WO2023120257A1

WO2023120257A1 - Composite material inspection device, composite material inspection method, composite material inspection program, and recording medium

Info

Publication number: WO2023120257A1
Application number: PCT/JP2022/045554
Authority: WO
Inventors: 伸吾岡本; 香織谷上; 千緒峰尾; 武大木
Original assignee: 国立大学法人愛媛大学; 帝人株式会社
Priority date: 2021-12-24
Filing date: 2022-12-09
Publication date: 2023-06-29

Abstract

An inspection device (1) comprises a storage unit (16) for storing a mechanical property inference model that is generated by machine learning based on mechanical property information and nondestructive inspection information of a first composite material including reinforcement fibers, the mechanical property information and the nondestructive inspection information being known, and that is for use in inferring, through reception as input of nondestructive inspection information of a second composite material which includes reinforcement fibers and has unknown mechanical property information, the mechanical property information of the second composite material. The inspection device acquires the nondestructive inspection information of the second composite material, inputs said nondestructive inspection information to the mechanical property inference model, acquires the mechanical property information of the second composite material from the mechanical property inference model, and performs output based on said mechanical property information.

Description

Composite material inspection device, composite material inspection method, composite material inspection program and recording medium

The present invention relates to an inspection device, an inspection method, an inspection program, and a recording medium for composite materials containing reinforcing fibers.

A composite material containing carbon fibers as reinforcing fibers can reinforce the fragility of the matrix resin with high-strength fibers. For this reason, it is widely used as a lightweight material with excellent mechanical properties.
Conventionally, in the production process of composite materials containing reinforcing fibers, ultrasonic inspection is performed to inspect defective products during the manufacturing of composite materials. For example, in Patent Document 1, the following inspection is performed in the process of impregnating carbon fibers with a thermoplastic resin. First, an ultrasonic wave transmitter and a wave receiver having directivity are placed facing each other at a certain distance from an object to be inspected (composite material in which carbon fiber is impregnated with thermoplastic resin). Then, an ultrasonic wave is emitted from one of the ultrasonic wave transmitters, the ultrasonic wave is received by the opposing wave receiver on the object to be inspected, and the propagation time of the ultrasonic wave is measured by the signal processing circuit. Detect internal defects of objects without contact. The data of the inspection using the ultrasonic wave here is converted into an image, and it is possible to determine whether the object to be inspected is pass/fail based on the image.

Patent Literatures

2 and 3 disclose devices that automatically perform high-precision searches in order to efficiently sort blood, feathers, and the like in the production process of processed foods.

Japanese Patent Application Laid-Open No. 2019-158459 WO2019/151393 WO2019/151394

In recent years, due to rising raw material prices and labor costs, it has become a challenge to keep production costs down while maintaining high quality. is required.
The sorting of composite materials by ultrasonic inspection described in US Pat. Therefore, it is difficult to grasp the state of the composite material in detail. In particular, it is difficult to establish an objective evaluation standard in pass/fail judgment performed by visually observing an image, and it is difficult to determine what is used to calculate the pass/fail criterion for a material.
Moreover, the food inspection systems described in

Patent Documents

2 and 3 are devices for humans to locate bones, and are different from techniques for inspecting composite materials. This food inspection system merely substitutes a neural network for the quality of an image or an object to be measured, which can be judged by humans.

An object of the present invention is to provide a composite material inspection apparatus, an inspection method, an inspection program, and a recording medium that can estimate the mechanical properties of a composite material and be useful for evaluating the composite material without measuring the mechanical properties. and

The above object can be solved by the following aspects.
An inspection apparatus according to one aspect of the present invention is a machine generated by machine learning based on the mechanical property information and the non-destructive test information of the first composite material containing reinforcing fibers, in which the mechanical property information and the non-destructive test information are known. A physical property estimation model,
Accessible to a model storage unit for storing a mechanical property estimation model for estimating mechanical property information of the second composite material with input of non-destructive inspection information of a second composite material containing reinforcing fibers whose mechanical property information is unknown. with a processor
The processor acquires non-destructive inspection information of the second composite material, inputs the non-destructive inspection information into the mechanical property estimation model, and extracts the mechanical property information of the second composite material from the mechanical property estimation model. It acquires and outputs based on the mechanical physical property information. However, the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is over 0 Hz.

In the inspection method of one aspect of the present invention, the mechanical property information and the non-destructive test information are known, and the mechanical property information and the non-destructive test information of the first composite material containing reinforcing fibers are machine-learned. generating a mechanical property estimation model for estimating mechanical property information of the second composite material by inputting non-destructive test information of the second composite material containing reinforcing fibers whose information is unknown; obtaining destructive test information; inputting the obtained non-destructive test information to the mechanical property estimation model; obtaining mechanical property information of the second composite material from the mechanical property estimation model; and providing an output based on the information. However, the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is over 0 Hz.

The inspection program of one aspect of the present invention performs machine learning of the mechanical property information and the nondestructive test information of the first composite material containing reinforcing fibers, for which the mechanical property information and the nondestructive test information are known, to obtain the mechanical property information. generating a mechanical property estimation model for estimating mechanical property information of the second composite material using as input non-destructive test information of a second composite material containing reinforcing fibers, for which is unknown; obtaining inspection information; inputting the obtained non-destructive inspection information to the mechanical property estimation model; obtaining mechanical property information of the second composite material from the mechanical property estimation model; and outputting an output based on the processor. However, the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is over 0 Hz.

According to the present invention, it is possible to estimate the mechanical properties of a composite material only from non-destructive inspection information without measuring the mechanical properties, and use this information to evaluate the composite material. According to the present invention, it is possible to instantaneously infer mechanical property information, which cannot be inferred from non-destructive inspection information no matter how hard a person tries, with high accuracy. As a result, waste loss in the production of composite materials can be reduced, and high-quality composite materials can be provided at low cost.

