State grasping system, state grasping device, and method for grasping state

Abstract

To provide a state grasping system capable of grasping the state of resin.SOLUTION: A state grasping system 10 includes: an acquisition unit 4 for acquiring data on a feature amount related to the state of resin by analyzing a target object containing the resin; an extraction unit 5 for extracting the feature amount from the data acquired by the acquisition unit 4; a grasping unit 6 for grasping the state of the resin from the feature amount extracted by the extraction unit 5 and a state grasping model for grasping the state; and an output unit 2 for outputting at least one of the result of grasping by the grasping unit 6 and information obtained by the result of the grasping.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a state grasping system, a state grasping device, and a state grasping method.

Background Art

[0002] Due to the global plastic regulations aiming for carbon neutrality and the increasing trend of ethical consumption, etc., the recycling material market is becoming active. While material recycling is excellent in terms of economy, it is preferable to appropriately restore the performance according to the state of the waste material. Patent Document 1 describes that "The present invention provides a method for producing a resin waste material molded body containing a thermoplastic resin and inorganic substance powder from an inorganic substance powder blended resin waste material, the method including a sorting step of sorting the inorganic substance powder blended resin waste material according to the particle diameter of the inorganic substance powder, a pulverizing step of pulverizing the sorted inorganic substance powder blended resin waste material, and a kneading step of kneading with an extruder. In the sorting step, it is preferable to measure the particle diameter of the inorganic substance powder by the small-angle X-ray scattering method."

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In Patent Document 1, only general material knowledge regarding the effectiveness of thermal analysis is mentioned. Therefore, for example, regarding resins such as polypropylene, it is not described to grasp the state of the resin using a grasping model for grasping the state of the resin. The problem to be solved by the present disclosure is to provide a state grasping system, a state grasping device, and a state grasping method capable of grasping the state of a resin.

Means for Solving the Problems

[0005] The state grasping system of the present disclosure includes an acquisition unit that acquires data on feature quantities related to the state of the resin by analyzing an object containing the resin, an extraction unit that extracts the feature quantities from the data acquired by the acquisition unit, and a grasping unit that grasps the state of the resin from the feature quantities extracted by the extraction unit and a state grasping model for grasping the state, and an output unit that outputs at least one of the grasping result by the grasping unit or information obtained using the grasping result. Other solution means will be described later in the mode for carrying out the invention.

Effect of the Invention

[0006] According to the present disclosure, it is possible to provide a state grasping system, a state grasping device, and a state grasping method capable of grasping the state of a resin.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0008] Hereinafter, modes for carrying out the present disclosure (referred to as embodiments) will be described with reference to the drawings. In the description of the following one embodiment, descriptions of other embodiments applicable to the one embodiment will be made as appropriate. The present disclosure is not limited to the following one embodiment, and different embodiments can be combined with each other, or arbitrarily modified within a range not significantly impairing the effects of the present disclosure. Also, the same members will be denoted by the same reference numerals, and overlapping descriptions will be omitted. Furthermore, those having the same function will be given the same name. The content shown in the drawings is merely schematic, and for the convenience of illustration, it may be changed from the actual configuration within a range not significantly impairing the effects of the present disclosure, or the illustration of some members may be omitted or deformed between the drawings. Also, in the same embodiment, it is not always necessary to include all the configurations.

[0009] FIG. 1 is a block diagram showing a state grasping system 10 according to the first embodiment. The state grasping system 10 is a system for grasping the state of a resin (for example, waste resin) in an object recovered in, for example, the market, improvement, etc. Since the resin in the object recovered in the market, improvement, etc. is derived from various places, products, parts, etc., it has various states (such as tensile mechanical properties (tensile mechanical strength)). And resins with unknown states are difficult to recycle. For this reason, the state grasping system 10 can grasp (infer, predict, analyze) the state of such resins with unknown states.

[0010] Conventionally, in order to know the state of a resin such as tensile mechanical properties, for example, after processing resin pellets into a predetermined test piece shape, state evaluation (measurement) can be performed. For this reason, the cost required for processing increases, and the cost of acquiring data is high. However, in the state grasping system 10, thermogravimetric measurement (TG), differential thermal analysis (DTA), infrared spectroscopy (IR), wide-angle X-ray diffraction measurement (WAXS), and color measurement, which will be described later, can all be measured regardless of the shape of the resin, so the cost for data acquisition can be suppressed.

[0011] The state of the resin includes, for example, the state regarding the structure of the resin that affects the tensile mechanical properties of the resin among the tissue structures of the resin (for example, the way of bonding between atoms, three-dimensional structure, type of functional group, bonding position of functional group, molecular weight, etc.). By including such a state, although details will be described later, for example, based on the peak width at a specific position, etc., the tensile mechanical properties of the resin can be evaluated as the state of the resin.

[0012] In particular, recycled resins (recycled resins) often have lower tensile mechanical properties than virgin materials. Therefore, by grasping the tensile mechanical properties of waste resins, measures (for example, the blending ratio of virgin materials) for recovering the tensile mechanical properties reduced compared to virgin materials can be determined. Thereby, a recycled resin material having tensile mechanical properties close to those of virgin materials can be provided.

[0013] The state of the resin is, although details will be described later, for example, the tensile elastic modulus, tensile yield stress, tensile yield strain, etc. of the resin. These are an example of tensile mechanical properties.

[0014] As the resin, for example, a thermoplastic resin is preferable. Among them, the resin preferably contains a structural unit (-CH2-CH(CH3)-) of polypropylene, and more preferably is polypropylene. The resin containing the structural unit of polypropylene is, for example, a copolymer of the structural unit of polypropylene and the structural unit (-CH2-CH2-) of polyethylene. Also included is the case where polypropylene and polyethylene have a material structure of a sea-island structure. Hereinafter, the resin (excluding polypropylene) containing the structural unit of polypropylene as the main unit (the most numerous unit) and polypropylene may be collectively referred to as polypropylene and the like.

[0015] Polypropylene and the like are widely traded in the market. Also, for example, they are relatively widely used in products such as household appliances and industrial products. For this reason, the amount of polypropylene and the like recovered in the market and the like is large. Therefore, by using the state grasping system 10, the states of a large amount of polypropylene and the like can be grasped quickly.

[0016] The state grasping system 10 includes an output unit 2, a production record DB (database) 3, an acquisition unit 4, an extraction unit 5, and a grasping unit 6. The production record DB 3 is stored, for example, in a server (not shown) arranged at a remote location. The output unit 2, the production record 3, the acquisition unit 4, the extraction unit 5, and the grasping unit 6 are connected to be mutually communicable via a network 1.

[0017] The output unit 2 is, for example, an output device that outputs at least one of the grasping result in the grasping unit 6 or the information obtained by using the grasping result to, for example, a user, a resin manufacturing apparatus, or the like. The output unit 2 outputs, for example, the information (tensile mechanical properties, contribution degree, degradation degree, production conditions, etc.) obtained in the example shown below. The output device is, for example, an input / output device such as a personal computer, a portable information terminal, or a portable communication terminal. However, the output unit 2 may also be a part of the functional units constituting the state grasping device 20 (Figure 3).

