Prediction system, prediction method, and program

Abstract

Provided are a prediction system and a prediction method with which it is possible to more accurately predict the characteristics of a resin molded article. A prediction system 1 comprises an acquisition unit (CPU 110) that acquires first measurement information obtained through measurement of a resin molded article performed by an ultrasonic measurement device and second measurement information obtained through measurement of the resin molded article by one or a plurality of characteristic measurement devices different from the ultrasonic measurement device, and a prediction unit (CPU 110) that predicts the toughness of the resin molded article and / or the rigidity resulting from thermal deformation of the resin molded article on the basis of the acquired first measurement information and second measurement information, the characteristic measurement device measuring at least one from among the acoustic characteristics, the atomic characteristics, the electrical characteristics, the magnetic characteristics, the mechanical characteristics, the optical characteristics, the radiation characteristics, the thermal characteristics, and the surface state of the resin molded article.

Description

Prediction system, prediction method, and program

[0001] The present invention relates to a prediction system, a prediction method, and a program.

[0002] In recent years, resin molded products have attracted attention in various fields, such as space, aircraft, automobiles, ships, fishing rods, electrical components, electronic components, home appliance components, parabolic antennas, bathtubs, flooring materials, and roofing materials. Under these circumstances, there is a need to accurately predict the properties of resin molded products. Patent Document 1 discloses that ultrasonic measurements of a resin molded product are performed in directions parallel and perpendicular to the molding direction, and multiple parameters are selected from the amplitude, sound velocity, or frequency obtained by the measurements to predict specific gravity, porosity, compressive strength, bending strength, and the like.

[0003] Japanese Patent Application Laid-Open No. 2004-170099

[0004] However, although ultrasonic measurements are carried out in Patent Document 1, the toughness of a resin molded product and its rigidity due to thermal deformation cannot be predicted by ultrasonic measurements alone.

[0005] An object of the present invention is to provide a prediction system and a prediction method that can more accurately predict the toughness of a resin molded product and the rigidity due to thermal deformation.

[0006] In order to solve the above problem, the prediction system of the present invention comprises: an acquisition unit that acquires first measurement information obtained by measuring a resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the characteristics of the resin molded product using one or more characteristic measurement devices different from the ultrasonic measurement device; and a prediction unit that predicts the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, wherein the characteristic measurement device is a device that measures at least one of the acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface condition of the resin molded product.

[0007] Furthermore, in order to solve the above-mentioned problems, the prediction method of the present invention is a prediction method using a prediction device, and includes: an acquisition step of acquiring first measurement information obtained by measuring a resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the characteristics of the resin molded product using one or more characteristic measurement devices different from the ultrasonic measurement device; and a prediction step of predicting the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, wherein the characteristic measurement device is a device that measures at least one of the acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface condition of the resin molded product.

[0008] In addition, in order to solve the above problem, the program of the present invention is a program that causes a computer of a prediction device to execute: an acquisition step of acquiring first measurement information obtained by measuring a resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the characteristics of the resin molded product using one or more characteristic measurement devices different from the ultrasonic measurement device; and a prediction step of predicting the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, wherein the characteristic measurement device is a device that measures at least one of the acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface condition of the resin molded product.

[0009] According to the present invention, the toughness of a resin molded product and its rigidity due to thermal deformation can be predicted with higher accuracy.

[0010] It is a diagram showing the overall configuration of a prediction system. It is a block diagram showing a schematic configuration of a prediction device. It is a diagram explaining the principle of a Talbot interferometer. It is a flowchart showing a prediction process. It is a flowchart showing a machine learning method of a trained model.

[0011] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings, but the scope of the invention is not limited to the illustrated examples.

[0012] <Configuration of Prediction System 1> Fig. 1 is a diagram showing the overall configuration of the prediction system 1. As shown in Fig. 1, the prediction system 1 includes, for example, a prediction device 100, an ultrasonic measurement device 200, and a characteristics measurement device 300. Note that Fig. 1 shows a case where there is one characteristics measurement device 300, but there may be multiple characteristics measurement devices 300.

[0013] This prediction system 1 predicts the toughness and thermal deformation stiffness of resin molded products. Toughness refers to the tenacity of a resin molded product. Toughness is a property distinct from surface hardness, and toughness makes a product more likely to absorb energy and break when subjected to a strong impact. Such toughness is primarily measured by tensile testing, but can also be measured by various other impact tests. Specific examples include tensile breaking strain, nominal tensile breaking strain, tensile strength strain, nominal tensile strain, tensile yield strain, elongation at break, tensile elongation (obtained using a Tensilon universal testing machine or the like (ISO 527-1, 2, K7161)), fracture toughness, and impact strength (obtained using a Charpy impact test or an Izod impact test (JIS K7111)). Stiffness refers to the resistance to dimensional change when external bending or twisting forces are applied. The present invention improves the accuracy of predicting stiffness due to thermal deformation. The rigidity is also an index of heat resistance, and specifically includes the deflection temperature under load (JIS K7191), the coefficient of linear expansion, and the Picat softening temperature.

