JP2024092154A - Estimation device, program, and estimation method - Google Patents

Abstract

To provide an estimation device or the like which is less likely to be influenced by a peripheral environment when estimating a water content or the like of an object.SOLUTION: According to an embodiment, there is provided an estimation device which estimates a water content of an object. The estimation device comprises an optical characteristic acquisition unit, a water-containing model information acquisition unit, and a water content estimation unit. The optical characteristic acquisition unit acquires optical characteristics of each of an object and a reference plate different from the object. The water-containing model information acquisition unit acquires water-containing model information created in association with the optical characteristics of the object and the water content of the object. The water content estimation unit estimates the water content of the object on the basis of the optical characteristics of the object, the optical characteristics of the reference plate, and the water-containing model information.SELECTED DRAWING: Figure 1

Description

The present invention relates to an estimation device, a program, and an estimation method.

For materials such as iron ore and coal, which are used as raw materials for steelmaking and fuel for power generation, it is necessary to maintain the moisture content within an appropriate range. If these materials are too dry, they will generate dust, while if they contain too much moisture, they may clog during transportation or require a large amount of heat for drying, reducing energy efficiency.

Therefore, it is necessary to understand the water content in these materials in order to maintain the water content within an appropriate range by sprinkling water when it is dry, or spraying chemicals such as water-blocking agents when the water content is too high.

For example, Patent Document 1 discloses a method for measuring the moisture content on the surface of an iron ore pile using a near-infrared moisture content meter in order to determine the moisture content in the material and to perform water sprinkling to prevent dust.

JP 2008-050076 A

However, the inventors' investigations revealed that estimating the moisture content of the pile surface as described above is often influenced by the surrounding environment, making it difficult to properly manage the values.

In consideration of the above circumstances, the present invention aims to provide an estimation device etc. that is less affected by the surrounding environment when estimating the moisture content etc. of an object.

According to one aspect of the present invention, there is provided an estimation device that estimates the moisture content of an object. The estimation device includes an optical property acquisition unit, a moisture model information acquisition unit, and a moisture content estimation unit. The optical property acquisition unit acquires optical properties of the object and a reference plate different from the object. The moisture model information acquisition unit acquires moisture model information that is created by associating the optical properties of the object with the moisture content of the object. The moisture content estimation unit estimates the moisture content of the object based on the optical properties of the object, the optical properties of the reference plate, and the moisture model information.

Specifically, the present invention provides the following:
(1)
An estimation device for estimating a moisture content of an object, comprising:
The apparatus includes an optical characteristic acquisition unit, a water content model information acquisition unit, and a water content estimation unit,
The optical characteristic acquisition unit acquires optical characteristics of the object and a reference plate different from the object,
the water-containing model information acquisition unit acquires water-containing model information that is created by associating optical characteristics of the object with a water content of the object;
The moisture content estimation unit estimates the moisture content of the object based on optical characteristics of the object, optical characteristics of the reference plate, and the moisture model information.
Estimation device.
(2)
In the estimation device according to (1),
The optical characteristic acquisition unit acquires the optical characteristics of the object and/or the reference plate for light of multiple different wavelengths.
(3)
In the estimation device according to (1) or (2),
The optical characteristic acquisition unit acquires, as the optical characteristics, one or more of absorptance, reflectance, and transmittance of the object and/or the reference plate.
(4)
In the estimation device according to any one of (1) to (3),
The optical property acquisition unit acquires the optical properties of the object and the reference plate by capturing images of the object and the reference plate within the same angle of view.
(5)
In the estimation device according to any one of (1) to (4),
An estimation device, wherein the optical properties of the object and/or the reference plate acquired by the optical property acquisition unit are acquired using a hyperspectral camera or a multispectral camera.
(6)
In the estimation device according to (5),
An estimation device, wherein the reference plate is coupled to a housing of the hyperspectral camera or the multispectral camera.
(7)
In the estimation device according to (6),
The reference plate is coupled to the housing so that a position and/or an orientation of the reference plate can be adjusted.
(8)
In the estimation device according to (7),
Further, the device includes a detection unit and an adjustment unit,
The detection unit detects information regarding light irradiated onto the hyperspectral camera or the multispectral camera,
The adjustment unit adjusts the position and/or orientation of the reference plate based on information about the light detected by the detection unit.
(9)
In the estimation device according to any one of (1) to (8),
The estimation device, wherein the object is a raw material for steelmaking or a fuel for power generation.
(10)
An estimation device for estimating the presence or absence or amount of a drug contained in an object, comprising:
The apparatus includes an optical characteristic acquisition unit, a drug-containing model information acquisition unit, and a drug information estimation unit,
The optical characteristic acquisition unit acquires optical characteristics of the object and a reference plate different from the object,
The drug-containing model information acquisition unit acquires drug-containing model information that is created by associating optical characteristics of the object with the presence or absence or amount of a drug in the object,
The drug information estimation unit estimates the presence or absence or content of the drug in the object based on the optical characteristics of the object, the optical characteristics of the reference plate, and the drug-containing model information.
Estimation device.
(11)
In the estimation device according to (10),
The optical characteristic acquisition unit acquires the optical characteristics of the object and/or the reference plate for light of multiple different wavelengths.
(12)
A program,
A program for causing a computer to function as each part of the estimation device according to any one of (1) to (11).
(13)
A method for estimating a moisture content of an object, comprising:
The method includes an optical characteristic acquisition step, a water content model information acquisition step, and a water content estimation step,
The optical characteristic acquisition step includes acquiring optical characteristics of the object and a reference plate different from the object,
The water-containing model information acquisition step acquires water-containing model information that is created by associating optical characteristics of the object with a water content of the object,
The moisture content estimating step estimates the moisture content of the object based on optical characteristics of the object, optical characteristics of the reference plate, and the moisture model information.
Estimation method.
(14)
A method for estimating the presence or absence or amount of a drug contained in a target object, comprising:
The method includes an optical characteristic acquisition step, a drug-containing model information acquisition step, and a drug information estimation step,
The optical characteristic acquisition step includes acquiring optical characteristics of the object and a reference plate different from the object,
The drug-containing model information acquisition step acquires drug-containing model information that is created by associating optical characteristics of the object with the presence or absence or amount of a drug in the object,
The drug information estimation step estimates the presence or absence or the amount of the drug contained in the object based on the optical characteristics of the object, the optical characteristics of the reference plate, and the drug-containing model information.
Estimation method.