FIG. 2 is a block diagram showing a configuration example of an inspection device; A flowchart of learning processing. The figure which shows the example of the neural network which outputs three reaction values. FIG. 4 is a diagram showing arithmetic processing between units of a neural network; Flowchart of inference processing. Discrimination surface and distribution of response values when RBF is used as the activation function. Discrimination surface and distribution of response values when sigmoid function is used as activation function. The figure which shows a vibration inspection image. The figure which shows a vibration inspection image. The figure which shows a vibration inspection image. The figure which shows a vibration inspection image.

An inspection system including an inspection apparatus that is one embodiment of the present invention will be described below, but the present invention is not limited to this.

[Overview of inspection system]
The inspection system of the present embodiment uses a composite material (second composite material) containing reinforcing fibers whose mechanical property information is unknown as an object to be inspected, and estimates the mechanical property information of this second composite material without actually measuring it. It is.
The mechanical physical property information of a composite material is information indicating the mechanical physical properties of the composite material, for example, information regarding fracture or elasticity such as strength of the composite material. Examples of mechanical property information include information on breaking strength such as tensile strength or bending strength, and information on elastic modulus related to each of breaking strength, compressive strength, shear strength, and the like.

Information on the elastic modulus may be the elastic modulus (e.g., tensile modulus or flexural modulus) itself, or the rank of elastic modulus (e.g., tensile elastic modulus or flexural modulus) (hereinafter referred to as mechanical described as physical property rank). Information about the elastic modulus includes information indicating that the elastic modulus (or its rank) corresponds to a defective product, information indicating that the elastic modulus (or its rank) corresponds to a non-defective product, and information indicating that the elastic modulus (or its rank) corresponds to a non-defective product. It is preferable to further include any of the information indicating that it was difficult to guess.

Information on the breaking strength may be the breaking strength (e.g., tensile strength or yield strength) itself, or the rank when the breaking strength (e.g., tensile strength or yield strength) is classified (hereinafter referred to as the mechanical property rank) description). Information on the breaking strength includes information indicating that the breaking strength (or its rank) corresponds to defective products, information indicating that the breaking strength (or its rank) corresponds to non-defective products, and information indicating that the breaking strength (or its rank) corresponds to non-defective products. It is preferable to further include any of the information indicating that it was difficult to guess.

A computer included in the inspection system acquires non-destructive inspection information of the second composite material, inputs this non-destructive inspection information into the mechanical property estimation model generated in advance and stored in the model storage unit, Inference is performed by this mechanical property estimation model, and information on the mechanical properties of the second composite material that is inferred, or information on the difficulty of inference is output. The estimated mechanical property information of the second composite material includes, for example, a mechanical property rank, information indicating whether the product is non-defective or defective, and the like. Methods for outputting information include displaying information on a display unit, transmitting the information as a message from a speaker, and printing the information on a printer.

In the present invention, the nondestructive inspection information is preferably vibration characteristic information. Vibration characteristics are information about the composite material itself, such as displacement, acceleration, and natural frequency, obtained by vibrating the composite material in a fixed or non-fixed state. The vibration characteristic information may be numerical data such as a natural frequency, or an inspection image using a wavelet image. As inspection images, for example, the wavelet images shown in FIGS. 8A to 8D can be exemplified. Here, the wavelet image is obtained by measuring the time change of the displacement of a predetermined point on the composite material when the composite material is vibrated, wavelet transforming the vibration, and then representing the vibration frequency on the vertical axis, the time on the horizontal axis, and the time on the horizontal axis. It is a two-dimensional image showing the amplitude of vibration in terms of brightness and hue.

The mechanical property estimation model uses machine learning (supervised learning or unsupervised learning deep It is a model that estimates mechanical property information by inputting non-destructive inspection information generated by letting it run (including learning). A neural network, a support vector machine, or the like, for example, is used as the mechanical property estimation model.

The computer of the inspection system constitutes the inspection equipment. This computer may include a processor, a storage unit consisting of a device capable of storing information such as a hard disk device or SSD (Solid State Drive), RAM (Random Access Memory) and ROM (Read Only Memory). good. This processor executes an inspection program stored in a ROM to acquire nondestructive inspection information of a composite material of an object to be inspected, input the acquired nondestructive inspection information into a mechanical property estimation model, and obtain a mechanical property estimation model. It performs processing such as acquisition of mechanical property information from the machine and output based on the acquired mechanical property information. The storage medium for storing the inspection program is not limited to ROM, and a known storage medium can be used, but a non-temporary storage medium is preferable, such as a hard disk device or SSD (Solid State Drive). may be used. A storage medium may also be referred to as a recording medium. Alternatively, the inspection program may be stored in a server (cloud) on the network, and the processor may download the program from the server and execute the program.

Non-destructive testing information for composite materials typically determines whether defects, voids, or foreign objects are present within the composite material, and if so, to what extent and to what extent. used for However, even if there are many defects, voids, or foreign matter inside the composite material, the mechanical properties may be good depending on the distribution state of the defects, voids, or foreign matter. In such a case, if the non-destructive inspection information is visually checked and it is determined that the product is defective because there are many defects, voids, or foreign substances, the composite material that should have been a good product will be discarded. As a result, production efficiency will decrease. On the other hand, the opposite is also possible. In other words, even if the non-destructive inspection information is visually confirmed and the product is determined to be good because there are few defects, voids, or foreign matter, the mechanical properties may be in a state corresponding to a defective product.