[0018] The acquisition unit 4 is, for example, an acquisition device that acquires data (data related to characteristic quantities) regarding characteristic quantities of the resin by analyzing an object containing the resin. However, the acquisition unit 4 may be a part of the functional units constituting the state grasping device 20 (Fig. 3).

[0019] From the viewpoint of improving the grasping accuracy by the state grasping system 10, the object to be grasped is preferably an object consisting only of resin or a mixture containing an arbitrary material other than resin with a small content of the arbitrary material. The arbitrary material is, for example, an additive (such as an antioxidant, a flame retardant, etc.) used for improving the functionality of the coexisting resin.

[0020] Also, the resin contained in the object is preferably a single resin species (for example, only polypropylene) or a mixture containing a plurality of resin species with a small content of resins other than the resin to be grasped. Examples of such an object include waste resins classified in advance by resin type in the market, factory, etc. Such waste resins are classified (categorized) as, for example, polypropylene, etc., so the proportion of polypropylene, etc. in the pre-resin contained in the waste resin is, for example, 95% by mass or more. In the examples of the present disclosure, the state of the entire object containing the resin is grasped, but hereinafter, for convenience, expressions such as "grasping the state of the resin" are also used as appropriate.

[0021] Specifically, the acquisition unit 4 is, for example, an analysis unit, an analysis device, etc. More specifically, for example, the acquisition unit 4 is at least one of measurement devices such as a thermogravimetric (TG) measurement device, a differential thermal (DTA) measurement device, an infrared spectroscopy (IR) measurement device, a wide-angle X-ray diffraction (WAXS) measurement device, a color (for example, L*a*b color system) measurement device. The acquisition unit 4 may be determined according to the type of resin to be grasped. By these acquisition devices, for example, data (measured data) related to the characteristic quantities described later can be obtained. Note that the data related to the characteristic quantities may be data of the characteristic quantities themselves or data that can acquire the characteristic quantities by fitting the measured data to an arbitrary model function. That is, the data related to the characteristic quantities may be data associated with the characteristic quantities.

[0022] For the measurement method using each measuring device, for example, the following content can be applied. As a measuring device integrating a thermal mass measuring device and a differential thermal measuring device, EXSTAR6200 manufactured by SII NanoTechnology Inc. can be used. As the measurement method, 10 (±1) mg of the sample is placed in an aluminum open container (GCA-0055 manufactured by Hitachi High-Tech Sciences Corporation), and after heating and cooling from room temperature (for example, 25°C) to 200°C under a nitrogen stream, it can be switched to an air stream and heated to 510°C at a heating rate of 10°C / min.

[0023] As the infrared spectroscopic measuring device, for example, Spectrum100 manufactured by PerkinElmer, Inc., a Fourier transform infrared spectroscopic device, can be used. As the measurement method, it can be measured by the total reflection method, and the wavenumber range from 4500 cm- 1 to 600 cm- 1 may be integrated 20 times. Also, the sample pressing pressure may be set to 100 according to the device display value.

[0024] As the wide-angle X-ray diffractometer, SmartLab manufactured by Rigaku Corporation can be used. As the measurement method, it may be measured at room temperature (for example, 25°C) by the Bragg-Brentano focused beam method. The applied voltage to the copper rotor is 45 kV, the current is 200 mA, K β filter is Ni, the solar slits are both 2.5° on the incident side and the light receiving side, the divergence slit is 0.15°, the light receiving slit is 0.15 mm, the long slit is 10 mm, and the scattering slit may not be used. The scanning axis may be set to a 2θ / θ interlocking operation with an interval of 0.01° and a speed of 5° / min, and the range of 5° ≤ 2θ ≤ 100° may be continuously scanned in 1D at room temperature.

[0025] As a color measurement device (spectrophotometric colorimetry), for example, CM-2600d manufactured by Konica Minolta can be used. As a measurement method, the lightness L* and chromaticity a*b* in the L*a*b* color space system may be measured. A white high-shielding and high-reflectivity sheet (Lumirror manufactured by Toray Industries) may be laid on a horizontal experimental table, and the sample may be placed thereon. In the L*a*b* color space system, the L value (L*) represents the lightness (brightness) of the color. The L value has a range of 0 to 100, where 0 is black and 100 is white, and the larger the number, the brighter the color. The a value (a*) and b value (b*) represent the strength of the color tone. When a* is on the plus (+) side, it represents a red tone, and when on the minus (-) side, it represents a green tone. B* represents a yellow tone when on the plus (+) side and a blue-violet tone when on the minus (-) side.

[0026] The acquisition unit 4 may be, for example, a measuring device that measures hardness. In this case, as the measuring device, CTS-102 manufactured by Mitutoyo can be used. As a measurement method, it may be measured with a weight of 4580 g using a Type D hardness tester fixed to a measurement / verification stand (CTS-102 manufactured by Mitutoyo) (JIS K 7215).

[0027] The feature quantity regarding the state of the resin is a numerical value that quantitatively represents the features of the data (measured data, target data) obtained by analyzing the object. The feature quantity is used as a clue for grasping the state in the grasping unit 6 described later.

[0028] In the example of the present disclosure, the resin is polypropylene or the like, and the feature quantity is a feature quantity that has a correlation (is linked) with the tensile mechanical properties of polypropylene or the like. Thereby, the tensile mechanical properties of polypropylene or the like, which is waste resin, can be grasped. The tensile mechanical properties are, as described above, for example, tensile elastic modulus, tensile yield stress, and tensile yield strain.

[0029] The feature quantity acquired by the acquisition unit 4 includes, for example, at least one of the first feature quantity, the second feature quantity, the third feature quantity, the fourth feature quantity, or the fifth feature quantity.

[0030] The first feature quantity is a feature quantity based on the heat quantity obtained by measuring the heat quantity of the resin in an air environment. The second feature quantity is a feature quantity based on the heat quantity obtained by differential heat measurement of the resin in an air environment. The third feature quantity is a feature quantity based on the infrared spectroscopy obtained by infrared spectroscopy measurement of the resin. The fourth feature quantity is a feature quantity based on the wide-angle X-ray diffraction obtained by wide-angle X-ray diffraction measurement of the resin. The fifth feature quantity is a feature quantity based on the color obtained by color measurement of the resin. By obtaining at least one of these feature quantities, the state of the resin can be grasped.

[0031] In one embodiment, the state of the resin is the tensile elastic modulus of the resin, and the feature quantity (the feature quantity extracted by the extraction unit 5) regarding the data acquired by the acquisition unit 4 includes a feature quantity having a correlation with the tensile elastic modulus (a feature quantity peculiar to the tensile elastic modulus). Thereby, based on the feature quantity, the tensile elastic modulus of the resin can be grasped.