According to the above aspect, an estimation device etc. is provided that is less affected by the surrounding environment when estimating the moisture content etc. of an object.

1 is a diagram showing an overall configuration of an information processing system 1. FIG. 2 is a diagram showing a hardware configuration of an information processing unit 2a. FIG. 2 is a functional block diagram showing functions of the estimation device 2. FIG. 2 is an activity diagram showing the flow of information processing using the estimation device 2. 2 is a schematic diagram of an optical characteristic measuring unit 2b used in the present embodiment. FIG. 10 is a schematic diagram for explaining the contents of an image captured by the optical characteristic measuring unit 2b. FIG. 13 is a schematic diagram for explaining an adjustment mechanism of the optical characteristic measuring unit 2b. FIG.

The following describes embodiments of the present invention. Note that the various features shown in the following embodiments can be combined with each other.

The program for implementing the software used in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are implemented on a client terminal (so-called cloud computing).

In this embodiment, a "unit" may also include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In this embodiment, various information is handled, and this information is represented, for example, by physical values of signal values representing voltage and current, high and low signal values as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

In the broad sense, a circuit is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and memory. In other words, it includes application specific integrated circuits (ASICs), programmable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)).

1. Hardware Configuration In this section, a hardware configuration of an information processing system 1 according to this embodiment will be described. FIG 1 is a diagram showing the overall configuration of the information processing system 1.

1.1 Information Processing System 1
The information processing system 1 of the present embodiment is a system configured to be capable of executing an estimation method for estimating the water content of an object, and an estimation method for estimating the presence or absence or amount of a drug contained in an object. Therefore, such information processing system 1 may be simply referred to as an "estimation system."
Here, the information processing system 1 of this embodiment includes an estimation device 2. For convenience, in this specification, the information processing system 1 is treated as a concept that also includes a substance S that is an object of estimation by the estimation device 2.
The estimation device 2 shown in Fig. 1 includes an information processing unit 2a and an optical property measuring unit 2b. The information processing unit 2a controls information processing and the like for estimating the water content in a substance S in the information processing system 1. The system exemplified as the information processing system 1 is composed of one or more devices or components. Therefore, even the information processing unit 2a alone is an example of a system. On the other hand, although not shown in detail, a mode in which a predetermined information processing is performed by a plurality of devices can also be exemplified.

Here, the substance S in the information processing system 1 of this embodiment is an object for which the moisture content, etc. needs to be estimated. This substance S is appropriately selected from among known substances. This substance S may be an inorganic substance or an organic substance. In the exemplary embodiment, this substance S (object) is a raw material for iron making or a fuel for power generation.
"Ironmaking raw materials" refers to materials used as raw materials and fuels for ironmaking in ironmaking facilities such as steelworks, and examples of such materials include coal, steel, dust, slag, coke, sintered ore, as well as auxiliary materials such as limestone and dolomite. "Power generation fuel" refers to materials used as fuels for power generation in power generation facilities such as power plants, and examples of such materials include coal and biomass fuels. In a more typical example, the substance S is coal or iron ore.
In this specification, the term "water content" may refer to an absolute mass, and also includes the water content per unit mass of a substance, that is, the water content rate.

1.2 Estimation device 2
1 includes an information processing unit 2a and an optical characteristic measuring unit 2b. Each component will be described below.

[Information processing section 2a]
The information processing unit 2a is a device that estimates the water content, etc., of the substance S through predetermined information processing.
2 is a diagram showing the hardware configuration of the information processing unit 2a. The information processing unit 2a has a control unit 21, a storage unit 22, an input unit 23, a display unit 24, and a communication unit 25, and is configured by electrically connecting each of these units via a communication bus 20. Each unit provided in the information processing unit 2a will be described below.

(Control unit 21)
The control unit 21 is, for example, a central processing unit (CPU) not shown. The control unit 21 realizes various functions related to the estimation device 2 by reading out a predetermined program stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 can be specifically realized by the control unit 21, which is an example of hardware, and executed as each functional unit included in the control unit 21. These will be described in more detail in the next section. Note that the control unit 21 is not limited to being single, and may be implemented with multiple control units 21 for each function. Also, a combination of these may be used.