[0014] Resin molded products are products molded solely from resin, or composite materials containing fillers and resin.

[0015] Examples of the resin include known thermosetting resins and thermoplastic resins. Specific examples include polyolefin resins such as polyethylene resin (PE), polypropylene resin (PP), and maleic anhydride-modified polypropylene (MAHPP), epoxy resins, phenolic resins, unsaturated polyester resins, vinyl ester resins, polycarbonate resins, polyester resins, polyamide (PA) resins, liquid crystal polymer resins, polyethersulfone resins, polyetheretherketone resins, polyarylate resins, polyphenylene ether resins, polyphenylene sulfide (PPS) resins, polyacetal resins, polysulfone resins, polyimide resins, polyetherimide resins, polystyrene resins, modified polystyrene resins, AS resins (copolymers of acrylonitrile and styrene), ABS resins (copolymers of acrylonitrile, butadiene, and styrene), modified ABS resins, MBS resins (copolymers of methyl methacrylate, butadiene, and styrene), modified MBS resins, polymethyl methacrylate (PMMA) resins, and modified polymethyl methacrylate resins. The resin contained in the composite material may be one of these resins, or a mixture of two or more of these resins.

[0016] Fillers are added to resins, for example, to improve the strength of composite materials. Fillers are added to resins at a volumetric concentration of 0.1% to 50%. Fillers may be, for example, fibrous or particulate. Examples of fibrous fillers include glass fiber (GF), carbon fiber (CF), aramid fiber, alumina fiber, silicon carbide fiber, boron fiber, and silicon carbide fiber. Examples of CF that can be used include polyacrylonitrile (PAN), pitch, cellulose, and hydrocarbon vapor-grown carbon fiber and graphite fiber. Examples of GF that can be used include E-glass and S-glass. It is preferable that the composite material contain at least one of glass fiber (GF) and carbon fiber (CF).

[0017] The particulate filler is, for example, calcium carbonate (CaCo ３ ), talc (Mg３ Si ４ O １０ (OH) ２ ), barium sulfate (BaSO ４ ), mica (Si, Al, Mg, K), aluminum hydroxide (Al(OH) ３ ), magnesium hydroxide (Mg(OH) ２ ), titanium oxide (TiO ２ ), zinc oxide (ZnO ２ ), antimony oxide (Sb ２ O ３ ), kaolin clay (Al ２ O ３ 2SiO ２ ・2H ２ The filler contained in the composite resin material may be one of these, or a mixture of two or more of these.

[0018] The composite material may contain a sensitivity adjuster. A sensitivity adjuster is a sample that functions like a contrast agent used in X-ray imaging, enabling measurements of the composite material with greater accuracy and sensitivity. Measuring a composite material containing a sensitivity adjuster using the characteristic measuring device 300 enables measurements to be performed with greater accuracy. For example, when the characteristic measuring device 300 is a Raman spectrometer, using zirconium tungstate as the sensitivity adjuster changes the Raman shift, allowing measurement information regarding the optical properties of the composite material to be generated with greater accuracy. For example, when the characteristic measuring device 300 is a fluorescence microscope, using a fluorescent dye as the sensitivity adjuster enables measurement information of the composite material to be generated with greater accuracy.

[0019] It is preferable that the sensitivity adjuster contained in the composite material has little effect on the physical properties of the composite material. This allows the composite material measured by the characteristic measuring device 300 to be used in a molded product. A test piece of the composite material containing the sensitivity adjuster may be prepared for measurement by the characteristic measuring device 300.

[0020] (Prediction device 100) The prediction device 100 is a computer such as a PC, a smartphone, a tablet terminal, etc. The prediction device 100 is configured to be connectable to the ultrasonic measurement device 200 and the characteristic measurement device 300, and transmits and receives various information to and from each device.

[0021] FIG. 2 is a block diagram showing a schematic configuration of the prediction device 100.

[0022] 2, the prediction device 100 includes a CPU (Central Processing Unit) 110, a ROM (Read Only Memory) 120, a RAM (Random Access Memory) 130, storage 140, a communication interface 150, a display unit 160, and an operation reception unit 170. Each component is connected to each other via a bus so as to be able to communicate with each other.

[0023] The CPU 110 controls the above components and performs various arithmetic processing in accordance with programs recorded in the ROM 120 and the storage 140. The CPU 110 functions as an acquisition unit that acquires first measurement information obtained by measuring the resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the resin molded product using one or more characteristic measurement devices different from the ultrasonic measurement device. The CPU 110 functions as a prediction unit that predicts the toughness and / or rigidity due to thermal deformation of the resin molded product using the acquired first measurement information and second measurement information as explanatory variables. Details will be described later.

[0024] The ROM 120 stores various programs and various data.

[0025] The RAM 130 serves as a working area for temporarily storing programs and data.

[0026] The storage 140 stores various programs including an operating system and various data. For example, an application for predicting the toughness of a resin molded product and its rigidity due to thermal deformation using a trained classifier is installed in the storage 140. The storage 140 may also store first measurement information and second measurement information (described below) acquired from the ultrasonic measurement device 200 and the characteristic measurement device 300. The storage 140 may also store trained models used as classifiers and training data used in machine learning.