[0032] In this case (when the resin is polypropylene), the first feature quantity includes, for example, at least one of the carbon content of polypropylene at a predetermined temperature, the progress rate of carbonization of polypropylene in a predetermined temperature range, the reaction amount of the oxidation reaction of polypropylene in a predetermined temperature range, or the activation energy and reaction amount of the decomposition reaction of polypropylene in a predetermined temperature range (for example, between 350 ° C and 400 ° C). The carbon content is, for example, the residue amount at the time of 500 ° C. The progress rate of carbonization is, for example, the mass change of polypropylene between 430 ° C and 500 ° C. The reaction amount of the oxidation reaction is, for example, the oxidation reaction amount (for example, the production rate of the product) of polypropylene that has proceeded between, for example, 220 ° C and 330 ° C. The activation energy and reaction amount of the decomposition reaction of polypropylene in a predetermined temperature range are, for example, the activation energy and reaction amount between 350 ° C and 400 ° C.

[0033] Also, in this case, the second feature quantity includes at least one of the number of modes of the oxidation reaction of polypropylene (how many stages the oxidation reaction proceeds) and the maximum heat generation temperature, or the heat generation amount of the decomposition reaction of polypropylene.

[0034] Furthermore, in this case, the third feature amount includes at least one of the peak position at 2920 cm -1 or the peak intensity at 2960 cm -1 (CH3 antisymmetric stretching).

[0035] Furthermore, in this case, the fourth feature amount includes at least one of the peak position of the α-phase (110), the peak position and width of the α-phase (130), the peak intensity of the α-phase (220), or the peak position of the α-phase (040).

[0036] These feature amounts show a high correlation with the tensile modulus of polypropylene. Therefore, by using these feature amounts, the tensile modulus of polypropylene can be grasped.

[0037] Furthermore, in this case, when the object to be grasped contains talc in addition to polypropylene, the fourth feature amount includes at least one of the peak intensity of the α-phase (002) or the peak intensity of the α-phase (006). When the object to be grasped contains rutile in addition to polypropylene, the fourth feature amount includes at least one of the peak intensity of the α-phase (110), the intensity or width of the peak of the α-phase (220), or the Lorentz component on the low-angle side with respect to the central angle of the peak. When polypropylene coexists with at least one of talc or rutile, a specific peak occurs. Therefore, by using the specific peak, the tensile modulus of polypropylene can be grasped.

[0038] Regarding the fifth feature amount, a feature amount based on at least one of SCI, SCE, UVcut, FL, and H can also be used. SCI (Specular Component Include) can be obtained by measuring all reflected light including specularly reflected light (synonymous with specular reflection). SCE (Specular Component Exclude) can be obtained by removing specularly reflected light and measuring only diffusely reflected light (synonymous with diffuse reflection). Physically, SCE represents the unevenness that can exist on the surface of the resin.

[0039] UV cut can be obtained by inserting a filter that cuts ultraviolet rays (UV) from the light source and removing the UV rays for measurement. FL can be obtained by measuring the fluorescence spectrum. Note that the fluorescence spectrum is the SCI spectrum obtained by subtracting the spectrum measured with the UV cut filter inserted from the SCI spectrum measured without the UV cut filter. FL is the spectrum caused by components such as the compatible solvent and antioxidant in the object to be grasped. H is the ratio obtained by dividing the SCE spectrum by the SCI spectrum.

[0040] In this embodiment, as described above, the state is the tensile modulus of elasticity. Therefore, as a feature amount specific to the tensile modulus of elasticity among the fifth feature amounts, at least one of b value (b*), 400 nm of SCE, and 400 nm of UV cut can be used. Also, at least one of b value (b*), L value (L*), b value of UV cut, and 370 nm to 430 nm of SCI can be used. Furthermore, 360 nm to 380 nm can be used as H. Furthermore, 390 nm of FL can also be used. Note that the wavelength physically represents the surface color of the resin.

[0041] In another embodiment, the state of the resin is the tensile yield stress, and the feature amounts include feature amounts (feature amounts specific to the tensile yield stress) having a correlation with the tensile yield stress. By using such feature amounts, the tensile yield stress of the resin can be grasped.

[0042] Specifically, in this embodiment, the resin contains a constitutional unit of propylene. Hereinafter, the resin containing a constitutional unit of propylene is conveniently referred to as a resin such as polypropylene. For such a resin, the first feature amount includes at least one of the carbon content of the resin such as propylene at a predetermined temperature or the progress rate of carbonization of the resin such as propylene in a predetermined temperature range. The predetermined temperature and the predetermined temperature range mentioned here can, for example, apply the description of the predetermined temperature and the predetermined temperature range in the first feature amount in the above-mentioned one embodiment.

[0043] Also, in this case, when the resin is a copolymer of a constituent unit of polypropylene and a constituent unit of polyethylene, the third feature amount is the sum and ratio of the peak intensities corresponding to the constituent units of polyethylene, 2900 cm -1 (CH2 Fermi resonance) peak width, or at least one of the peak positions of 2920 cm -1 (CH2 antisymmetric stretch).

[0044] Furthermore, in this case, the fourth feature amount includes at least one of the peak position of the α-phase (040), the peak intensity of the α-phase (110), the peak position of the α-phase (130), or the amount of the amorphous component.

[0045] These feature amounts show a high correlation with the tensile yield stress of polypropylene and the like. Therefore, by using these feature amounts, the tensile yield stress of polypropylene and the like can be grasped.

[0046] Furthermore, in this case, when the object further contains talc, the fourth feature amount includes the peak width of the α-phase (008). Similar to the above talc and the like, also in this embodiment, by using such a fourth feature amount, the tensile yield stress of polypropylene and the like can be grasped.

[0047] Also, in this embodiment, for the fifth feature amount, a feature amount based on at least one of SCI, UV cut, and FL can also be used. In this embodiment, as described above, the state is the tensile yield stress. Therefore, as a feature amount specific to the tensile yield stress among the fifth feature amounts, the a value and b value (b*) of UV cut among SCI, and 400 nm to 500 nm among FL can be used.

[0048] In yet another embodiment, the state of the resin is the tensile yield strain, and the feature amount includes a feature amount having a correlation with the tensile yield strain (a feature amount specific to the tensile yield strain). By using such a feature amount, the tensile yield strain of the resin can be grasped.

[0049] In this embodiment, the resin is polypropylene. And the first feature quantity includes at least one of the carbon content of polypropylene at a predetermined temperature, the progress rate of carbonization of polypropylene in a predetermined temperature range, the activation energy and the most active temperature of the decomposition reaction of polypropylene in a predetermined temperature range. Here, the predetermined temperature and the predetermined temperature range can be applied, for example, to the description of the predetermined temperature and the predetermined temperature range in the first feature quantity in the above one embodiment.

[0050] The second feature quantity includes at least one of the starting temperature and the heat quantity of the oxidation reaction of polypropylene, or the starting temperature and the heat quantity of the decomposition reaction of polypropylene. Further, when the resin is a copolymer of a structural unit of polypropylene and a structural unit of polyethylene, the third feature quantity may include the sum and ratio of the peak intensities corresponding to the structural units of polyethylene. The third feature quantity may include the peak position at 2920 cm -1 The third feature quantity includes at least one of the sum and ratio of the peak intensities, or the peak position. The fourth feature quantity includes at least one of the peak position of the α-phase (130), the peak intensity of the α-phase (020), or the peak width of the α-phase (13-1).