(Memory unit 22)
The storage unit 22 stores various pieces of information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the estimation device 2 executed by the control unit 21, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 22 stores various programs, variables, etc. related to the estimation device 2 executed by the control unit 21.

(Input unit 23)
The input unit 23 may be included in the housing of the information processing unit 2a, or may be externally attached. For example, the input unit 23 may be implemented as a touch panel integrated with the display unit 24. If it is a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, a switch button, a mouse, a QWERTY keyboard, or the like may be adopted instead of the touch panel. That is, the input unit 23 accepts an operation input made by the user. The input is transferred as a command signal to the control unit 21 via the communication bus 20, and the control unit 21 can execute a predetermined control or calculation as necessary.

(Display unit 24)
The display unit 24 may be, for example, included in the housing of the information processing unit 2a or may be externally attached. The display unit 24 displays a screen of a graphical user interface (GUI) that can be operated by a user. This is preferably implemented by using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display according to the type of the information processing unit 2a.

(Communication unit 25)
The communication unit 25 is configured to be able to transmit various electrical signals from the information processing unit 2a to external components. The communication unit 25 is also configured to be able to receive various electrical signals from the external components to the estimation device 2. The communication unit 25 may have a network communication function, which allows various information to be communicated between the optical property measuring unit 2b or the estimation device 2 and external devices via a communication line.

[Optical characteristic measuring unit 2b]
The optical property measuring unit 2b is configured to measure the optical property of the substance S that is the estimation target.
The measurement range of the optical properties and the method of dividing it can be appropriately selected according to the application, and the optical property measurement unit 2b can also be appropriately selected according to the measurement range of the optical properties and the method of dividing it, and is not particularly limited as long as it can measure the optical properties. For example, when measuring the material S piled in a yard in a pile shape, a hyperspectral camera or a multispectral camera can be used as the optical property measurement unit 2b. In this case, the hyperspectral camera or the multispectral camera needs to measure from above the yard. Therefore, such an optical property measurement unit 2b may be attached to the boom of an aircraft (e.g., an unmanned aircraft UAV such as a drone) that can fly at a position higher than the maximum height of the pile of the material S, or a reclaimer that can be extended to a position higher than the maximum height of the pile. That is, in such a case, the optical properties of the material S to be estimated are measured using a hyperspectral camera or a multispectral camera, and in particular, are measured using a hyperspectral camera or a multispectral camera attached to the aircraft.

When measuring the material S piled up in a yard as described above, the height at which the optical property measuring unit 2b is placed is not particularly limited, but is preferably placed at a position 20 m or more and 200 m or less higher than the yard. Specifically, the height at which the optical property measuring unit 2b is placed may be, for example, 25 m or more, 30 m or more, 35 m or more, 40 m or more, 45 m or more, 50 m or more, 55 m or more, 60 m or more, 65 m or more, 70 m or more, 75 m or more, 80 m or more, 85 m or more, 90 m or more, 95 m or more, 100 m or more, 105 m or more, 110 m or more, 115 m or more, 120 m or more, 125 m or more, 130 m or more, 135 m or more, or 195 m or less, 190 m or less, 185 m or less, 180 m or less, 175 m or less, 170 m or less, 165 m or less, or 160 m or less.

The specific structure and functions of the optical property measuring unit 2b will be explained later.

The optical property information measured by the optical property measuring unit 2b may be transmitted to the information processing unit 2a via communication with the information processing unit 2a, or a recording medium may be attached to the optical property measuring unit 2b to record the acquired information thereon, and the information processing unit 2a may acquire the optical property information via the recording medium. Since the information processing unit 2a can thus execute a predetermined information processing via the storage medium, the information processing unit 2a alone may be referred to as the "estimation device."

2. Functional Configuration In this section, the functional configuration of the present embodiment will be described. Fig. 3 is a functional block diagram showing the functions of the estimation device 2. As described above, information processing by software (stored in the storage unit 22) is specifically realized by hardware (the control unit 21), and can be executed as each functional unit included in the control unit 21.

Specifically, the estimation device 2 (control unit 21) may include, as its functional units, an optical property acquisition unit 211, a water content model information acquisition unit 212, a water content estimation unit 213, a detection unit 214, an adjustment unit 215, a drug content model information acquisition unit 216, a drug information estimation unit 217, a display control unit 218, and a memory management unit 219. Note that these functional units may be increased or omitted as appropriate depending on the application to which the estimation device 2 is applied.

(Optical characteristic acquisition unit 211)
The optical characteristic acquisition unit 211 is configured to be able to execute an optical characteristic acquisition process. In the optical characteristic acquisition process, the optical characteristic acquisition unit 211 acquires the optical characteristics of the object and a reference plate different from the object. The acquisition here can adopt both a form of acquiring information measured by the optical characteristic measurement unit 2b and a form of acquiring information not measured by the optical characteristic measurement unit 2b. In addition, the information acquisition path for the object and the reference plate may be different.

(Water-containing model information acquisition unit 212)
The wet model information acquisition unit 212 is configured to be able to execute a wet model information acquisition step. In the wet model information acquisition step, the wet model information acquisition unit 212 acquires wet model information that is created by associating the optical characteristics of the object with the water content of the object. Details of this wet model information will be described later.