[0027] The communication interface 150 is an interface for communicating with other devices. A wired or wireless communication interface conforming to various standards is used as the communication interface 150. The communication interface 150 is used, for example, to receive the first measurement information and the second measurement information from the ultrasonic measurement device 200 and the characteristic measurement device 300, and to transmit the prediction results to a server or the like for storage.

[0028] The display unit 160 includes an LCD (liquid crystal display), an organic EL display, etc., and displays various information. The display unit 160 may be configured with viewer software, a printer, etc.

[0029] The operation reception unit 170 includes a touch sensor, a pointing device such as a mouse, a keyboard, etc., and receives various operations from the user. The display unit 160 and the operation reception unit 170 may form a touch panel by superimposing a touch sensor serving as the operation reception unit 170 on the display surface serving as the display unit 160.

[0030] (Ultrasonic Measuring Device 200) The ultrasonic measuring device 200 applies ultrasonic waves to a resin molded product, measures the response of the resin molded product to the ultrasonic waves, i.e., the acoustic characteristics, and generates first measurement information. By measuring the resin molded product using the ultrasonic measuring device, it is possible to generate measurement information including information on the specific volume, filler content, resin type, etc. For example, the measurement method used by the ultrasonic measuring device 200 is the method for measuring the sound velocity in solids using the ultrasonic pulse method (a method using a reference test piece) specified in JIS Z2353_2003. In particular, the measurement method used by the ultrasonic measuring device 200 is a surface echo first-back echo method.

[0031] (Characteristics measuring device 300) The characteristic measuring device 300 is a device for measuring a resin molded product to generate second measurement information. Here, the characteristic measuring device 300 is a device for measuring the chemical and physical properties of the resin molded product, such as acoustic properties, atomic properties, electrical properties, magnetic properties, mechanical properties, optical properties, radiation properties, thermal properties, and surface conditions. The characteristic measuring device 300 is preferably a device capable of measuring the resin molded product non-destructively. This allows the resin molded product, after being measured by the characteristic measuring device 300, to be used in subsequent manufacturing processes, etc.

[0032] The characteristic measuring device 300 is, for example, a scanning electron microscope (SEM), an infrared spectrometer, an impedance spectrometer, a terahertz wave spectrometer, a Raman spectrometer, an X-ray diffraction device, a differential scanning calorimetry (DSC), a nuclear magnetic resonance (NMR), a fluorescence fingerprint measuring device, or an X-ray Talbot-Lau device.

[0033] Scanning electron microscopes irradiate resin moldings with an electron beam to observe the surface condition of composite materials. Infrared spectroscopy, terahertz spectroscopy, and Raman spectroscopy irradiate resin moldings with electromagnetic waves to measure the response of composite materials to electromagnetic waves, i.e., their optical properties. Impedance spectroscopy measures the electrical properties of resin moldings as impedance at various frequencies. X-ray diffraction instruments irradiate resin moldings with X-rays to measure the radiation properties of composite materials. Differential scanning calorimeters vary the temperature of resin moldings to measure their heat capacity, i.e., their thermal properties. Nuclear magnetic resonance instruments can analyze the molecular structure and physical properties of resin moldings. Nuclear magnetic resonance instruments can obtain information not only on the structure of resin moldings, but also on intermolecular and intramolecular interactions, molecular mobility, and other aspects. Fluorescence fingerprinting instruments measure the optical fingerprint of resin moldings. Fluorescence fingerprints contain information on organic substances derived from their type, environmental impact, concentration, and other factors. Statistical analysis of fluorescence fingerprints can be used to classify resin moldings. The X-ray Talbot-Lau device measures the resin molded product and generates Talbot information, which will be described later.

[0034] Here, an X-ray Talbot-Lau device will be described. (Photography Using a Talbot Interferometer and a Talbot-Lau Interferometer) Here, a photographing method using a Talbot interferometer and a Talbot-Lau interferometer will be described. As shown in FIG. 3 , when X-rays emitted from a radiation source 11 pass through a first grating 14, the transmitted X-rays form images at regular intervals in the z direction. These images are called self-images, and the phenomenon of forming self-images is called the Talbot effect. A second grating 15 is placed at the position where the self-images are formed, generally parallel to the self-images. A Moiré fringe image (indicated by Mo in FIG. 3 ) is obtained by the X-rays that pass through the second grating 15. That is, the first grating 14 forms a periodic pattern, and the second grating 15 converts the periodic pattern into Moiré fringes. If a resin molded product is present between the radiation source 11 and the first grating 14, the phase of the X-rays is shifted by the resin molded product, and the Moiré fringes on the Moiré fringe image are distorted at the edge of the resin molded product, as shown in FIG. 3 . This disturbance in the moiré fringes can be detected by processing the moiré fringe image, and an image of the resin molded product can be produced. This is the principle of the Talbot interferometer.