[0051] These feature quantities show a high correlation with the tensile yield strain of polypropylene. Therefore, by using these feature quantities, the tensile yield strain of polypropylene can be grasped.

[0052] Furthermore, in this embodiment, when the object further contains chlorite, the fourth feature quantity includes the peak position of the α-phase (001). Similar to the above talc and the like, also in this embodiment, by using such a fourth feature quantity, the tensile yield strain of polypropylene can be grasped.

[0053] Also, in this embodiment, for the fifth feature quantity, a feature quantity based on at least one of SCI, SCE, UVcut, and FL can also be used. In this embodiment, the state is the tensile yield strain as described above. Therefore, as a feature quantity specific to the tensile yield strain among the fifth feature quantities, at least one of the a value (a*) of SCE, 400 nm, the a value of UVcut, and the b value (b*) of UVcut can be used. Also, at least one of the b value (b*) of SCI, the a value of UVcut, the b value of UVcut, and 360 nm to 410 nm can be used. Further, 400 nm to 440 nm of FL can also be used.

[0054] Table 1 and Table 2 below are tables that extract and summarize some of the feature quantities obtained in each of the above embodiments.

[0055]

Table 1

[0056]

Table 2

[0057] Thus, the resin contains polypropylene, and the feature quantity is a feature quantity that has a correlation with the tensile mechanical properties of polypropylene. Thereby, using the state grasping system 10, the tensile mechanical properties of an object containing polypropylene as waste resin can be grasped.

[0058] Returning to the embodiment shown in FIG. 1, the extraction unit 5 is an extraction device that extracts feature quantities from the data (measured data and experimental data regarding feature quantities) acquired by the acquisition unit 4. However, the extraction unit 5 may be a part of the functional units constituting the state grasping device 20 (FIG. 3).

[0059] The specific method of extraction is not limited. For example, it can be extracted by fitting the data (for example, raw data) obtained by the acquisition unit 4 to an arbitrary model function.

[0060] Specifically described for each feature amount, the first feature amount can be extracted, for example, by fitting the data obtained by a thermal mass measurement device using the Sestak-Berggren function. The second feature amount can be extracted by fitting the data obtained by a differential thermal measurement device using a plurality of Extreme functions. The third feature amount can be extracted by fitting the data obtained by infrared spectroscopic measurement using a plurality of pseudo-Voigt functions. The fourth feature amount can be extracted by fitting the data obtained by a wide-angle X-ray diffractometer using a plurality of asymmetric pseudo-Voigt functions.

[0061] However, the extraction is not limited to fitting to a model function. That is, as the fifth feature amount, the data itself obtained by a color measurement device can be used as a feature amount.

[0062] The grasping unit 6 is a grasping device that grasps (predicts, infers, determines) the state (characteristics) of the resin from the feature amount extracted by the extraction unit 5 and a state grasping model that grasps the state of the resin. However, the grasping unit 6 may be a part of the functional unit that constitutes the state grasping device 20 (FIG. 3).

[0063] The state grasping model is a model constructed in advance, and is a model that outputs the state of the resin (for example, tensile mechanical properties) by inputting a feature amount. The state grasping model is, for example, a machine learning model that can be constructed by supervised learning. The state grasping model can be constructed by any method. For example, it can be constructed by performing machine learning with the above-described respective feature amounts as explanatory variables and the state of the resin (such as tensile mechanical properties) as an objective variable.

[0064] The production record DB3 is a database that records whether the state of each resin has been grasped in the past. In the production record DB3, the states grasped in the past are recorded for each resin characteristic. Each resin characteristic (each characteristic of the object) means, for example, characteristics such as the name of the resin, the collection location of the collected object, the collection time, the type of structure (such as home appliances, vehicles, etc., by use, etc.) in which the resin contained in the object was used. By providing the production record DB3, it is possible to confirm whether the resin whose state is to be grasped by the state grasping system 10 of the present disclosure has already been grasped in the past. And for resins that have already been grasped, the state can be grasped without extracting feature amounts. Thereby, the time for state grasping can be reduced.

[0065] FIG. 2 is a diagram for explaining the content included in the production record DB3 of the first embodiment. In FIG. 2, only information on polypropylene is exemplified as an example, but as described above, for resins other than polypropylene, the following information is also recorded.

[0066] In the production record DB3, catalog information of polypropylene existing in the market is recorded. Specifically, for example, information on the manufacturer and model number of polypropylene, information on the properties of polypropylene, information on additives to polypropylene, recommended processing conditions for polypropylene, etc. are recorded. Furthermore, literature information on polypropylene is recorded. Specifically, for example, information on the properties before and after compounding of polypropylene (if virgin polypropylene is compounded into waste polypropylene, how the properties such as tensile mechanical properties change), information on additives to polypropylene, etc. are recorded. Furthermore, experimental information on polypropylene is also recorded. Specifically, for example, analysis information on polypropylene, information on the properties before and after compounding of polypropylene, information on additives to polypropylene, information on deterioration of polypropylene, etc. are recorded.

[0067] FIG. 3 is a flowchart showing a state grasping method (hereinafter referred to as the state grasping method of the present disclosure) executed by the state grasping system 10 of the first embodiment. The state grasping method of the present disclosure includes steps S11 to S17. In the following, although the state exemplifies the tensile mechanical properties, the following description can be similarly applied to other states.

[0068] First, a user who wants to grasp the tensile mechanical properties of an object containing resin obtains the object (step S11). The user inputs the characteristics of the object (for example, the name of the resin) to the output unit 2. Thereby, the state grasping system 10 (for example, the acquisition unit 4) checks whether there are the same characteristics in the production result DB3 (step S12). If so (Yes), the state grasping system 10 (for example, the acquisition unit 4) acquires the tensile mechanical properties recorded in the production result DB3 (step S13). The output unit 2 outputs the acquired tensile mechanical properties (the grasping result in the grasping unit 6). For example, the acquired tensile mechanical properties are displayed on the display device (for example, a monitor) of the output unit 2.

[0069] On the other hand, if it is not in the production result DB3 (No), the tensile mechanical properties of the object are unknown. Therefore, the acquisition unit 4 acquires data on the feature amount related to the state of the resin by analyzing the object containing resin (acquisition step, step S14). Specifically, the acquisition unit 4 measures the object by at least one of measurement methods such as thermogravimetry (TG), differential thermal analysis (DTA), IR (infrared spectroscopy), and WAXS (wide-angle X-ray diffraction) (step S14).

[0070] Next, the extraction unit 5 extracts the feature amount from the data acquired in step S14 (acquisition step) (extraction step, step S15). Specifically, the extraction unit 5 extracts the feature amount (for example, the first feature amount to the fifth feature amount) by an extraction method corresponding to the measurement method (step S15). More specifically, the extraction is performed along the extraction method by the extraction unit 5 with reference to FIG. 1 above.