(Moisture Content Estimation Unit 213)
The moisture content estimating unit 213 is configured to be able to execute a moisture content estimating step, in which the moisture content estimating unit 213 estimates the moisture content of the object based on the optical characteristics of the object, the optical characteristics of a reference plate, and the moisture model information.

(Detection unit 214)
The detection unit 214 is configured to be able to execute a detection process, in which the detection unit 214 detects information related to light irradiated onto the hyperspectral camera or multispectral camera.

(Adjustment unit 215)
The adjustment unit 215 is configured to be able to execute an adjustment process. In the adjustment process, the adjustment unit 215 adjusts the position and/or orientation of the reference plate based on information about the light detected by the detection unit 214. Specific aspects of this detection and adjustment will be described later.

(Drug-containing model information acquisition unit 216)
The drug-containing model information acquisition unit 216 is configured to be able to execute a drug-containing model information acquisition step. In the drug-containing model information acquisition step, the drug-containing model information acquisition unit 216 acquires drug-containing model information that is created by associating the optical characteristics of the object with the presence or absence or amount of drug in the object. Details of this drug-containing model information will be described later.

(Drug information estimation unit 217)
The drug information estimation unit 217 is configured to be able to execute a drug information estimation step. In the drug information estimation step, the drug information estimation unit 217 estimates the presence or absence or the amount of a drug contained in the target object based on the optical characteristics of the target object, the optical characteristics of the reference plate, and the drug-containing model information.

(Display control unit 218)
The display control unit 218 is configured to be able to execute a display control step. In the display control step, the display control unit 218 displays various information stored in the storage unit 22 or a screen or the like including the information in a visible manner. Specifically, the display control unit 218 controls visual information such as a screen, an image, an icon, a message, etc. to be displayed on the display unit 24 or the like of the estimation device 2. The display control unit 218 may generate only rendering information for displaying the visual information on the estimation device 2.

(Memory management unit 219)
The memory management unit 219 is configured to be able to execute a memory management process. In the memory management process, the memory management unit 219 is configured to manage various pieces of information to be stored that are related to the information processing system 1. Typically, the memory management unit 219 is configured to store information measured by the optical characteristic measuring unit 2b, information estimated by the estimation device 2, and the like in a memory area. This memory area is exemplified by the memory unit 22 of the estimation device 2 and the memory units of various terminals, but this memory area does not necessarily have to be within the information processing system 1, and the memory management unit 219 can also manage various pieces of information to be stored in an external storage device or the like.

3. Details of Information Processing In Section 3, the information processing method executed by the estimation device 2 and the like will be described with reference to an activity diagram and the like. Fig. 4 is an activity diagram showing the flow of information processing using the estimation device 2. Note that examples of the information processing method (estimation method) executed by the estimation device 2 and the like include an "estimation method for estimating the water content of an object" and an "estimation method for estimating the presence or absence of a drug in an object or the amount of drug contained therein", and these will be described in order below, and overlapping content will be omitted as appropriate.

[Method for estimating the moisture content of an object]
As shown in FIG. 4, in the information processing method of this embodiment, the optical property acquisition unit 211 of the estimation device 2 acquires the optical properties of the object and a reference plate different from the object (step S1).

This step is achieved by the information processing unit 2a acquiring the optical characteristics of the object measured by the optical characteristic measuring unit 2b, etc., and acquiring the optical characteristics of a reference plate different from the object. The optical characteristics of the reference plate can also be acquired by the optical characteristic acquiring unit 211 of the information processing unit 2a acquiring the optical characteristics measured by a measuring device different from the optical characteristic measuring unit 2b that acquires the optical characteristics of the object. On the other hand, the optical characteristic acquiring unit 211 of the information processing unit 2a acquiring the optical characteristics of the reference plate measured by the same configuration as the optical characteristic measuring unit 2b that measures the optical characteristics of the object. In a more typical example, the optical characteristic acquiring unit 211 can acquire the optical characteristics of each by capturing images of the object and the reference plate within the same angle of view.

The manner in which this optical characteristic is acquired will be described further with reference to the drawings. Figure 5 is a schematic diagram of the optical characteristic measuring unit 2b used in this embodiment.

This optical property measuring unit 2b includes a camera housing 260, a lens 261, a reference plate 262, and a support member 263. As mentioned above, this optical property measuring unit 2b may be attached to an aircraft.

The camera housing 260 is configured to capture an image of a specific object. The camera housing 260 is also configured to be able to acquire the optical characteristics of the imaged object. A known imaging device can be used as the camera housing 260, but typically it is a hyperspectral camera or a multispectral camera. In other words, the optical characteristics of the object and/or reference plate acquired by the optical characteristic acquisition unit 211 can be acquired using a hyperspectral camera or a multispectral camera.

Lens 261 is attached to the camera housing 260 and is configured to adjust the focal length, etc.

The reference plate 262 is made of a member having a diffuse reflection surface, for example, whose surface color does not change much over time. Typically, a plate made of a resin member to which a pigment of a specific color has been added and whose surface has been roughened can be used as the reference plate 262. The resin that makes up the surface of the reference plate 262 can be selected as appropriate, and is made of, for example, fluororesin (PTFE; pertetrafluoroethylene). In addition, as a commercially available material that is easily available, the "Zenith Polymer Standard Diffuse Reflection Target" manufactured by SphereOptics can be used. The surface color of the reference plate 262 can be set appropriately according to the color tone of the material S, and is preferably made of a color that is approximately the same color tone as the material S.