[0035] A multi-slit 12 is placed between the radiation source 11 and the first grating 14 and close to the radiation source 11, and X-ray imaging is performed using a Talbot-Lau interferometer. The Talbot interferometer is based on the premise that the radiation source 11 is an ideal point radiation source, but in actual imaging, a focal spot with a relatively large focal spot diameter is used, and therefore the multi-slit 12 produces an effect as if X-rays were being irradiated from a series of multiple point radiation sources. This is the X-ray imaging method using a Talbot-Lau interferometer, and even when the focal spot diameter is relatively large, it is possible to produce the same Talbot effect as with a Talbot interferometer.

[0036] With this type of X-ray Talbot-Lau device, at least three types of images (two-dimensional images) can be reconstructed (referred to as reconstructed images) by capturing a moiré image Mo ( FIG. 3 ) of a resin molded product using a method based on the principles of fringe scanning and analyzing the moiré image Mo using Fourier transform. These three types of images are: an absorption image (same as a normal X-ray absorption image) that visualizes the average component of the moiré fringes in the moiré image Mo; a differential phase image that visualizes the phase information of the moiré fringes; and a small-angle scattering image that visualizes the visibility of the moiré fringes. It is also possible to generate even more types of images by, for example, recombining these three types of reconstructed images.

[0037] Next, the three or more small-angle scattering images for each of the prepared relative angles are aligned. Because the sample is rotated, each image is returned to the specified angle.

[0038] Finally, fitting is performed for each pixel with a sine wave, and fitting parameters are extracted. A sine wave graph is a graph in which the horizontal axis represents the relative angle between the sample and the lattice, and the vertical axis represents the small-angle scattering signal value of a certain pixel. The amplitude, average, and phase of the sine wave are obtained as fitting parameters. An image showing the amplitude value for each pixel is called an "amp image," an image showing the average value for each pixel is called an "ave image," and an image showing the phase for each pixel is called a "pha image." The amp image, ave image, and pha image are collectively called "orientation images." The fitting method is not limited to sine waves; for example, the angle (phase) with the greatest intensity can be calculated as θ ０An ellipse with the highest intensity as a and the lowest intensity as b may be fitted to the following equation (1) expressed in polar coordinates with the position r(θ). In this case, in accordance with the names used in sine wave fitting, an image with a value (a-b) / 2 corresponding to the amplitude of each pixel is called an "amp image," an image showing a value (a+b) / 2 corresponding to the average value of each pixel is called an "ave image," and an image showing a value (a+b) / 2 corresponding to the θ of each pixel is called an "amp image." ０ The image showing the major axis a, minor axis b, and phase θ of the signal intensity for each pixel may be referred to as a "pha image." ０ may be assigned to the image as an orientation image.

[0039] Such an X-ray Talbot-Lau device generates a Talbot image containing information about the filler orientation of the resin molded product. That is, the Talbot information generated by the X-ray Talbot-Lau device is information about the Talbot image. The Talbot image is an image generated by the X-ray Talbot-Lau device photographing the resin molded product and using the Talbot effect. Images that have been subjected to image processing such as the orientation image are also included in the Talbot image. A reconstructed image reconstructed from the moiré image Mo is also included in the Talbot image.

[0040] <Functions of Prediction Device 100> The following describes the functions of the CPU 110 of the prediction device 100 as an acquisition unit, extraction unit, prediction unit, and display control unit that reads programs stored in the storage 140 and executes processes.

[0041] The acquisition unit acquires the first measurement information generated by the ultrasonic measurement device 200 and the second measurement information generated by the characteristic measurement device 300. The first measurement information and the second measurement information acquired by the acquisition unit preferably include information about the same region of the composite resin. This makes it possible to predict with high accuracy the toughness and stiffness due to thermal deformation of a specific region of the composite resin in a prediction based on the first measurement information and the second measurement information, which will be described later.

[0042] The extracting unit extracts feature quantities from each of the first measurement information and the second measurement information acquired by the acquiring unit. The feature quantities are, for example, numerical values ​​extracted from the spectra, images, etc. acquired by the acquiring unit and associated with the physical properties of the resin molded product.

[0043] The first measurement information is information relating to an ultrasound image of the resin molding. The extracting unit extracts principal components or frequency characteristics from the first measurement information.

[0044] When the second measurement information is, for example, information about the infrared absorption spectrum or terahertz band absorption spectrum of the resin molded product, the extraction unit extracts the main component from the second measurement information. When the second measurement information is information about the X-ray diffraction spectrum of the resin molded product, the extraction unit extracts the main component, crystallinity, etc. from the second measurement information. When the second measurement information is information about the impedance spectroscopy spectrum of the resin molded product, the extraction unit extracts capacitance, resistance, etc. from the second measurement information. The frequency characteristics are, for example, attenuation and sound speed, etc.

[0045] When the second measurement information is an impedance spectrum of the resin molded product, the extraction unit extracts a resistance value or capacitance at a specific frequency from the second measurement information. When the second measurement information is an SEM image of the resin molded product, the extraction unit extracts a predetermined numerical value obtained by image analysis. The extraction unit may extract multiple feature quantities from each of the first measurement information and the second measurement information. Furthermore, the feature quantities extracted from the second measurement information may be principal components obtained by principal component analysis of the spectrum. Furthermore, the feature quantities extracted from the second measurement information may be principal components obtained by principal component analysis of the measured waveform.