As a result of verification based on the above viewpoints, the present inventors found that there is a correlation between nondestructive inspection information and mechanical physical property information, and obtained a large number of measured data of nondestructive inspection information and mechanical physical property information, By applying machine learning to models such as neural networks or support vector machines, we succeeded in inferring mechanical property information of composite materials with high accuracy from non-destructive inspection information of composite materials. Obtaining mechanical property information from non-destructive inspection information has not been considered in the past. For this reason, it was not easy for those skilled in the art to build a machine learning model that takes non-destructive inspection information as input and outputs machine physical property information.
A detailed example of the inspection system will be described below. Note that an example in which the mechanical property estimation model is a neural network will be described below.

[Reinforcing fiber]
The type of reinforcing fiber used in the present invention can be appropriately selected according to the application of the composite material a (second composite material with unknown mechanical property information) to be inspected, and is not particularly limited. not something. Either inorganic fibers or organic fibers can be suitably used as the reinforcing fibers.
Examples of the inorganic fibers include carbon fibers, activated carbon fibers, graphite fibers, glass fibers, tungsten carbide fibers, silicon carbide fibers (silicon carbide fibers), ceramic fibers, alumina fibers, natural mineral fibers (basalt fibers, etc.), and boron fibers. , boron nitride fibers, boron carbide fibers, and metal fibers.

[Carbon fiber]
When using carbon fiber as the fiber, the carbon fiber generally includes polyacrylonitrile (PAN)-based carbon fiber, petroleum/coal pitch-based carbon fiber, rayon-based carbon fiber, cellulose-based carbon fiber, lignin-based carbon fiber, phenol-based Carbon fibers, vapor-grown carbon fibers, and the like are known, and any of these carbon fibers can be suitably used in the present invention.

[Form of reinforcing fiber]
In the present invention, the form of the reinforcing fiber is not particularly limited, but the continuous fiber that the present inventors carried out as a specific example will be described below. However, the present invention is not limited to continuous fibers.
A continuous fiber means a reinforcing fiber obtained by aligning a reinforcing fiber bundle in a continuous state without cutting the reinforcing fiber into short fibers. For the purpose of obtaining a composite material a having excellent mechanical properties, it is preferable to use continuous reinforcing fibers. More specifically, the continuous fiber is preferably a fiber having a length of 1 m or more. It is used as a prepreg impregnated with uncured resin.

[Composite material a]
The composite material a is reinforced with reinforcing fibers. Hereinafter, an example of the embodiment performed by the present inventors will be described, but the present invention is not limited to the composite material a described below.

1. Molded Body The composite material a is preferably a molded body after molding, and may be a molded body using a thermoplastic resin or a molded body using a thermosetting prepreg. A prepreg is a sheet of continuous carbon fibers arranged in one direction (unidirectional prepreg), a substrate made of carbon fibers such as a carbon fiber fabric impregnated with a thermosetting resin, or a thermosetting resin. It is an intermediate molding material impregnated with a part of resin and the remaining part is arranged on at least one surface.

2. Unidirectional Material Composite material a is preferably a unidirectional material. The unidirectional material refers to a material in which continuous reinforcing fibers with a length of 100 mm or more are aligned in one direction inside the composite material a. As the unidirectional material, a laminate of a plurality of continuous reinforcing fibers may be used. In particular, when the composite material a is a unidirectional material and is a composite material using a thermosetting prepreg, the mechanical properties are less affected by fiber orientation. Therefore, it is possible to improve the accuracy of estimating mechanical property information using a model, which will be described later.

[Preferred composite material]
The composite material contains reinforcing fibers and a matrix resin as essential components, and other components as optional components.

Vr=(t2−t1)/t2×100 Formula (A)
t1=(Wf/Df+Wm/Dm+Wz/Dz)/Area (mm ² ) Formula (B)

t1: Theoretical thickness of composite material (mm)
t2: Measured thickness of composite material (mm)
Df: Density of reinforcing fiber (mg/mm ³ )
Dm: density of matrix resin (mg/mm ³ )
Dz: Density of other components (mg/mm ³ )
Wf: mass of reinforcing fiber (mg)
Wm: Mass of matrix resin (mg)
Wz: mass of other components (mg)
The porosity Vr is more preferably 5% or less, still more preferably 3% or less. If the porosity is within the range, the accuracy of mechanical property prediction of the present invention is improved.

[Production of composite material a]
For example, composite material a can be prepared as follows.
1. Material Reinforcing fiber: Carbon fiber “Tenax (registered trademark)” STS40-24K (tensile strength 4,300 MPa, tensile modulus 240 GPa, number of filaments 24,000, fineness 1,600 tex, elongation 1.8%, density 1 .78 g/cm ³ , manufactured by Teijin Limited)
・Base material resin: Thermosetting resin composition with epoxy resin as the main component

2. Preparation of unidirectional prepreg A unidirectional prepreg was prepared by a hot-melt method as follows. First, a coater was used to apply the above thermosetting resin composition onto release paper to prepare a resin film. Next, the carbon fiber bundles are sent out from the creel, passed through a comb, and after aligning the pitch between the carbon fiber bundles, are widened through a fiber opening bar to form a sheet having a fiber basis weight per unit area of 100 g/m ² . aligned in one direction. After that, the above resin films were superimposed on both sides of the carbon fiber, heated and pressurized to impregnate with the thermosetting resin composition, and wound up with a winder to produce a unidirectional prepreg. The resulting unidirectional prepreg had a resin content of 30 wt. %.

3. Preparation of Composite Material a Eleven sheets of unidirectional prepreg were manually laminated in the direction of 0° to obtain a prepreg laminate having a lamination structure of [011] _T . The prepreg laminate is placed in a bag film, heated in an autoclave, heated at 130 ° C. for 120 minutes, and cured to form a 1 mm thick CFRP molded body (unidirectional carbon fiber reinforced thermosetting resin composite A material, Composite a), was produced.