In addition, the optical property measuring unit 2b of this embodiment is provided with a support member 263 for supporting the reference plate 262 on the camera housing 260. In other words, by providing this support member 263, the reference plate 262 can be connected to the housing of the hyperspectral camera or multispectral camera.

That is, in the exemplary optical property measuring unit 2b of this embodiment, the camera housing 260 captures an image in the direction in which the reference plate 262 is present, thereby capturing an image of the object (material S) and the reference plate 262 within the same angle of view. This also makes it possible to measure the optical properties of each. FIG. 6 is a schematic diagram for explaining the image captured by the optical property measuring unit 2b. Both the reference plate 262 and the material S are captured within the angle of view AG1 captured by the optical property measuring unit 2b, making it possible to measure the optical properties of each. The optical properties measured in this manner can be acquired by the information processing unit 2a via a communication circuit or the like.

Here, the optical characteristics measured by the optical characteristic measuring unit 2b (i.e., the optical characteristics acquired by the optical characteristic acquiring unit 211) may be any of the known optical characteristics of the object and/or the reference plate, but are typically one or more of the absorptance, reflectance, and transmittance.

The optical characteristics measured by the optical characteristic measuring unit 2b may be optical characteristics for one wavelength, but are preferably optical characteristics for multiple wavelengths of light that are different from each other. In other words, the optical characteristic acquiring unit 211 can acquire the optical characteristics of the object and/or the reference plate for multiple wavelengths of light that are different from each other.

The optical properties are typically obtained by acquiring optical properties for light of a wavelength that matches the model (water-containing model information/drug-containing model information). Specific aspects are described in detail in the subsequent explanation of the process for acquiring the water-containing model.

That is, apart from the above-mentioned step S1, the moisture model information acquisition unit 212 of the estimation device 2 acquires moisture model information that is created by associating the optical characteristics of the object with the moisture content of the object (step S2). Note that the order of performing steps S1 and S2 is arbitrary, and it is possible to perform step S1 prior to step S2, to perform step S2 prior to step S1, or to perform both steps simultaneously.

Here, the water-containing model information will be explained.
This moisture model information indicates the relationship between the optical properties of a material identical to the material S to be estimated for light of a predetermined wavelength and the moisture content in the material. As will be described later, in the estimation method of this embodiment, the optical properties of the object are corrected in accordance with the optical properties of the reference plate. From this perspective, the moisture model information only needs to indicate the relationship between the corrected optical properties of the object and the moisture content in the material.

Typically, the moisture model information indicates the relationship between the moisture index calculated as a function of the difference between two optical properties of a substance identical to the substance S to be estimated for two different wavelengths of light, and the moisture content in the substance.

The light of the above-mentioned predetermined wavelength is, for example, light of a wavelength within the wavelength range of 800 nm to 2400 nm. Within the wavelength range of 800 nm to 2400 nm, there are multiple wavelength peaks at which water molecules show absorption. Therefore, optical properties (particularly reflectance) measured within this wavelength range tend to have a high correlation with the actual moisture content of the substance S. In particular, the moisture content index calculated as a function of the difference between two optical properties for light of two different wavelengths within the wavelength range of 800 nm to 2400 nm reflects the effects of the two wavelengths, and therefore has a particularly high correlation with the actual moisture content of the substance S. By using moisture content model information showing the relationship between the moisture content index and moisture content of the substance S, the moisture content of the substance S can be accurately estimated regardless of the measurement distance and weather conditions.

The wavelength ranges for selecting the two wavelengths mentioned above are preferably within the ranges of 800 nm to 1100 nm, 1160 nm to 1340 nm, and 1440 nm to 2400 nm. By adopting such wavelength ranges, it is possible to reduce the influence of moisture in the atmosphere, and as a result, it is possible to estimate the water content of material S while reducing the influence of the measurement distance and weather (sunny, cloudy).

Here, we will explain "a function of the difference between two optical properties of a substance for light of two different wavelengths within a wavelength range of 800 nm to 2400 nm" (hereinafter sometimes referred to as "difference function"). As an example, a specific description will be given of a case in which 1050 nm and 1330 nm are selected as the two light wavelengths, and reflectance is selected as the optical property. If the reflectance for light of a wavelength of 1050 nm is R ₁₀₅₀ and the reflectance for light of a wavelength of 1330 nm is R ₁₃₃₀ , the difference between the two optical properties is expressed as R ₁₃₃₀ -R _1050. The difference function is expressed as f(R ₁₃₃₀ -R ₁₀₅₀ ).

To generalize this, if the optical characteristics for light of wavelengths inm and jnm are _Oi and _Oj , respectively, the difference between the two optical characteristics is expressed as _Oj - _Oi , and the function of the difference is expressed as f( _Oj - _Oi ). Note that _Oi and _Oj may be the same optical characteristics or different optical characteristics. "The same optical characteristics" refers to, for example, a case where _Oi and _Oj are both reflectance, and "different optical characteristics" refers to, for example, a case where _Oi is reflectance and _Oj is absorptance.