[0071] Finally, the grasping unit 6 grasps the state of the resin (grasping step, steps S16 and S17) from the feature amount extracted in step S15 (extraction step) and the state grasping model for grasping the state. Specifically, the grasping unit 6 inputs the extracted feature amount into a pre-constructed state grasping model (step S16). The state grasping model outputs tensile mechanical properties from the input feature amount, whereby the tensile mechanical properties are obtained (step S17, output step). Specifically, the output unit 2 outputs the obtained tensile mechanical properties (grasping result at the grasping unit 6), and for example, the obtained tensile mechanical properties are displayed on the display device (e.g., monitor) of the output unit 2.

[0072] FIG. 4 is a block diagram showing the state grasping device 20 of the first embodiment. The state grasping device 20 is realized by one device integrating the above-mentioned production result DB3, acquisition unit 4, extraction unit 5, and grasping unit 6. Therefore, the state grasping device 20 includes the production result DB3, acquisition unit 4, extraction unit 5, and grasping unit 6.

[0073] As a specific hardware configuration, the state grasping device 20 includes a processor 41 (such as a CPU), a memory 42, a storage device 43, and a communication device 44 (such as an interface). These hardware configurations can be similarly applied to the extraction device as the above-mentioned extraction unit 5 and the grasping device as the grasping unit 6.

[0074] FIG. 5 is a block diagram showing the state grasping system 10 of the second embodiment. The second embodiment is suitable for, for example, the development of new materials. Specifically, for the material synthesized by the user, the grasped tensile mechanical properties and the feature amounts (effective feature amounts) that effectively contributed to the grasping are presented to the user. Then, the user can infer the physicochemical phenomena that exhibit the tensile mechanical properties using the presented information and utilize it for the conditions of the next synthesis experiment.

[0075] The state grasping system 10 of the second embodiment further includes an effective feature amount determination unit 7. The effective feature amount determination unit 7 is an effective feature amount determination device that determines which feature amount among a plurality of feature amounts related to the state of the resin is effective, that is, which feature amount affects the state of the resin. However, the effective feature amount determination unit 7 may be a part of the functional unit that constitutes the state grasping device 20 (Fig. 5). That is, the state grasping device 20 may further include the effective feature amount determination unit 7.

[0076] The method for calculating the effective feature amount (method for determining the effective feature amount) is not particularly limited. For example, a decision tree-based algorithm that can be attached to the above state grasping model can be used. In such a state grasping model, the input is the feature amount, and the output is the state of the resin and the effective feature amount. The effective feature amount is an index obtained by quantifying the degree of effectiveness, and is also referred to as, for example, the contribution degree (contribution rate) below. The higher the contribution degree, the higher the degree of effectiveness and the higher the correlation (relevance) to the state. Therefore, for example, if it is desired to control the tensile mechanical properties, it is advantageous to control the feature amount with a relatively high contribution degree.

[0077] Also, as the decision tree-based algorithm, for example, gradient boosting decision tree, random forest, decision tree, etc. can be used. Subspecies of these may also be used. Since the feature amount has a very high sparsity, a decision tree-based algorithm that can classify by the presence or absence of a numerical value can be preferably used.

[0078] In the example of the present disclosure, for example, the Gini impurity G(k) (indicating the badness of classification at node k) represented by the following formulas (1) and (2) is used.

[0079]

Number

[0080] In formula (1), G(k) is the impurity at a certain node k. n is the number of target labels. p(i) is the frequency of the target label i at a certain node k.

[0081]

Number

[0082] In Equation (2), I(j) is the importance of a certain feature j. F(j) is the set of nodes for which a certain feature j is the target of splitting. Nparent(i) is the number of samples at a certain node i. Nleft_child(i) is the number of samples of the left node among the child nodes of a certain node i. Nright_child(i) is the number of samples of the right node among the child nodes of a certain node i. Gparent(i) is the Gini impurity at a certain node i. Gleft_child(i) is the Gini impurity at the left node among the child nodes of a certain node i. Gright_child(i) is the Gini impurity at the right node among the child nodes of a certain node i.

[0083] Also, the SHAP value can be used to determine the effective features. The SHAP value is a value approximately calculated by a simple calculation of the Shapley value, and it is a value indicating how much each feature affects the predicted value.

[0084] In the example of the present disclosure, the effective feature determination unit 7 calculates the degree of influence on the state of the resin, that is, the contribution degree, for a plurality of features. Thereby, it becomes easy to determine which feature is effective. The higher the contribution degree, the higher the degree of influence on the state of the resin, and the lower the contribution degree, the smaller the degree of influence on the state of the resin. Therefore, by being able to grasp the contribution degree, it becomes easier to control the state of the resin.

[0085] FIG. 6 is a diagram for explaining the production result DB3 of the second embodiment. In the second embodiment, in addition to the content of the production result DB3 (FIG. 2) of the first embodiment, features (effective features) that effectively contribute to the state grasping model are further recorded.

[0086] FIG. 7 is a flowchart showing a state grasping method executed by the state grasping system 10 of the second embodiment. The user is, for example, a person who wants to develop a new material using tensile mechanical properties as an index. The user newly synthesizes a sample (resin) (step S21). It is confirmed whether the newly synthesized sample exists in the production result DB3 (step S22). The confirmation method is the same as that of the first embodiment (hereinafter, the same confirmation is performed in the third and subsequent embodiments). If it exists (Yes), the user formulates other target values or specifications (step S23). In step S23, if the production result DB3 records that another user other than the user who synthesized the new sample synthesized the same type of resin (similar resin), the user formulates other tensile mechanical properties or other specifications.

[0087] On the other hand, if it does not exist in step S22 (No), steps S24 to S27 are performed in the same manner as steps S14 to S16 (step S24: acquisition step, step S25: extraction step, steps S26 and S27: grasping step, output step). However, in the second embodiment, the state grasping model takes a plurality of feature amounts as inputs and outputs the state and contribution degree of the resin. Therefore, the effective feature amount determination unit 7 determines the contribution degree, which is an effective feature amount, using the state grasping model. As a result, in step S28 (output step), the feature amounts (effective feature amounts, contribution degrees) that contributed to the grasping are also obtained. Specifically, the output unit 2 outputs the obtained tensile mechanical properties and feature amounts (both are the grasping results in the grasping unit 6), and for example, the obtained tensile mechanical properties and feature amounts are displayed on the display device (for example, a monitor) of the output unit 2.

[0088] FIG. 8 is a diagram showing the output result output in the second embodiment. FIG. 8 is a graph showing a y-y plot with the measured values of the tensile mechanical properties on the horizontal axis and the predicted values of the tensile mechanical properties on the vertical axis. FIG. 8 is a graph obtained by randomly performing cross-validation 100 times to examine the accuracy of the state grasping model, and one of the execution results is extracted therefrom. For example, the graph shown in FIG. 8 is output to the output unit 2 provided in the state grasping system 10, for example. The output unit 2 includes, for example, a display device, and the graph is displayed on the display device, for example.