[Measurement of tensile modulus and tensile strength]
As specific examples of the breaking strength or elastic modulus of the present invention, the present inventors measured the tensile elastic modulus and tensile strength of the composite material a as described below.
The above CFRP molded body was processed into a test piece shape (length 250 mm×width 15 mm) by a water jet, and a tab made of glass fiber reinforced resin matrix composite material was adhered. Based on ASTM D3039 method, a 0° direction tensile test was performed using a universal testing machine at a test speed of 2 mm/min to calculate the tensile modulus and tensile strength of the CFRP molded body (composite material a).

[Vibration characteristic information]
In the present invention, the nondestructive inspection information is preferably vibration characteristic information. There is no particular limitation on the vibration inspection method used to acquire the vibration characteristic information, and any inspection method that detects internal defects, voids, or foreign matter in the molded body region without destroying the molded body region may be used. Also, the finite element method (FEA) may be used to acquire the vibration characteristic information. As the vibration characteristic information, an image obtained by converting the information obtained by the vibration inspection or the finite element method is preferably used, and it is particularly preferable that the converted image is a wavelet image.

Specific wavelet images are shown in FIGS. 8A to 8D. To acquire this image, vibration measurements were performed with impulse excitation under free-free boundary conditions. A hole of Φ2 mm was made in the molded body, and a nylon line (22-8231 manufactured by Takagi Tsugyo Co., Ltd.) was passed through the hole and suspended from a beam to obtain a free-free boundary condition. An acceleration pickup sensor (356A01 made by PCB PIEZOTRONICS) was installed in the area of the compact, and vibration was applied using an impulse hammer (GK-3100 made by Ono Sokki). A real-time acoustic vibration analysis system (DS-3000 manufactured by Ono Sokki Co., Ltd.) was used for data measurement and analysis. At this time, the sampling frequency was set to 2000 Hz.

The obtained vibration data was analyzed using wavelet analysis software (BIOMAS manufactured by ELMEC) to obtain a wavelet image showing vibration frequency on the vertical axis, time on the horizontal axis, and vibration amplitude on the luminance and hue. .
Figures 8A and 8B are wavelet images of defect-free compact areas, and Figures 8C and 8D are wavelet images of defective compact areas. 8A to 8D are images obtained by binarizing the two-dimensional image obtained by analyzing the vibration, and indicate that the more the white portion, the greater the amplitude of the vibration at that frequency. A portion indicated by reference numeral 803 in FIG. 8C and reference numeral 804 in FIG. 8D has a spherical pattern, and it can be seen that vibration of about 450 Hz was intermittently generated. 8C and 804 in FIG. 8D are clearly different from 801 in FIG. 8A and 802 in FIG. 8B.

[Vibration damping of vibration characteristics]
The image preferably contains vibration damping information. Vibration damping is a vibration phenomenon in which the amplitude decreases over time in time history data of vibration. For example, looking at the pattern 801 in FIG. 8A and the pattern 802 in FIG. 8B, the length of the white pattern in the vertical direction at about 450 Hz in FIGS. is seen to be attenuating. At this time, the speed at which the vibration of about 450 Hz is damped is faster at reference numeral 801 in FIG. 8A than at reference numeral 802 in FIG. 8B. 8A-8D, the faster the vibration at about 450 Hz damped, the smaller the tensile modulus and tensile strength. It should be noted that FIGS. 8A-8D are merely examples. The frequency at which vibration damping occurs differs depending on the shape and natural frequency of the test piece. In addition, mechanical properties other than tensile modulus and tensile strength do not necessarily decrease as vibration damping speed increases.

[Acoustic characteristics]
The non-destructive inspection information in the present invention may be acoustic property information.
[frequency]
1. Sampling Frequency In general, the sampling frequency refers to the frequency of taking samples per unit time in sampling, which is the processing required to convert analog waveforms such as voice into digital data. In order to correctly sample a certain waveform, it is necessary to sample at a frequency that is at least twice the bandwidth of the frequency component of the waveform. In the present invention, the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information of the second composite material is over 0 Hz.
The lower limit is preferably 50 Hz or higher, more preferably 250 Hz or higher, even more preferably 5,000 Hz or higher, and even more preferably 10,000 Hz or higher. On the other hand, the upper limit is preferably 50,000 Hz or less, more preferably 40,000 Hz or less, and even more preferably 30,000 Hz or less.
Therefore, the sampling frequency is preferably 50 Hz or more and 50,000 Hz or less, more preferably 250 Hz or more and 50,000 Hz or less, further preferably 5,000 Hz or more and 40,000 Hz or less, and 10,000 Hz or more. 30,000 Hz or less is even more preferable.
From another point of view, the sampling frequency is preferably at least twice the frequency at which vibration damping occurs.
From another point of view, the sampling frequency for obtaining the vibration characteristics of the second composite material is preferably twice or more the natural frequency of the primary mode described later, and more than twice the natural frequency of the secondary mode. preferable.

