hopper, from a time series of images of the contents discharged by a discharge device that discharges the contents to the outside of the hopper, as information indicating the discharge state, and determines a set discharge amount, which is a set value of the discharge amount of the discharge device; The state determination unit determines a state of the contents inside the hopper based on the movement state, the actual discharge amount, and the set discharge amount.

5. The information processing device according to claim 1 , further comprising a control determination unit that determines control for maintaining or improving a state of the contents inside the hopper in accordance with a determination result of the state determination unit.

6. The information processing device according to any one of claims 1 to 5, wherein when the state determination unit determines that the contents are attached to a wall surface of the hopper, the state determination unit determines the attachment location of the contents based on the movement state identified by the movement state identification unit.

7. An information processing device as described in any one of claims 1 to 6, further comprising a capacity estimation unit that estimates the amount of the contents contained in the hopper based on the discharge state identified by the discharge state identification unit and the amount of the contents placed into the hopper.

8. A movement state determination unit that determines a movement state of an object located at an upper portion of the hopper among the objects contained inside the hopper; A discharge state determination unit that determines a discharge state of the stored contents from the hopper; a state determination unit that determines a state of the contents inside the hopper based on the moving state and the discharging state; a target object detection unit for detecting a predetermined target object that may cause the hopper to enter a predetermined state; an information processing device comprising: a cause estimation unit that, when the state determination unit determines that the state of the hopper is the specified state within a specified period after the target content detection unit detects the target content, estimates that the cause of the state is the target content.

9. a movement state determination unit that determines a movement state of an item located at an upper portion of the hopper among the items contained inside the hopper; A discharge state determination unit that determines a discharge state of the stored contents from the hopper; and a control determination unit that determines control for maintaining or improving a state of the contents inside the hopper based on the movement state and the discharge state, The control decision unit is an information processing device that determines control to maintain or improve the state of the contents inside the hopper using a control prediction model that models the relationship between the movement state of the contents in the upper part of the hopper and the discharge state of the contents from the hopper, and the control to be executed during the movement state and the discharge state.

10. A state determination method executed by one or more information processing devices, comprising: a movement state identifying step of identifying a movement state of an item located at an upper portion of the hopper among the items contained inside the hopper; a discharge state determination step of determining a discharge state of the contents from the hopper; and a state determination step of determining a state of the contents inside the hopper based on the movement state and the discharge state, A state determination method in which, in the state determination step, the state of the contents inside the hopper is determined using a state prediction model that models the relationship between the movement state of the contents in the upper part of the hopper and the discharge state of the contents from the hopper, and the state of the contents inside the hopper.

11. A control decision method executed by one or more information processing devices, comprising: a movement state identifying step of identifying a movement state of an item located at an upper portion of the hopper among the items contained inside the hopper; a discharge state determination step of determining a discharge state of the contents from the hopper; and a control determination step of determining a control for maintaining or improving a state of the contents inside the hopper based on the movement state and the discharge state, In the control decision step, a control decision method is used to decide control for maintaining or improving the state of the contents inside the hopper, using a control prediction model that models the relationship between the movement state of the contents at the top of the hopper and the discharge state of the contents from the hopper, and the control to be executed during the movement state and the discharge state.

12. A state determination program for causing a computer to function as an information processing device as described in any one of claims 1, 3, and 4, comprising the state determination program for causing a computer to function as the movement state determination unit, the discharge state determination unit, and the state determination unit.

13. 10. A control decision-making program for causing a computer to function as the information processing device according to claim 9, the control decision-making program causing a computer to function as the movement state specifying unit, the discharge state specifying unit, and the control decision unit.

Images