[0089] In the graph shown in FIG. 8, the plot (dot-shaped circle) of the training data used for constructing the state grasping model is shown, and an ideal straight line on which the training data lies is also shown. In addition, the plot (black and white) of the test data for grasping the tensile mechanical properties using the state grasping model is also shown together with the R 2 value. A user referring to FIG. 8 can recognize the high accuracy of grasping the tensile mechanical properties using the state grasping model.

[0090] FIG. 9 is a diagram showing the output result output in the second embodiment, and is a different diagram from FIG. 8. The graph (box-and-whisker plot) shown in FIG. 9 is a graph showing the statistical R 2 of the prediction accuracy when randomly performing cross-validation of the y-y plot 100 times in the same manner as in FIG. 8 above. The horizontal axis represents the tensile elastic modulus, tensile yield strain, and tensile yield stress as the tensile mechanical properties. The vertical axis is the R 2 value. A user referring to FIG. 9 can recognize the high accuracy of grasping using the state grasping model for any of the tensile elastic modulus, tensile yield strain, and tensile yield stress.

[0091] FIG. 10 is a diagram showing the output result output in the second embodiment, and is a different diagram from FIGS. 8 and 9. FIG. 10 is a graph (box-and-whisker plot) showing the contribution degree (contribution rate, effective rate, effectiveness) obtained using the state grasping model. FIG. 10 is a graph with the explanatory variables (features) on the horizontal axis and the contribution degree on the vertical axis. The contribution degree is shown for each explanatory variable. The graph shown in FIG. 10 is a graph showing the contribution degree statistically when randomly performing cross-validation of the y-y plot 100 times in the same manner as in FIG. 8 above.

[0092] The greater the width of the contribution degree (length in the vertical axis direction), the greater the contribution degree. Therefore, the user referring to FIG. 10 can intuitively grasp the height of the contribution degree for each feature amount shown on the horizontal axis. In the illustrated example, among the plurality of explanatory variables, it can be recognized that the feature amount corresponding to the leftmost explanatory variable contributes the most (has a high contribution degree).

[0093] In the above second embodiment, the user can know the feature amounts that are likely to affect the tensile mechanical properties based on the contribution degree. Thereby, the user can infer the physicochemical phenomenon from the grasped tensile mechanical properties and the contribution degree of the feature amounts, and devise the next experiment.

[0094] FIG. 11 is a block diagram showing the state grasping system 10 of the third embodiment. In the third embodiment, for waste resin with unknown characteristics (for example, in pellet form), the tensile mechanical properties and the degree of resin degradation are grasped using the state grasping model. Then, based on the grasped tensile mechanical properties and the degree of resin degradation, creation conditions such as, for example, the amount of virgin material to be newly added and the amount of waste resin to be used are proposed according to the target tensile mechanical properties of the recycled resin. The recycled resin includes waste resin and, for example, virgin material, and is the resin newly used by the user.

[0095] The state grasping system 10 of the third embodiment further includes a degradation degree grasping unit 8 and a proposal unit 9. The degradation degree grasping unit 8 is a device that grasps the degree of degradation of waste resin with unknown characteristics. However, the degradation degree grasping unit 8 may be a part of the functional units constituting the state grasping device 20 (FIG. 3). That is, the state grasping device 20 may further include the degradation degree grasping unit 8.

[0096] The degree of degradation of the waste resin is the degree of degradation with respect to virgin resin. Usually, additives such as antioxidants and flame retardants are mixed in the resin. For example, due to the aging degradation of the resin, the properties of the additives change or decompose. Therefore, in the example of the present disclosure, the degree of degradation of the waste resin can be grasped by grasping such changes and decompositions of the additives.

[0097] The determination of the degree of deterioration can be performed, for example, using the deterioration degree determination model stored in the deterioration degree determination unit 8. The deterioration degree determination model is included in, for example, the above state determination model. The deterioration degree determination model can be constructed, for example, by machine learning using physical properties obtained from a deterioration test using virgin materials by an acceleration test as explanatory variables and physical properties of resin as target variables. As a specific method of machine learning, it can be constructed, for example, by the same method as the above state determination model.

[0098] The proposal unit 9 is a device that proposes conditions (manufacturing conditions, recipe) capable of producing a recycled resin having functions desired by the user. However, the proposal unit 9 may be a part of the functional units constituting the state determination device 20 (Fig. 3). That is, the state determination device 20 may further include the proposal unit 9.

[0099] For example, when the degree of deterioration of the waste resin is relatively large, the functions of the resin (such as tensile mechanical properties) may be lower than those of the virgin material (such as tensile mechanical properties). Therefore, in this case, by using a relatively large amount of virgin material in combination with the waste resin, the functions of the recycled resin composed of the waste resin and the virgin material can be restored.

[0100] The proposed manufacturing conditions can be determined, for example, using the proposal model stored in the proposal unit 9. The proposal model can be constructed, for example, by machine learning using the performance (such as tensile mechanical properties) and degree of deterioration of the waste resin as explanatory variables and the performance (such as tensile mechanical properties) of the recycled resin composed of the waste resin and the virgin material as target variables. As a specific method of machine learning, it can be constructed, for example, by the same method as the above state determination model. For the construction of the proposal model, data described in catalogs, documents, etc. can be used, for example.

[0101] Fig. 12 is a diagram for explaining the manufacturing result DB3 of the third embodiment. In the third embodiment, in addition to the contents of the manufacturing result DB3 (Fig. 6) of the second embodiment, descriptors that effectively contribute to the proposal model (recipe design model) are further recorded. Descriptors are, for example, properties before blending, information on blends, processing conditions, etc.

[0102] FIG. 13 is a flowchart showing a state grasping method executed by the state grasping system 10 of the third embodiment. The user is, for example, a person who wants to improve the tensile mechanical properties of recycled resin using waste resin (to make the desired tensile mechanical properties). The user obtains waste resin (step S31). It is confirmed whether the obtained waste resin exists in the production result DB3 (step S32). If it exists (Yes), recycled resin is synthesized under the production conditions in the production result DB3 (step S33).

[0103] On the other hand, if it does not exist in the production condition DB3 (No), steps S34 to S36 are executed in the same manner as steps S14 to S16 (FIG. 3) (step S34: acquisition step, step S35: extraction step, steps S36, S37: grasping step, output step). Further, the degradation degree grasping unit 8 also inputs the feature amount extracted in step S35 (the same as step S15 above) to the degradation degree grasping model (step S39). Then, by the degradation degree grasping model outputting the degradation degree, the degradation degree is acquired (grasped) (step S40, output step). Specifically, the output unit 2 outputs the acquired tensile mechanical properties and degradation degree (both are the grasping results by the grasping unit 6), and for example, the acquired tensile mechanical properties and degradation degree are displayed on the display device (for example, a monitor) of the output unit 2.

[0104] The proposal unit 9 inputs the tensile mechanical properties and degradation degree acquired in steps S37 and S40 to the proposal model (step S38). Thereby, the proposed production conditions are acquired (step S41, output step). Specifically, the output unit 2 outputs the production conditions, which are the information obtained using the acquired tensile mechanical properties and degradation degree, and the acquired production conditions are displayed on the display device (for example, a monitor) of the output unit 2.