The form of the difference function is not particularly limited as long as it is a function of _Oj -Oi, and functions such as _Oj - _Oi , C( _Oj - _Oi ), C/( _Oj - _Oi ), C ^Oj-Oi , e ^Oj-Oi , log( _Oj - _Oi ) (wherein C is an arbitrary constant) can be used. The difference function may further include _Oi and _Oj in the formula, and for example, the following formulas (1) to (3) can be used.

( _Oj - _Oi )/ _Oj ... (1)
( _Oj - _Oi )/ _Oi ... (2)
( _Oj - _Oi )/( _Oj + _Oi ) ... (3)

In one embodiment, the normalization difference spectral index (NDSI) can be used as the difference function. Specifically, the normalization difference spectral index is expressed by the following formula (4) where R _i and R _j are the reflectances for light with wavelengths inm and j nm, respectively.

NDSI=( _Rj - _Ri )/( _Rj + _Ri ) (4)

The moisture model information is not particularly limited as long as it indicates the relationship between the moisture index and moisture content of the substance S, but for example, a function indicating the relationship between the moisture index and moisture content, a lookup table, or a trained model of the relationship between them can be used.

In the case where a function showing the relationship between the water content index and the water content of a material S is used as the water content model information, an example of a method for creating such a function will be described. A plurality of materials S with known water contents are prepared with different water contents so as to cover the range of possible water contents (it is preferable that there is at least one point above the upper limit of the possible water content and one point below the lower limit of the possible water content, but this is not limited thereto). For each of the materials S, two wavelengths are selected from the wavelengths at regular intervals (for example, 10 nm) within a wavelength range of, for example, 800 nm to 2400 nm, and the optical properties of the material S with known water content for these wavelengths are measured. A regression analysis is performed on the difference between the two optical properties for the two wavelengths and the water content (known), and two wavelengths with particularly high coefficients of determination are found, and the function at those wavelengths is used as a function showing the relationship between the water content index and the water content of the material S. In addition, for such a function, the measurement distance and weather conditions can be changed to use a combination of two wavelengths with a coefficient of determination of a certain level or more (for example, R ² >0.8). This can further improve the accuracy of the estimation. Furthermore, if it is desired to estimate the water content of a substance regardless of the brand of substance S, the brand of the substance may be changed and a combination of two wavelengths that provides a coefficient of determination above a certain level (for example, R ² >0.8) may be used.

The wavelength range from which the two wavelengths are selected is preferably 850 nm or more and 900 nm or more. The wavelength range from which the two wavelengths are selected is preferably 2300 nm or less, 2200 nm or less, 2100 nm or less, 2000 nm or less, 1900 nm or less, 1800 nm or less, and 1700 nm or less.

The interval between increments is not particularly limited, but is preferably 5 nm or more, 6 nm or more, 7 nm or more, 8 nm or more, 9 nm or more, or 10 nm or more. By having an interval between increments that is greater than or equal to the required amount, it is possible to easily create the hydrated model information. On the other hand, it is preferable that the interval between increments is 50 nm or less, 45 nm or less, 40 nm or less, 30 nm or less, 20 nm or less, 15 nm or less, or 10 nm or less. By having an interval between increments that is less than or equal to the required amount, it is possible to create the hydrated model information with high accuracy.

Although there are no particular limitations to the regression analysis, simple regression analysis, multiple regression analysis, etc. can be used.

In addition, in the information processing method of this embodiment, after steps S1 and S2 are executed, the moisture content estimation unit 213 estimates the moisture content of the object based on the optical characteristics of the object, the optical characteristics of the reference plate, and the moisture model information (step S3).

In other words, as described above, the optical property acquisition unit 211 acquires the optical properties of the object, and the moisture model information acquisition unit 212 acquires the moisture model information, so in theory it is possible to estimate the moisture content of the object (substance S) based on this information. However, the inventors' studies have revealed the following circumstances. That is, the optical properties of the object are easily affected by external factors (such as the position of the sun and the weather), and there is room to improve the accuracy of the estimated data. In contrast, the estimation method of this embodiment can solve the above-mentioned problems by referring to the optical properties of a reference plate when estimating the moisture content.

In other words, in the estimation method of this embodiment, the estimated moisture content of the object is corrected based on the optical characteristics of the reference plate. This correction is typically performed as follows, although not necessarily limited to the following:

That is, when the optical characteristic of the measured reference plate is _OST and the optical characteristic of the measured object is _OOB , in this step S3, the value expressed by the following formula (5) is treated as the moisture index (I) used in the moisture content estimation step, and the moisture content of the object is estimated by performing calculations based on the above-mentioned moisture model information.

I = O _OB / O _ST ... (5)

In the estimation method of this embodiment, it is sufficient that the moisture content finally output is a corrected value. Therefore, the estimation method of this embodiment can also be achieved by first determining the moisture content estimated from the relationship with the moisture model information based on the measurement value of the object (substance S) whose optical properties have been measured, and then correcting the moisture content determined based on the relationship with the optical properties of a reference plate that has been measured separately.