2. Natural Frequency of Primary Mode When the non-destructive inspection information is vibration characteristic information, the natural frequency of the primary mode of the first composite material and the second composite material is preferably between 0 Hz and 1000 Hz or less. Within this range, for example, when the molded body is assembled in an automobile, comfort is improved without resonating with vibrations from the outside or from the engine room. More preferably, the primary mode natural frequency of the first composite material and the second composite material is more than 0 Hz and 500 Hz or less.
On the other hand, when the non-destructive inspection information is acoustic property information, the natural frequency of the primary mode of the first composite material and the second composite material is preferably more than 0 Hz and 20,000 Hz or less, and more than 0 Hz and 10,000 Hz or less. It is more preferable to have

[Finite element method]
The mechanical property information or non-destructive inspection information of the first composite material is preferably obtained by the finite element method. Here, the finite element method (FEM) is one of numerical analysis techniques, and can numerically obtain approximate solutions of differential equations that are difficult to solve analytically. Actual measurement of mechanical properties or non-destructive testing (preferably vibration characteristics or acoustic characteristics information) by creating an analysis model that applies material parameters identified in advance by comparing actual measurements and analyses, to the shape of the first composite material. These information can be obtained by the finite element method without

[Inspection system]
Data converted into a format that can be input to the input layer of the neural network is hereinafter referred to as input data. In the inspection system, the non-destructive test information (hereinafter referred to as the non-destructive test information sample) of the sample of the first composite material a (hereinafter referred to as the composite material sample b) and the machine obtained by actual measurement from the composite material sample b Physical property information (hereinafter referred to as a mechanical physical property information sample) is acquired as second input data, and neural network learning is performed using this second input data. When the learning of the neural network is completed, the non-destructive inspection information of the composite material a is input to the neural network as the first input data, and the mechanical property information of the composite material a is estimated based on the reaction values in the output layer from the neural network. . Based on the estimated mechanical property information, the composite material a may be sorted into non-defective products and non-defective products.

In order for the inspection system to perform effective learning and high-precision inference, it is possible to use non-destructive inspection information (preferably vibration inspection images or acoustic property images) optimized for learning and inference processing. For example, various image processing may be performed on the vibration test image so that detection of the vibration test image is facilitated. Note that the vibration inspection image is one type of vibration characteristic information.

[Inspection device]
FIG. 1 is a block diagram showing a configuration example of an inspection apparatus 1. As shown in FIG. The inspection apparatus 1 performs image processing, generation of input data, neural network learning, and estimation of machine physical property information using the neural network. The inspection apparatus 1 is an information processing apparatus such as a computer that includes one or more processors such as a CPU (Central Processing Unit), a storage unit, and a communication unit, and runs an OS (operating system) and applications. be. The inspection device 1 may be a physical computer, a virtual machine (VM), a container, or a combination thereof. The structure of the processor is, more specifically, an electric circuit combining circuit elements such as semiconductor elements.

The inspection apparatus 1 includes an image storage unit 11 that stores nondestructive inspection information and nondestructive inspection information samples, a processing unit 12 that processes the nondestructive inspection information and nondestructive inspection information samples, an input data generation unit 13, and a learning unit. A data storage unit 14 , a learning unit 15 , a model storage unit 16 , an estimation unit 17 , a display unit 18 and an operation unit 19 are provided. The processing unit 12, the input data generating unit 13, the learning unit 15, and the estimating unit 17 are functional blocks implemented by the processor of the inspection apparatus 1 executing programs. This program includes an inspection program for composite materials.

The image storage unit 11 is preferably a storage area for storing vibration inspection images (or acoustic characteristic images). The image memory portion 11 is a volatile memory such as SRAM (Static Random Access Memory) and DRAM (Dynamic RANDOM ACCESSS MEMORY). MagNetroResistive Random Access Memory) A non-volatile memory such as FeRAM (Ferroelectric Random Access Memory) may also be used.

The processing unit 12 preferably performs image processing on the vibration inspection image (or the acoustic characteristic image), and stores the image after the image processing in the image storage unit 11 . Examples of image processing include generating an image by extracting the luminance of each color of red, green, and blue (RGB) in pixels in the image, and subtracting the luminance of green (G) from the luminance of red (R) in each pixel. generation of an image obtained by converting to the HSV color space, generation of an image in which only the red component is extracted, and the like, but other types of image processing may be performed.
The processing unit 12 may also perform image enlargement, reduction, cropping, noise removal, rotation, inversion, color depth change, contrast adjustment, brightness adjustment, sharpness adjustment, color correction, and the like.

The input data generation unit 13 generates input data to be input to the input layer of the neural network from the nondestructive inspection information or nondestructive inspection information samples stored in the image storage unit 11 . For example, when the later-described learning is performed using the vibration test image, it is preferable to cut out a desired portion from the vibration test image or remove an extra portion from the vibration test image to obtain the second input data.

When the inspection device 1 is executing the learning process, the input data generation unit 13 saves the input data in the learning data storage unit 14 . When the inspection device 1 is inspecting the composite material a, the input data is transferred to the estimation unit 17 .
Note that, when performing the learning process, the input data generation unit 13 may generate input data using, for example, an image (non-destructive inspection information sample) captured by an external device or system.

The learning data storage unit 14 is a storage area that stores a plurality of input data used for neural network learning. The input data stored in the learning data storage unit 14 is used as learning data for the learning unit 15 . Input data (second input data) used as learning data is stored in association with a mechanical property information sample obtained by measuring the composite material sample b from which the input data is obtained. In addition to at least one of the mechanical property rank and the mechanical property value (e.g., elastic modulus) of the composite material sample b, this mechanical property information sample includes information indicating that the mechanical property value corresponds to a non-defective product, and information indicating that the mechanical property value corresponds to a defective product. and information indicating that it is difficult to estimate mechanical property values.