[0105] FIG. 14 is a flowchart showing a state grasping method executed by the state grasping system 10 of the fourth embodiment. As the state grasping system 10 of the fourth embodiment, for example, the state grasping system 10 shown in FIG. 5 above can be used. Further, the fourth embodiment can be executed in combination with at least one of the first to third embodiments above, for example. In the fourth embodiment, an existing state grasping model is refined. Thereby, the accuracy of state grasping can be improved.

[0106] First, a user who wants to improve the state grasping model obtains an object containing a resin whose state is to be grasped (step S51). Further, the user designs the compounding conditions and / or process conditions (step S51). Then, step S52 is performed in the same manner as step S12 (FIG. 3) above. If it exists (Yes), consider using another object or the compounding conditions and / or process conditions recorded in the production result DB3 (step S53).

[0107] On the other hand, if it does not exist (No in step S52), data is acquired and features are extracted in the same manner as steps S14 and S15 above (steps S54, S55). The acquisition of data is performed by the acquisition unit 4, and the extraction of features is performed by the extraction unit 5. Also, together with steps S54 and S55, the object (for example, pellets) is processed into the shape of a test piece for evaluating the tensile mechanical properties (step S57). By evaluating the tensile mechanical properties using the test piece, the tensile mechanical properties are obtained (i.e., actually measured) (step S58). The features and tensile mechanical properties obtained in steps S55 and S58 are associated with the features and the tensile mechanical properties and stored in the production result DB3 (step S56).

[0108] In the same manner as the above step S28 (FIG. 7), the feature amounts (effective feature amounts) that contributed to the grasping are acquired (step S59). The acquisition of the effective feature amounts is performed by the effective feature amount determination unit 7. At the same time, in the fourth embodiment, the effective feature amount determination unit 7 further limits the feature amounts (explanatory variables) that constitute the state grasping model to the effective feature amounts (step S59). By doing so, it is possible to relatively increase the feature amounts that are likely to affect the tensile mechanical properties (high contribution degree). As a result, since the state grasping model is configured to include many feature amounts with relatively high contribution degrees, the grasping accuracy can be improved and the grasping calculation can be speeded up. For example, it is possible to handle, as effective feature amounts, those within a predetermined number, such as the top five when the feature amounts are arranged in descending order of contribution degree being equal to or greater than a predetermined value.

[0109] Then, the data stored in the above step S56 (including the data in which the feature amounts are limited to the effective feature amounts) is added to the production result DB3, and the state grasping model is constructed again (step S60). The construction of the state grasping model is performed by the grasping unit 6.

[0110] FIG. 15 is a flowchart showing the state grasping method executed by the state grasping system 10 of the fifth embodiment. As the state grasping system 10 of the fifth embodiment, for example, the state grasping system 10 shown in FIG. 11 above can be used. Also, the fifth embodiment can be executed in combination with at least one of the above first to third embodiments, for example. Further, the fifth embodiment can also be executed in combination with the above fourth embodiment. In the fifth embodiment, the existing degradation degree grasping model is refined. Thereby, the grasping accuracy of the degradation degree can be improved.

[0111] A user who wishes to improve the deterioration level grasping model obtains an object (waste resin, etc.) containing deteriorated resin (step S71). The user considers other raw materials, etc. and extracts features in the same manner as in steps S52 to S55 (all in FIG. 14) described above (steps S72 to S75). In addition to steps S74 and S75, the user measures the object by a method for measuring a deterioration index (for example, the concentration of additives such as antioxidants and flame retardants in the object) (step S76). In step S76, the object is measured from a different perspective than in step S74.

[0112] The feature amount and the deterioration index are linked, as will be described in detail later in step S78. This creates a correlation between the feature amount and the deterioration index. In addition, the deterioration level grasping model uses the deterioration index as the objective variable and other analysis results (for example, feature amount based on the differential heat, etc.) as the explanatory variable. Therefore, in step S80 described later, the deterioration level grasping model can be constructed.

[0113] The measurement of the object in step S76 may be performed by the same method as that used in step S74, and step S74 may also serve as step S76. In step S76, a degradation index is acquired (step S77).

[0114] The degradation index and the feature amount obtained by a different analysis are linked to each other and stored in the manufacturing record DB3 (step S78).Then, the explanatory variables are limited in the same manner as in step S59 (FIG. 14) (step S79).Finally, the data newly stored in the manufacturing record DB3 (including data in which the feature amount is limited to the effective feature amount) is added to reconstruct the degradation degree grasping model (step S80).

[0115] FIG. 16 is a block diagram showing the state grasping system 10 of the sixth embodiment. As the state grasping system 10 of the sixth embodiment, for example, the state grasping system 10 shown in FIG. 11 above can be used. Further, the sixth embodiment can be executed in combination with at least one of the first to third embodiments above, for example. Furthermore, the sixth embodiment can be executed in combination with at least one of the fourth or fifth embodiments above.

[0116] In the sixth embodiment, the production result DB 3 is connected to the network 11, and the production result DB 3 is updated using external public information via the network 11. Then, the proposed model recorded in the proposal unit 9 is reconstructed and refined using the updated production result DB 3.

[0117] FIG. 17 is a flowchart showing the state grasping method executed by the state grasping system 10 of the sixth embodiment. In the sixth embodiment, a recipe design model capable of designing (determining, proposing) a manufacturing method (recipe) for manufacturing a target recycled resin from waste resin is constructed.

[0118] First, the blending information of the resin is obtained (step S91). The obtaining is performed by, for example, the acquisition unit 4 via the network 11. The blending information of the resin is, for example, the characteristics of the resin before and after blending, the type, amount, size of the blend, and processing conditions for obtaining tensile mechanical properties. The blending information of the resin is information publicly available outside, such as information based on experiments and information described in documents such as papers and catalogs. Next, the obtained blending information is organized (step S92). The organizing is performed by, for example, the acquisition unit 4. The form of the information, such as the unit and descriptor, differs depending on the information source. Therefore, for example, the unit is unified and grouped. The organized information is stored in the production result DB 3 (step S93).

[0119] Of the information stored in the production result DB 3, it is determined whether the explanatory variables (features) effective for predicting the target variable (tensile mechanical properties) are effective and known (for example, obvious) features (step S94). The determination is executed by, for example, the effective feature determination unit 7. For example, it is known that if an object containing resin further contains talc, the tensile mechanical properties (for example, tensile elastic modulus) of the object are improved. Therefore, if it is known and effective (Yes), the effective feature determination unit 7 limits the explanatory variables to known and effective features (step S95). Next, the processes after step S96 are performed.

[0120] On the other hand, if it is not known (No), the proposal unit 9 constructs a recipe design model with the tensile mechanical properties after compounding as the target variable and the tensile mechanical properties before compounding and the information of the compounded material as the explanatory variables (step S96). The construction is executed by arbitrary machine learning. The proposal unit 9 performs Bayesian optimization on the constructed recipe design model with the user's target specifications (target tensile mechanical properties) to derive the values of the explanatory variables (step S97). In step S96 above, it is the "forward direction" in which a recipe design model for deriving the value of the target variable from the explanatory variables is constructed, but in step S97, the values of the explanatory variables are derived from the target variable by a method such as Bayesian optimization.