The water content of the substance S estimated in this manner is appropriately displayed (output) to the user. Here, specific output methods include, for example, the following modes.
For example, when piles of the material S are arranged over a wide range, the range may be divided into certain ranges (areas), the optical properties may be measured, and the moisture content estimated for each specific range (area) may be output. When piles of the material S are arranged over a wide range, the range may be divided into certain ranges (areas), the optical properties may be measured, and all or part of the results may be integrated to output the optical properties of a larger range. When dividing the measurement range of the optical properties into certain ranges (areas), the measurement range and output range may be divided equally or unequal. Also, the measurement range and output range may be divided into certain units, such as for each pile, and the optical properties may be measured and the estimated moisture content may be output. For example, the measurement range may be divided equally into units smaller than the pile, and the ranges that include the piles within the divided ranges may be integrated to output the moisture content estimated for each pile. In this way, the measurement range of the optical properties and the division method thereof and the output range and the division method thereof may be appropriately combined depending on the application, etc.
In addition, the piles may be classified according to the moisture content, and may be colored or indicated by letters on the piles in the image or schematic diagram of the yard. These output results are displayed on the display unit 24, for example. Typically, the display can be realized by the function of the display control unit 218 of the estimation device 2.

In the estimation method of this embodiment, the following configuration can also be adopted: Fig. 7 is a schematic diagram for explaining an adjustment mechanism of the optical characteristic measuring unit 2b.
That is, the reference plate 262 of the optical characteristic measuring unit 2b may be connected to the housing (camera housing 260) so that the position and/or orientation of the reference plate 262 can be adjusted. That is, when estimating the moisture content described above, if the reference plate 262 or the object is in the shade, the estimation accuracy may decrease. In response to this, by connecting the reference plate 262 to the camera housing 260 so that the position and/or orientation of the reference plate 262 can be adjusted, it becomes easier to prevent a situation in which the estimation accuracy decreases. Specifically, in the optical characteristic measuring unit 2b of FIG. 7, the support member 263 is configured to be movable, and can rotate around the base of the camera housing 260 (see FIG. 7a), or the support member 263 can rotate on its axis (see FIG. 7b). In addition, the reference plate 262 may be configured to be movable, or the reference plate 262 may be configured to rotate around the base of the support member 263 (see FIG. 7c). Of course, the adjustment mechanism for the position and orientation of the reference plate 262 is not limited to these.

Although such adjustment of the reference plate 262 may be performed manually, the following configuration may also be adopted. That is, the detection unit 214 may be configured to detect information related to the light irradiated onto the camera housing 260 (hyperspectral camera or multispectral camera), and the adjustment unit 215 may be configured to adjust the position and/or orientation of the reference plate 262 based on the information related to the light detected by the detection unit 214. That is, based on the functions of the detection unit 214 and adjustment unit 215 provided in the estimation device 2, the sunlight conditions of the reference plate 262 and the target object may be estimated, and based on this, the position and/or orientation of the reference plate 262 may be automatically adjusted. This can contribute to improving the estimation accuracy of the moisture content, etc.

[Method for estimating the presence or absence or amount of a drug contained in a target object]
In this estimation method, the presence or absence or amount of a drug in an object is estimated. In this estimation method, steps corresponding to steps S1, S2, and S3 described above are also performed, but the difference is that the model information used in this estimation method is drug-containing model information created by associating the optical properties of the object with the presence or absence or amount of a drug in the object.

That is, in the case where substance S contains a specific chemical, similar to the case where substance S contains water, the estimation device 2 of this embodiment can estimate the presence or absence of the chemical and the amount contained. Here, the "chemical" may be any known chemical that can be combined with substance S. For example, if this substance S (target object) is a raw material for ironmaking or fuel for power generation, and the substance S is piled up in a pile, the chemical may be a dust suppressant.

As the dust suppressant, there is no particular limitation, but wax emulsion solution, resin emulsion solution, silicone oil, mineral oil, heavy oil, etc. can be used. Wax emulsions are divided into natural wax and synthetic wax, based on the raw material of the wax. Of these, natural waxes include, but are not limited to, animal wax (beeswax, spermaceti, etc.), plant wax (carnauba wax, rice wax, candelilla wax, etc.), petroleum wax (paraffin wax, microcrystalline wax, etc.), mineral wax (montan wax, ceresin wax, etc.), etc. In addition, as the synthetic wax, there is no particular limitation, but polyethylene wax, natural wax modified products, hardened oil of oils and fats, etc. can be used. As the emulsion resin of the emulsion resin solution, there is no particular limitation, but for example, acrylic resin, acrylic copolymer resin, vinyl acetate resin, synthetic rubber, urethane resin, asphalt (emulsifier), acrylic-styrene emulsion, styrene-butadiene emulsion, ethylene-vinyl acetate, emulsion, versatic acid acrylic acid, etc. can be used. Examples of silicone oils that can be used include dimethyl silicone oil and organic functional silicone oil (functional groups include amino, epoxy, mercapto, phenyl, long-chain alkyl, and hydrogen groups). Dustproofing agents made of such resin emulsion solutions form a hydrophobic coating on the surface of the pile.

In this estimation method, the optical property acquisition unit 211 may be configured to acquire the optical properties of the object and/or the reference plate 262 for light of multiple wavelengths different from each other, and the same type of configuration as the estimation method for estimating the water content of the object described above can be appropriately adopted. For example, when optical properties for light of multiple wavelengths different from each other are acquired, the accuracy of estimating the drug content (presence or absence and/or amount of drug content) can be improved.