For example, the correspondence of the mechanical property information sample to the second input data obtained from the composite material sample b (hereinafter, this correspondence is also referred to as labeling) is the mechanical property value of the composite material sample b (for example, the elastic modulus ) can be directly input by the user operating the operation unit 19 . After the input, the inspection apparatus 1 sorts the mechanical property values into mechanical property ranks. For example, the tensile modulus can be classified into the following mechanical property ranks.
Mechanical property rank 1: Tensile modulus of composite material is 30 GPa or more Mechanical property rank 2: Tensile modulus of composite material is 25 to 30 GPa
Mechanical property rank 3: Tensile modulus of composite material is 25 GPa or less

This mechanical property rank may be output in units of 3 GPa or 1 GPa instead of 5 GPa as described above. In addition, if the mechanical property information sample corresponding to the second input data obtained from the composite material sample b is known, the mechanical property rank can be automatically labeled by a program or script instead of the user operation. good. The mechanical property rank labeling may be performed before or after converting the nondestructive test information sample obtained from the composite material sample b into the second input data.

The learning unit 15 uses the input data (second input data) stored in the learning data storage unit 14 to perform neural network learning. The learning unit 15 stores the learned neural network in the model storage unit 16 . The learning unit 15 can learn, for example, a three-layer neural network consisting of an input layer, a hidden layer, and an output layer. Real-time response performance during inspection of the composite material a can be ensured by learning the three-layer neural network. The number of units included in each of the input layer, hidden layer, and output layer is not particularly limited. The number of units included in each layer can be determined based on required response performance, inference target, discrimination performance, and the like.

It should be noted that the three-layer neural network is just an example, and this does not preclude the use of multi-layer neural networks with more layers. When using a multi-layered neural network, various types of neural networks such as convolutional neural networks can be used.

The model storage unit 16 is a storage area that stores the neural network learned by the learning unit 15. A plurality of neural networks may be stored in the model storage unit 16 according to the type of the composite material a to be inspected. Since the model storage unit 16 is set so that it can be referred to by the estimation unit 17, the estimation unit 17 uses the neural network stored in the model storage unit 16 to inspect the composite material a (estimate mechanical property information). be able to. The model storage unit 16 may be a volatile memory such as RAM or DRAM, or a non-volatile memory such as NAND flash memory, MRAM or FeRAM. Note that the model storage unit 16 may be located at a location accessible by the processor of the inspection apparatus 1 and may not be built in the inspection apparatus 1 . For example, the model storage unit 16 may be a storage externally attached to the inspection device 1 or a network storage connected to a network accessible from the inspection device 1 .

The estimation unit 17 uses the neural network stored in the model storage unit 16 to estimate the mechanical property information of the composite material a. The estimation unit 17 estimates the mechanical property rank of the composite material a based on the reaction values output from the units of the output layer. Examples of units in the output layer include a unit with mechanical property rank 1, a unit with mechanical property rank 2, a unit with mechanical property rank 3, and a unit that is difficult to guess, but other types of units may be prepared. . For example, there is a possibility that a large amount of foreign matter or the like is mixed in a product with a low estimated mechanical property rank. The mechanical property rank of the composite material a may be estimated using the difference or ratio of the reaction values of a plurality of units.

The display unit 18 is a display that displays images and text. The display unit 18 may display a photographed image, an image after image processing, or an estimation result by the estimation unit 17 .

The operation unit 19 is a device that provides means for operating the inspection device 1 by the user. The operation unit 19 is, for example, a keyboard, mouse, buttons, switches, voice recognition device, etc., but is not limited to these.

[Learning process]
Before estimating the mechanical property rank of the composite material a by the inspection device 1, the neural network is trained using the non-destructive inspection information sample and the mechanical property information sample of the composite material sample b of the same type as the composite material a. There is a need. FIG. 2 is a flowchart of learning processing.

First, the processor of the inspection device 1 acquires a nondestructive information sample for each of the multiple composite material samples b (step S201). Non-destructive information samples include, for example, vibration information obtained by vibration inspection of composite material samples. Composite material samples from which non-destructive inspection information is acquired include those with high and low mechanical property ranks. When a unit that outputs a reaction value that is difficult to guess is provided in the output layer of the neural network, a nondestructive test information sample that makes it difficult to guess the mechanical property information of the composite material sample may be prepared. Examples of difficult-to-guess nondestructive test information samples include images in which the composite material sample b is not sufficiently captured, composite material sample b image is not clear.

The processor of the inspection apparatus 1 generates second input data from each acquired nondestructive inspection information sample (step S201). Next, the processor of the inspection apparatus 1 acquires mechanical property information samples for each of the plurality of composite material samples b, and stores the acquired mechanical property information samples in association with the respective second input data (step S203 ).
Note that step S203 may be performed before step S202. In this case, even after each nondestructive inspection information sample is converted to the second input data, the mechanical property information sample associated with the nondestructive inspection information sample is taken over to the second input data. good.

Next, the processor of the inspection device 1 starts learning by the neural network based on the second input data (step S204).

FIG. 3 shows an example of a neural network that outputs three response values. A neural network 301 in FIG. 3 is a neural network having three layers: an input layer 302 , a hidden layer 303 and an output layer 304 . The output layer 304 includes

units

311, 312, 313 that infer mechanical property ranks. Although there are three

units

311, 312, and 313 in FIG. 3, the number can be increased or decreased as appropriate according to the rank of mechanical properties.
In a neural network, a value input to an input layer is propagated through a hidden layer and an output layer to obtain a reaction value of the output layer. In step S205, when the second input data is input to the neural network, a hidden Neural network parameters and structures, such as the number of layers 303, the number of units included in each of the input layer 302 and hidden layer 303, and the coupling coefficients between units included in each of the input layer 302 and hidden layer 303, are adjusted. be. In this way, a mechanical physical property estimation model is generated and stored in the model storage unit 16 .

FIG. 4 shows arithmetic processing between units of the neural network. FIG. 4 shows the units of the (m−1)-th layer and the units of the m-th layer. For the sake of explanation, it is assumed that only some units of the neural network are shown in FIG. The unit numbers in the (m-1)-th layer are k=1, 2, 3, . . . The unit numbers in the m-th layer are j=1, 2, 3, . . .
Assuming that the reaction value of unit number k of the (m-1)-th layer is a _k ^m-1 , the reaction value of unit number j of the m-th layer a _j ^m can be obtained using the following equation (2).