[0046] The feature quantity extracted from the Talbot information, which is the second measurement information, may be the Talbot image itself, such as an orientation image (amp image, ave image, pha image), or may be an image signal value acquired from a specific region of the Talbot image. The feature quantity extracted from the Talbot information may be the degree of orientation, the orientation angle, etc.

[0047] Furthermore, the feature extracted from the Talbot information may be the eccentricity ecc. The eccentricity ecc can be calculated, for example, by calculating σ1=ave+amp (corresponding to the maximum value of the small-angle signal value) and σ2=ave-amp (corresponding to the minimum value of the small-angle signal value) using the signal values ​​amp and ave obtained from the orientation image, using the following equation (2). The orientation image may include an image (ecc image) showing the eccentricity ecc for each pixel.

[0048]

[0049] The acquiring unit may acquire information from which feature quantities have been extracted. That is, the first measurement information and the second measurement information may be information from which feature quantities have been extracted from information about the resin molding measured by the ultrasonic measurement device 200 and the characteristic measurement device 300.

[0050] The prediction unit predicts the toughness and stiffness due to thermal deformation of the resin molded product based on the first measurement information and the second measurement information acquired by the acquisition unit. Specifically, the prediction unit uses a trained classifier to input the feature quantities of the first measurement information and the second measurement information extracted by the extraction unit and predicts the toughness and stiffness due to thermal deformation of the resin molded product. The prediction unit predicts, for example, the elastic modulus, yield strength, plasticity, tensile strength, elongation, fracture energy, or hardness of the resin molded product.

[0051] The display control unit causes the display unit 160 to output information relating to the toughness of the resin molded product and the rigidity due to thermal deformation predicted by the prediction unit.

[0052] The processing executed by the prediction device 100 will be described in detail below.

[0053] <Prediction Processing> Fig. 4 is a flowchart showing the procedure of the prediction processing executed in the prediction device 100. The processing of the prediction device 100 shown in the flowchart in Fig. 4 is stored as a program in the storage 140 of the prediction device 100, and is executed by the CPU 110 controlling each unit.

[0054] (Steps S101 and S102) The prediction device 100 first acquires first measurement information obtained by measuring the resin molded product using the ultrasonic measurement device 200 (step S101). Next, the prediction device 100 acquires second measurement information obtained by measuring the resin molded product using the characteristic measurement device 300 (step S102). The prediction device 100 may acquire the first measurement information and the second measurement information simultaneously, or may acquire the first measurement information after acquiring the second measurement information.

[0055] For example, prediction device 100 acquires first measurement information from ultrasonic measurement device 200 and second measurement information from characteristic measurement device 300. Ultrasonic measurement device 200 and characteristic measurement device 300 may store the first measurement information and second measurement information in another device such as a server, and prediction device 100 may acquire the first measurement information and second measurement information from the other device.

[0056] (Step S103) The prediction device 100 extracts feature amounts from the first measurement information and the second measurement information acquired in the processes of steps S101 and S102.

[0057] (Step S104) The prediction device 100 inputs the feature quantities of each of the first measurement information and the second measurement information extracted in the process of step S103 into a classifier that has been trained in advance by machine learning to predict the toughness and stiffness due to thermal deformation of the resin molded product. For example, the classifier is trained by machine learning using training data including feature quantities of each of the first measurement information and the second measurement information of a large number of resin molded products prepared in advance and measured values ​​of the toughness and stiffness due to thermal deformation of each of the resin molded products, using a learning method such as that described below. Specifically, the classifier is trained in advance using the feature quantities of each of the first measurement information and the second measurement information of the resin molded products as input data and the measured values ​​of the toughness and stiffness due to thermal deformation of each of the resin molded products as output data. In this way, the prediction device 100 can predict the toughness and stiffness due to thermal deformation of the resin molded product by inputting the feature quantities extracted from each of the first measurement information and the second measurement information into the classifier. Measurement values ​​of the toughness and rigidity due to thermal deformation of a resin molded product are obtained by, for example, a Tensilon universal test, a Charpy impact test, an Izod impact test, or the like.

[0058] The classifier may perform machine learning using first measurement information and second measurement information about a plurality of resin molded products as input data and measurement values ​​of the toughness and stiffness due to thermal deformation of each of the plurality of resin molded products as output data. Furthermore, the information input to the classifier is not limited to the feature quantities of each of the first measurement information and the second measurement information. For example, in addition to the feature quantities of each of the first measurement information and the second measurement information, information at the time of manufacture may be input to the classifier and used as information for learning and prediction.

[0059] (Step S105) The prediction device 100 generates prediction results of the toughness and stiffness due to thermal deformation of the resin molded product based on the output of the classifier in the process of step S104.