[0121] The derived values of the explanatory variables are the information of the compounded material described in step S91 above. Therefore, by using the information of the compounded material derived here as recipe information (design conditions, manufacturing conditions), a recycled resin having the target tensile mechanical properties can be designed.

Explanation of Signs

[0122] 1, 11 Network 10 State Grasping System 2 Input / Output Device 20 State Grasping Device 3 Production Result DB 4 Acquisition Unit 5 Extraction Unit 6 Grasping Unit 7 Effective Feature Determination Unit 8 Degradation Degree Grasping Unit 9 Proposal Department

Claims

1. An acquisition unit that acquires data on a feature quantity related to the state of the resin by analyzing an object containing the resin; An extraction unit that extracts the feature quantity from the data acquired by the acquisition unit; A grasping unit that grasps the state of the resin from the feature quantity extracted by the extraction unit and a state grasping model that grasps the state; An output unit that outputs at least one of the grasping result by the grasping unit or information obtained using the grasping result. A state grasping system characterized by the above.

2. The state grasping system according to Claim 1, wherein the feature quantity acquired by the acquisition unit includes a first feature quantity based on the thermal mass obtained by measuring the thermal mass of the resin in an air environment, a second feature quantity based on the amount of heat obtained by differential thermal measurement of the resin in an air environment, a third feature quantity based on infrared spectroscopy obtained by infrared spectroscopic measurement of the resin, a fourth feature quantity based on wide-angle X-ray diffraction obtained by wide-angle X-ray diffraction measurement of the resin, or a fifth feature quantity based on the color obtained by color measurement of the resin, and includes at least one of the feature quantities. A state grasping system characterized by the above.

3. The state grasping system according to Claim 2, wherein the state is the tensile modulus of elasticity, and the feature quantity includes a feature quantity having a correlation with the tensile modulus of elasticity. A state grasping system characterized by the above.

4. The state grasping system according to Claim 3, wherein the resin is polypropylene, the first feature quantity includes the carbon content of polypropylene at a predetermined temperature, the progress rate of carbonization of polypropylene in a predetermined temperature range, the reaction amount of the oxidation reaction of polypropylene in a predetermined temperature range, or the activation energy and reaction amount of the decomposition reaction of polypropylene in a predetermined temperature range, and includes at least one of them, the second feature quantity includes the number of modes and the maximum heat generation temperature of the oxidation reaction of polypropylene, or the heat generation amount of the decomposition reaction of polypropylene, and includes at least one of them, the third feature quantity includes 2920 cm -１ the peak position, or 2960 cm －１ peak intensity, at least one of them, the fourth feature quantity includes the peak position of the α phase (110), the peak position and width of the α phase (130), the peak intensity of the α phase (220), or the peak position of the α phase (040), and includes at least one of them. A state grasping system characterized by the above.

5. The state grasping system according to Claim 4, wherein the fourth feature quantity is when the object further contains talc, the peak intensity of the α phase (002), or The peak intensity of the α-phase (006), including at least one of when the object further contains rutile, the peak intensity of the α-phase (110), at least one of the intensity or width of the peak of the α-phase (220), or the Lorentz component on the low-angle side with respect to the central angle of the peak including at least one of A state grasping system characterized by this.

6. A state grasping system according to claim 2, wherein the state is the tensile yield stress, and the feature amount includes a feature amount having a correlation with the tensile yield stress is A state grasping system characterized by this.

7. A state grasping system according to claim 6, wherein the resin is a resin such as polypropylene containing a constitutional unit of propylene, the first feature amount is the carbon content of the resin such as polypropylene at a predetermined temperature, or the rate of progress of carbonization of the resin such as polypropylene in a predetermined temperature range, including at least one of the third feature amount is when the resin is a copolymer of a constitutional unit of polypropylene and a constitutional unit of polyethylene, the sum and ratio of the peak intensities corresponding to the constitutional unit of polyethylene, 2900 cm －１ peak width, or 2920 cm －１ peak position, including at least one of the fourth feature amount is the peak position of the α-phase (040), the peak intensity of the α-phase (110), the peak position of the α-phase (130), or the amount of amorphous component, including at least one of A state grasping system characterized by this.

8. A state grasping system according to claim 7, wherein the fourth feature amount is when the object further contains talc, including the peak width of the α-phase (008) A state grasping system characterized by this.

9. A state grasping system according to claim 2, wherein the state is the tensile yield strain, and the feature amount includes a feature amount having a correlation with the tensile yield strain A state grasping system characterized by this.

10. A state grasping system according to claim 9, wherein the resin is polypropylene, the first feature amount is the carbon content of polypropylene at a predetermined temperature, the rate of progress of carbonization of polypropylene in a predetermined temperature range, the activation energy and the most active temperature of the decomposition reaction of polypropylene in a predetermined temperature range, including at least one of the second feature amount is the starting temperature and heat quantity of the oxidation reaction of polypropylene, or the starting temperature and heat quantity of the decomposition reaction of polypropylene, including at least one of the third feature amount is When the resin is a copolymer of a constituent unit of the polypropylene and a constituent unit of the polyethylene, the sum and ratio of the peak intensities corresponding to the constituent units of the polyethylene, or 2920 cm －１ the peak position of, includes at least one of The fourth feature amount is the peak position of the α-phase (130), the peak intensity of the α-phase (020), or the peak width of the α-phase (13 - 1), includes at least one of A state grasping system characterized by this.

11. The state grasping system according to claim 10, wherein The fourth feature amount is when the object further contains chlorite, includes the peak position of the α-phase (001) A state grasping system characterized by this.

12. The state grasping system according to claim 1, wherein the state includes a state regarding the structure of the resin that affects the tensile mechanical properties of the resin among the structures of the resin A state grasping system characterized by this.

13. The state grasping system according to claim 1, wherein the resin contains polypropylene, the feature amount is a feature amount having a correlation with the tensile mechanical properties of polypropylene A state grasping system characterized by this.

14. An acquisition unit that acquires data on a feature amount related to the state of the resin by analyzing an object containing the resin, an extraction unit that extracts the feature amount from the data acquired by the acquisition unit, a grasping unit that grasps the state of the resin from the feature amount extracted by the extraction unit and a state grasping model for grasping the state, and an output unit that outputs at least one of the grasping result in the grasping unit or information obtained using the grasping result. A state grasping device characterized by this.

15. An acquisition step of acquiring data on a feature amount related to the state of the resin by analyzing an object containing the resin, an extraction step of extracting the feature amount from the data acquired in the acquisition step, a grasping step of grasping the state of the resin from the feature amount extracted in the extraction step and a state grasping model for grasping the state, and an output step of outputting at least one of the grasping result in the grasping step or information obtained using the grasping result. A state grasping method characterized by this.

Images