Here, W _jk ^m is a weight and indicates the strength of coupling between units. b _j ^m is the bias. f(...) is the activation function. From equation (2), the reaction value of an arbitrary unit in the m-th layer is obtained by weighted addition of the reaction values of all units (k=1, 2, 3, . . . ) in the m−1-th layer and activating You can see that it is the output value when input as a variable of the function.
Next, examples of activation functions will be described. Equation (3) below is the normal distribution function.

Here, μ is the average value and indicates the central position of the bell-shaped peak drawn by the normal distribution function. σ is the standard deviation and indicates the width of the peak. Since the value of Equation (3) depends only on the distance from the center of the peak, the Gaussian function (normal distribution function) can be said to be a kind of radial basis function (RBF). A Gaussian function (normal distribution function) is an example, and other RBFs may be used.
Equation (4) below is a sigmoid function. The sigmoid function asymptotically approaches 1.0 in the limit of x→∞. Also, it asymptotically approaches 0.0 at the limit of x→−∞. That is, the sigmoid function takes values in the range (0.0, 1.0).

It should be noted that this does not preclude the use of functions other than the Gaussian function and the sigmoid function as the activation function. For example, we used Relu in the convolutional layer and softmax in the output layer.

In neural network learning, after input data is input to the input layer, the weight _Wjk , which is the strength of the connection between units, is adjusted so that a correct output is obtained. A correct output (reaction value of a unit in the output layer) expected when inputting input data labeled with a certain mechanical property rank in a neural network is also called a teacher signal.
For example, if input data labeled with a mechanical property rank of 311 is input to the neural network 301, the reaction value of the unit 311 is 1, the reaction value of the unit 312 is 0, and the reaction value of the unit 313 is 0 in the teacher signal. . When input data labeled with a mechanical property rank of 312 is input to the neural network 301, the reaction value of the unit 311 is 0, the reaction value of the unit 312 is 1, and the reaction value of the unit 313 is 0 in the teacher signal.
For example, the adjustment of the weights _Wjk can be performed using a back propagation method (Back Propagation Method). In the backpropagation method, the weights _Wjk are adjusted in order from the output layer so that the deviation between the output of the neural network 310 and the teacher signal becomes small. Equation (5) below shows the improved backpropagation method.

Note that when a Gaussian function is used as the activation function, not only the weight _Wjk but also σ and μ in Equation (3) are subject to adjustment as parameters in the improved back propagation method. By adjusting the values of the parameters σ and μ, the learning convergence of the neural network is assisted. Equation (6) below shows the value adjustment process performed for the parameter σ.

Equation (7) below shows the value adjustment process performed for the parameter μ.

Here, t is the number of times of learning, η is a learning constant, _δk is a generalization error, _Oj is a response value of unit number j, α is a sensitivity constant, and β is a vibration constant. ΔW _jk , Δσ _jk , and Δμ _jk indicate respective correction amounts of weights W _jk , σ, and μ.

Here, the modified back propagation method is used as an example to describe the process of adjusting the weights W _jk and parameters, but a general back propagation method may be used instead. Hereinafter, when the backpropagation method is simply referred to, it includes both the improved backpropagation method and the general backpropagation method.
The number of times the weights _Wjk and parameters are adjusted by the backpropagation method may be one time or a plurality of times, and is not particularly limited. In general, it can be determined whether or not to repeat adjustment of the weights _Wjk and parameters by the back propagation method based on the estimation accuracy of the mechanical property rank when using test data. Repeated adjustment of the weight _Wjk and parameters may improve the accuracy of estimating the mechanical property rank.
By using the method described above, the values of the weights W _jk , the parameters σ and μ can be adjusted in step S205. Once the values of the weights W _jk , parameters σ, and μ are adjusted, it is possible to perform an inference process using a neural network.

FIG. 5 is a flowchart for explaining the operation of estimating mechanical property information by the inspection device 1 that operates according to the composite material inspection program. The processor of the inspection apparatus 1 acquires non-destructive inspection information of the composite material a (preferably captures a vibration inspection image or an acoustic property image) (step S501). When the vibration test image (or acoustic property image) is used as non-destructive test information, there may be a step of performing image processing on the vibration test image (or acoustic property image) between steps S501 and S502.

Next, the processor of the inspection device 1 generates first input data from the nondestructive inspection information (step S502). The first input data has N elements equal to the number of units in the input layer of the neural network, and is in a format that can be input to the neural network.

Next, the processor of the inspection device 1 inputs the first input data to the neural network (step S503). The first input data is transmitted in order of the input layer, the hidden layer, and the output layer. The processor of the inspection device 1 estimates the mechanical property rank based on the reaction values in the output layer of the neural network (step S504).

The inference process using a neural network is equivalent to the process of finding the position of the first input data within the identification space. FIG. 6 shows an example of a discriminant space when using a Gaussian function as an activation function. If a radial basis function (RBF) such as a Gaussian function is used as the activation function, the identification surface that divides the identification space into regions for each rank of mechanical properties becomes a closed surface. Further, by adding a height direction index to each category of the mechanical property rank, it is possible to localize the area related to each category in the identification space.

Fig. 7 shows an example of the discriminant space when using the sigmoid function as the activation function. If the activation function is a sigmoid function, the identification surface is an open surface. The learning process of the neural network described above corresponds to the process of learning a discriminative curved surface in the discriminative space. Although only the mechanical property rank 311 and the mechanical property rank 312 are shown in the regions in FIGS. 6 and 7, there may be distributions of three or more mechanical property ranks.