[0060] (Step S106) The prediction device 100 outputs the prediction result generated in the process of step S105. For example, the prediction device 100 displays the values ​​of the toughness of the resin molded product and the rigidity due to thermal deformation predicted in the process of step S104 on the display unit 160 together with information about the resin molded product.

[0061] <Learning Process> Next, a machine learning method for a trained model used in a classifier will be described.

[0062] FIG. 4 is a flowchart showing a machine learning method for a trained model.

[0063] In the process of FIG. 4 , machine learning is performed using a large number (i sets) of data sets as training sample data, in which the feature quantities of the first measurement information and the second measurement information of a plurality of resin molded products prepared in advance are input and the measured values ​​of the toughness and stiffness due to thermal deformation of each of the plurality of resin molded products are output. A learning device (not shown) functioning as a classifier may be, for example, a standalone high-performance computer using a CPU and a GPU processor, or a cloud computer. Below, a learning method using a neural network formed by combining perceptrons such as deep learning in the learning device will be described, but this is not limiting and various other techniques may be applied. For example, random forests, decision trees, support vector machines (SVMs), logistic regression, k-nearest neighbors, topic models, etc. may be applied.

[0064] (Step S111) The learning device reads learning sample data, which is teacher data. If it is the first time, the first set of learning sample data is read, and if it is the i-th time, the i-th set of learning sample data is read.

[0065] (Step S112) The learning device inputs the input data from the read learning sample data to the neural network.

[0066] (Step S113) The learning device compares the prediction result of the neural network with the correct answer data.

[0067] (Step S114) The learning device adjusts the parameters based on the comparison results. For example, the learning device adjusts the parameters by performing a process based on back-propagation (back-propagation) so that the difference in the comparison results becomes smaller.

[0068] (Step S115) If the learning device has completed processing of all data from the first to i-th sets (YES), the process proceeds to step S116; if not (NO), the process returns to step S111, the next learning sample data is read, and the process from step S111 onwards is repeated.

[0069] (Step S116) The learning device determines whether or not to continue learning. If it decides to continue (YES), the process returns to step S111, and it executes the processes from the first set to the i-th set again in steps S111 to S115. If it decides not to continue (NO), the process proceeds to step S117.

[0070] (Step S117) The learning device stores the trained model constructed in the processing up to this point and ends the processing (END). The storage destination includes the internal memory of the prediction device 100. In the processing of FIG. 4 described above, the trained model generated in this manner is used to predict the toughness and stiffness due to thermal deformation of the resin molded product.

[0071] [Effects] As described above, the prediction system 1 includes an acquisition unit (CPU 110) that acquires first measurement information obtained by measuring a resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the properties of the resin molded product using one or more property measurement devices other than the ultrasonic measurement device, and a prediction unit (CPU 110) that predicts the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information. The property measurement device is a device that measures at least one of the acoustic properties, atomic properties, electrical properties, magnetic properties, mechanical properties, optical properties, radiation properties, thermal properties, and surface condition of the resin molded product. Therefore, the toughness and rigidity due to thermal deformation of the resin molded product can be predicted more accurately.

[0072] The prediction method is a prediction method using a prediction device, and includes an acquisition step (steps S101 and S102) of acquiring first measurement information obtained by measuring the resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the properties of the resin molded product using one or more property measurement devices different from the ultrasonic measurement device, and a prediction step (step S104) of predicting the toughness and / or stiffness due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, where the property measurement device is a device that measures at least one of the acoustic properties, atomic properties, electrical properties, magnetic properties, mechanical properties, optical properties, radiation properties, thermal properties, and surface condition of the resin molded product. Therefore, the toughness and stiffness due to thermal deformation of the resin molded product can be predicted with higher accuracy.

[0073] The program also causes the computer of the prediction device 100 to execute an acquisition step (steps S101 and S102) of acquiring first measurement information obtained by measuring a resin molded product using an ultrasonic measurement device and second measurement information obtained by measuring the properties of the resin molded product using one or more property measurement devices different from the ultrasonic measurement device, and a prediction step (step S104) of predicting the toughness and / or stiffness due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, where the property measurement device is a device that measures at least one of the acoustic properties, atomic properties, electrical properties, magnetic properties, mechanical properties, optical properties, radiation properties, thermal properties, and surface condition of the resin molded product. Thus, the toughness and stiffness due to thermal deformation of the resin molded product can be predicted with greater accuracy.

[0074] The effects of the present invention will be explained using the following examples, although the technical scope of the present invention is not limited to the following examples.

[0075] (Creating a Trained Classifier) ​​First, multiple resin molded product samples were prepared to create training data. These samples were prepared using the following combinations of four types of resin, three types of filler, three filler concentrations (weight ratios), and two injection pressures. The resin and filler were mixed in advance at the desired ratio using a Labo Plastomill (registered trademark) extruder manufactured by Toyo Seiki Seisaku-sho, Ltd. Pellets were thus prepared. The resin molded product samples were molded using an SE50D injection molding machine manufactured by Sumitomo Heavy Industries, Ltd. The sample shape was a dumbbell-shaped test piece type A1 as specified in JIS K7139.