As described above, the estimation device 2 of this embodiment can realize an estimation device that is less affected by the surrounding environment when estimating the moisture content, etc., of an object.

4. Modifications In Section 4, modifications of the information processing method of the estimation device 2 and the like described above will be described.

The above embodiment has been described as the configuration of the estimation device 2, but a program that causes a computer to function as each part of the estimation device 2 may also be provided.

In the above embodiment, an estimation method using a predetermined model was shown, but the information associated when creating the model information is not limited to the above. In other words, the model information used in this embodiment may also be associated with various other conditions, such as weather conditions and regional conditions.

The above describes the embodiments of the present invention, but these are merely examples of the present invention, and various configurations other than those described above can be adopted. Furthermore, the present invention is not limited to the above-described embodiments, and modifications and improvements within the scope of the present invention that can achieve the object of the present invention are included in the present invention.

1: Information processing system 2: Estimation device 2a: Information processing unit 2b: Optical property measurement unit 20: Communication bus 21: Control unit 22: Memory unit 23: Input unit 24: Display unit 25: Communication unit 211: Optical property acquisition unit 212: Water-containing model information acquisition unit 213: Water content estimation unit 214: Detection unit 215: Adjustment unit 216: Drug-containing model information acquisition unit 217: Drug information estimation unit 218: Display control unit 219: Memory management unit 260: Camera housing 261: Lens 262: Reference plate 263: Support member AG1: Angle of view S: Substance

Claims (14)

An estimation device for estimating a moisture content of an object, comprising:
The apparatus includes an optical characteristic acquisition unit, a water content model information acquisition unit, and a water content estimation unit,
The optical characteristic acquisition unit acquires optical characteristics of the object and a reference plate different from the object,
the water-containing model information acquisition unit acquires water-containing model information that is created by associating optical characteristics of the object with a water content of the object;
The moisture content estimation unit estimates the moisture content of the object based on optical characteristics of the object, optical characteristics of the reference plate, and the moisture model information.
Estimation device. 2. The estimation device according to claim 1,
The optical characteristic acquisition unit acquires the optical characteristics of the object and/or the reference plate for light of multiple different wavelengths. 2. The estimation device according to claim 1,
The optical characteristic acquisition unit acquires, as the optical characteristics, one or more of absorptance, reflectance, and transmittance of the object and/or the reference plate. 2. The estimation device according to claim 1,
The optical property acquisition unit acquires the optical properties of the object and the reference plate by capturing images of the object and the reference plate within the same angle of view. 2. The estimation device according to claim 1,
An estimation device, wherein the optical properties of the object and/or the reference plate acquired by the optical property acquisition unit are acquired using a hyperspectral camera or a multispectral camera. 6. The estimation device according to claim 5,
An estimation device, wherein the reference plate is coupled to a housing of the hyperspectral camera or the multispectral camera. 7. The estimation device according to claim 6,
The reference plate is coupled to the housing so that a position and/or an orientation of the reference plate can be adjusted. The estimation device according to claim 7,
Further, the device includes a detection unit and an adjustment unit,
The detection unit detects information regarding light irradiated onto the hyperspectral camera or the multispectral camera,
The adjustment unit adjusts the position and/or orientation of the reference plate based on information about the light detected by the detection unit. 2. The estimation device according to claim 1,
The estimation device, wherein the object is a raw material for steelmaking or a fuel for power generation. An estimation device for estimating the presence or absence or amount of a drug contained in an object, comprising:
The apparatus includes an optical characteristic acquisition unit, a drug-containing model information acquisition unit, and a drug information estimation unit,
The optical characteristic acquisition unit acquires optical characteristics of the object and a reference plate different from the object,
The drug-containing model information acquisition unit acquires drug-containing model information that is created by associating optical characteristics of the object with the presence or absence or amount of a drug in the object,
The drug information estimation unit estimates the presence or absence or content of the drug in the object based on the optical characteristics of the object, the optical characteristics of the reference plate, and the drug-containing model information.
Estimation device. The estimation device according to claim 10,
The optical characteristic acquisition unit acquires the optical characteristics of the object and/or the reference plate for light of multiple different wavelengths. A program,
A program for causing a computer to function as each unit of the estimation device according to any one of claims 1 to 11. A method for estimating a moisture content of an object, comprising:
The method includes an optical characteristic acquisition step, a water content model information acquisition step, and a water content estimation step,
The optical characteristic acquisition step includes acquiring optical characteristics of the object and a reference plate different from the object,
The water-containing model information acquisition step acquires water-containing model information that is created by associating optical characteristics of the object with a water content of the object,
The moisture content estimating step estimates the moisture content of the object based on optical characteristics of the object, optical characteristics of the reference plate, and the moisture model information.
Estimation method. A method for estimating the presence or absence or amount of a drug contained in a target object, comprising:
The method includes an optical characteristic acquisition step, a drug-containing model information acquisition step, and a drug information estimation step,
The optical characteristic acquisition step includes acquiring optical characteristics of the object and a reference plate different from the object,
The drug-containing model information acquisition step acquires drug-containing model information that is created by associating optical characteristics of the object with the presence or absence or amount of a drug in the object,
The drug information estimation step estimates the presence or absence or the amount of the drug contained in the object based on the optical characteristics of the object, the optical characteristics of the reference plate, and the drug-containing model information.
Estimation method.