As described above, by using the inspection system of this embodiment, the mechanical property information of the composite material a can be estimated from the non-destructive inspection information (preferably vibration inspection image or acoustic property image) of the composite material a. In the inventions described in Patent Document 2 (International Publication No. 2019/151393) and Patent Document 3 (International Publication No. 2019/151394), a neural network is used to determine what a human can judge by looking at an image or a measurement object. It's just a substitute. In other words, in these inventions, since the object to be inspected is the photographed food, humans can easily determine the presence or absence of foreign matter in the food.
On the other hand, the mechanical property information is a numerical value or a rank based on this, and the non-destructive inspection information (preferably vibration inspection image or acoustic property image) is a visualization or numerical representation of the internal state of the composite material. . In other words, even if a skilled worker sees the non-destructive inspection information, he cannot infer mechanical property information from it.
For example, no matter how hard humans try, it is clear that they cannot guess machine physical property information from the vibration inspection images of FIGS. 8A to 8D. By using the inspection apparatus 1 of the present embodiment, it is possible to instantaneously infer mechanical property information that cannot be inferred no matter how hard a skilled worker tries, without actually measuring it.

This application claims priority based on Japanese Patent Application No. 2021-210610 filed on December 24, 2021.

Claims

A mechanical property estimation model generated by machine learning based on the mechanical property information and the nondestructive test information of the first composite material containing reinforcing fibers, wherein the mechanical property information and the nondestructive test information are known,
Accessible to a model storage unit for storing a mechanical property estimation model for estimating mechanical property information of the second composite material with input of non-destructive inspection information of a second composite material containing reinforcing fibers whose mechanical property information is unknown. with a processor
The processor acquires non-destructive inspection information of the second composite material, inputs the non-destructive inspection information into the mechanical property estimation model, and extracts the mechanical property information of the second composite material from the mechanical property estimation model. Acquire, output based on the mechanical property information,
The composite material inspection apparatus, wherein the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is higher than 0 Hz.
The inspection device according to claim 1,
The inspection device, wherein the non-destructive inspection information is an image or numerical data indicating vibration characteristics or acoustic characteristics.
The inspection device according to claim 1 or 2,
The inspection device, wherein the mechanical property information is information on the elastic modulus or breaking strength of the composite material.
The inspection device according to claim 3,
The information on the elastic modulus includes the elastic modulus or the rank when the elastic modulus is ranked,
The inspection device, wherein the information about the breaking strength includes the breaking strength or the rank when the breaking strength is ranked.
The inspection device according to claim 4,
The information on the elastic modulus or breaking strength includes information indicating that the elastic modulus or breaking strength is difficult to estimate, information indicating that the elastic modulus or breaking strength corresponds to a defective product, and the elasticity inspection device including at least one of information indicating that the modulus or breaking strength corresponds to a good product.
The inspection device according to any one of claims 1 to 5,
The inspection device, wherein the reinforcing fibers are carbon fibers.
The inspection device according to any one of claims 1 to 6,
The inspection device, wherein the first composite material and the second composite material are each a prepreg containing a thermosetting matrix resin.
The inspection device according to any one of claims 1 to 7,
The inspection device, wherein the first composite material and the second composite material are each unidirectional materials.
The inspection device according to any one of claims 1 to 8,
The inspection device, wherein the mechanical property information or non-destructive inspection information of the first composite material includes at least one piece of information obtained by a finite element method.
The inspection device according to claim 2,
The inspection device, wherein the image includes a vibration damping waveform.
The inspection device according to any one of claims 1 to 10,
The inspection device, wherein the non-destructive inspection information is vibration characteristic information.
The inspection device according to claim 11,
The inspection apparatus, wherein the sampling frequency when acquiring the vibration characteristic information is 250 Hz or more and 50,000 Hz or less.
The inspection device according to claim 11 or 12,
The inspection apparatus, wherein the first composite material and the second composite material have a primary mode natural frequency of more than 0 Hz and not more than 1000 Hz.
The inspection device according to any one of claims 1 to 10,
The inspection device, wherein the non-destructive inspection information is acoustic property information.
The inspection device according to claim 14,
The inspection apparatus, wherein the first composite material and the second composite material have primary mode natural frequencies of more than 0 Hz and 20,000 Hz or less.
By machine learning the mechanical property information and the non-destructive test information of the first composite material containing reinforcing fibers for which the mechanical property information and non-destructive test information are known, the second containing reinforcing fibers for which the mechanical property information is unknown generating a mechanical property estimation model for estimating mechanical property information of the second composite material using non-destructive inspection information of the two composite materials as input;
obtaining non-destructive inspection information of the second composite material;
a step of inputting the acquired non-destructive inspection information into the mechanical property estimation model, acquiring mechanical property information of the second composite material from the mechanical property estimation model, and outputting based on the mechanical property information; with
The composite material inspection method, wherein the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is higher than 0 Hz.
By machine learning the mechanical property information and the non-destructive test information of the first composite material containing reinforcing fibers for which the mechanical property information and non-destructive test information are known, the second containing reinforcing fibers for which the mechanical property information is unknown generating a mechanical property estimation model for estimating mechanical property information of the second composite material using non-destructive inspection information of the two composite materials as input;
obtaining non-destructive inspection information of the second composite material;
a step of inputting the acquired non-destructive inspection information into the mechanical property estimation model, acquiring mechanical property information of the second composite material from the mechanical property estimation model, and outputting based on the mechanical property information; is a program that causes the processor to execute
The composite material inspection program, wherein the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and the sampling frequency when acquiring the non-destructive inspection information is higher than 0 Hz.
A recording medium storing the inspection program according to claim 17.