[0076] Resins: polypropylene (Noblen (registered trademark) W101 manufactured by Sumitomo Chemical Co., Ltd.), polyamide 66 (Leona 1300S manufactured by Asahi Kasei Corporation), ABS (Toyolac 700 314 manufactured by Toray Industries, Inc.), polycarbonate (Iupilon (registered trademark) H-3000R manufactured by Mitsubishi Engineering Plastics Corporation); Fillers: PAN (polyacrylonitrile)-based carbon fiber (CF-N manufactured by Japan Polymer Sangyo Co., Ltd.), PAN-based carbon fiber (TC-33 manufactured by Taiwan Plastics Corporation), glass fiber (CS3J-960 manufactured by Nitto Boseki Co., Ltd.); Filler concentrations: 0%, 10%, 30%; Injection pressure: 50 MPa, 100 MPa.

[0077] Next, each of the 72 types of resin molded product samples was measured using the following ultrasonic device and characteristic measurement device, and the feature values ​​were trained into a classifier. Measurements were taken near the center of the dumbbell-shaped test pieces.

[0078] <Ultrasonic Measuring Device> Ultrasonic measuring device (ultrasonic imaging device FineSAT 3 (manufactured by Hitachi)).

[0079] <Characteristics Measuring Apparatus> X-ray diffractometer (Smart Lab, manufactured by Rigaku Corporation); Fluorescence fingerprint measuring apparatus; 3D fluorescence spectrum of fluorescence spectrophotometer F-7000 (manufactured by Hitachi High-Tech); Raman spectrometer (laser Raman spectrophotometer NRS-4500 (manufactured by JASCO)); Infrared spectrophotometer (FT-IR) (AVATAR370, manufactured by Thermo Fisher Scientific); Terahertz wave spectrometer (C12068-01, manufactured by Hamamatsu Photonics K.K.); Impedance spectrometer (Model 126096, manufactured by Solartron. Conductive tape with a diameter of 5 mm was attached to two places on the sample, 50 mm apart, and used as electrodes for measurement.); Scanning electron microscope (SEM), manufactured by JEOL; Differential scanning calorimeter (DSC), manufactured by Shimadzu Corporation; Nuclear magnetic resonance apparatus (NMR): manufactured by JEOL; X-ray Talbot-Lau apparatus (apparatus described in JP 2019-184450 A).

[0080] Using an ultrasonic device, measurements were performed using the surface echo / first bottom echo method specified in JIS Z 2353. From the first measurement information obtained by the measurement, feature quantities such as surface gain, bottom gain, sound velocity, ss (surface-bottom sample), and surface gain / bottom gain were extracted.

[0081] From the second measurement information obtained by measurement using an X-ray diffraction device, a fluorescence fingerprint measurement device, a Raman spectroscopy device, an infrared spectroscopy device, and a terahertz wave spectroscopy device, principal components were extracted as feature quantities from the spectrum. From the second measurement information obtained by measurement using an impedance spectroscopy device, capacitance, resistance, etc. were extracted as feature quantities. Feature quantities were extracted from images (second measurement information) obtained by measurement using an SEM. From the second measurement information obtained by measurement using DSC and NMR, principal component analysis was performed on the spectrum and feature quantities were extracted. With an X-ray Talbot-Lau device, feature quantities were extracted from the second measurement information obtained by measurement, namely, absorption images, differential phase images, and small-angle scattering images, and information on the degree of filler orientation obtained from these images.

[0082] In addition, the breaking elongation, Charpy impact test value, and deflection temperature under load were measured using a Tensilon universal testing machine, an impact testing machine, and a deflection temperature under load, and the results were used to train the classifier.

[0083] (Examples 1 to 24, Comparative Example) First, six types of resin molded product samples were prepared. These samples were prepared using the following combinations of two types of resin, two types of filler, two conditions of filler concentration (weight ratio), and one condition of injection pressure. The samples were prepared in the same manner as the training data. Resin: Polyamide 66 (Leona 1300S manufactured by Asahi Kasei Corporation), polycarbonate (Iupilon (registered trademark) H-3000R manufactured by Mitsubishi Engineering Plastics Corporation); Filler: PAN (polyacrylonitrile)-based carbon fiber (CF-N manufactured by Nippon Polymer Sangyo Co., Ltd.), glass fiber (CS3J-960 manufactured by Nitto Boseki Co., Ltd.); Filler concentration: 0%, 30%; Injection pressure: 50 MPa

[0084] In the examples, samples of each of these resin molded products were measured using an ultrasonic device and the measuring device shown in Table I below. In the comparative examples, samples of each of these resin molded products were measured using only the ultrasonic device. After this, in the examples, the feature quantities of the measurement information generated by the ultrasonic device and the feature quantities of the device shown in Table I below were input into a trained classifier to determine predicted values ​​of the breaking elongation, Charpy impact test value, and deflection temperature under load. In the comparative examples, only the feature quantities of the ultrasonic measurement values ​​generated by the ultrasonic device were input into a trained classifier to determine predicted values ​​of the breaking elongation, Charpy impact test value, and deflection temperature under load.

[0085] In addition, measurements were taken of each resin molded product using a Tensilon universal testing machine, a Charpy impact tester, and a deflection temperature under load tester. Next, the error between the predicted value and the measured value was calculated, and then the average error for the resin molded product was calculated.

[0086]

[0087]

[0088] Examples 1 to 24, in which the toughness and rigidity due to thermal deformation of a resin molded product were predicted based on the first measurement information generated by an ultrasonic measurement device and the second measurement information generated by a characteristic measurement device, had smaller errors than the comparative example. Among Examples 1 to 24, Examples 7, 10, 11, 12, 19, 22, 23, and 24, which used multiple characteristic measurement devices together with an X-ray Talbot-Lau measurement device, were able to reduce errors compared to the other Examples. Furthermore, Examples using three characteristic measurement devices, including an ultrasonic measurement device, were able to reduce errors compared to the other Examples.

[0089] The above-described configurations of the prediction device 100 and the prediction system 1 are merely the main configurations described in order to explain the features of the above-described embodiments and examples, but are not limited to the above-described configurations and may be modified in various ways within the scope of the claims. Furthermore, configurations that are included in general prediction systems are not excluded.

[0090] For example, the prediction device 100 may include components other than the above-described components, or may not include some of the above-described components.

[0091] Furthermore, the prediction device 100, the ultrasonic measurement device 200, and the characteristic measurement device 300 may each be configured by a plurality of devices, or may be configured by a single device.

[0092] Furthermore, the functions of each component may be realized by other components. For example, the ultrasonic measurement device 200 or the characteristic measurement device 300 may be integrated into the prediction device 100, and some or all of the functions of the ultrasonic measurement device 200 and the characteristic measurement device 300 may be realized by the prediction device 100.

[0093] Furthermore, the processing units of the flowcharts in the above embodiments are divided according to the main processing content in order to facilitate understanding of each process. The classification of the processing steps does not limit the scope of the present invention. Each process can be divided into more processing steps. Furthermore, one processing step may execute more processes.

[0094] The means and methods for performing various processes in the systems according to the above-described embodiments can be realized by either dedicated hardware circuits or programmed computers. The programs may be provided, for example, on computer-readable recording media such as flexible disks and CD-ROMs, or online via a network such as the Internet. In this case, the programs recorded on the computer-readable recording media are typically transferred to and stored in a storage unit such as a hard disk. The programs may also be provided as standalone application software, or may be incorporated into the software of the device as a function of the system.

[0095] The present disclosure can be used in a prediction system, a prediction method, and a program.

[0096] REFERENCE SIGNS LIST 100 Prediction device 110 CPU (acquisition unit, prediction unit) 120 ROM 130 RAM 140 Storage 150 Communication interface 160 Display unit 170 Operation reception unit 200 Ultrasonic measurement device 300 Characteristics measurement device

Claims

1. An acquisition unit that acquires first measurement information obtained by measuring a resin molded product with an ultrasonic measurement device and second measurement information obtained by measuring the characteristics of the resin molded product with one or more characteristic measurement devices different from the ultrasonic measurement device; A prediction unit that predicts the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information; A prediction system comprising: The characteristic measurement device is a device that measures at least any one of the acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface state of the resin molded product.

2. The prediction unit according to claim 1, wherein the first measurement information and the second measurement information are used as explanatory variables and predicted using machine learning, and the explanatory variables are obtained from three or more devices. Prediction system.

3. The prediction system according to claim 1, wherein the resin molded product contains a filler.

4. The prediction system according to claim 3, wherein the filler has a fibrous shape.

5. The prediction system according to any one of claims 1 to 4, wherein the characteristic measurement device can measure the resin molded product non-destructively.

6. The prediction system according to any one of claims 1 to 4, wherein the characteristic measurement device includes at least any one of an infrared spectroscopic measurement device, a Raman spectroscopic measurement device, an X-ray diffraction device, or an X-ray Talbot-Lau device.

7. A prediction method by a prediction device, comprising: an acquisition step of acquiring first measurement information obtained by measuring a resin molded product with an ultrasonic measurement device and second measurement information obtained by measuring the characteristics of the resin molded product with one or more characteristic measurement devices different from the ultrasonic measurement device; A prediction step of predicting the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information; The characteristic measurement device is a device that measures at least any one of the acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface state of the resin molded product. Prediction method.

8. A program that causes a computer of a prediction device to execute: an acquisition step of acquiring first measurement information obtained by measuring a resin molded product with an ultrasonic measurement device and second measurement information obtained by measuring characteristics of the resin molded product with one or more characteristic measurement devices different from the ultrasonic measurement device; and a prediction step of predicting the toughness and / or rigidity due to thermal deformation of the resin molded product based on the acquired first measurement information and second measurement information, wherein the characteristic measurement device is a device that measures at least any one of acoustic characteristics, atomic characteristics, electrical characteristics, magnetic characteristics, mechanical characteristics, optical characteristics, radiation characteristics, thermal characteristics, and surface state of the resin molded product.

Images