Deformation temperature prediction method, deformation temperature prediction device, and program

Abstract

The goal is to improve the accuracy of qualitative deformation temperature predictions. [Solution] A deformation temperature prediction method (deformation temperature prediction process) using a deformation temperature prediction device, comprising a first prediction step (step S3) of predicting the deformation temperature from the formulation information and elastic modulus of the resin material.

Description

Technical Field

[0001] The present invention relates to a method for predicting deformation temperature, a device for predicting deformation temperature, and a program.

Background Art

[0002] In recent years, material development utilizing data science such as machine learning has begun to be adopted by research institutions and material development manufacturers. Specifically, in the formulation design of resin composite materials, a system is constructed to predict target physical properties using formulation information and the like as explanatory variables. For example, Patent Document 1 describes that in order to improve prediction accuracy, a plurality of prediction models are created, and the model with the best accuracy is adopted to enhance the prediction accuracy.

Prior Art Documents

Patent Documents

[0003] [[ID=2�]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, the mechanical strength could be predicted with relatively high accuracy from the formulation of raw materials, but the prediction accuracy of deformation temperatures such as the deflection temperature under load, which are thermal physical properties, was low, presenting a problem in practical use.

[0005] Therefore, an object of the present invention is to improve the prediction accuracy of qualitative deformation temperatures.

Means for Solving the Problems

[0006] To solve the above problems, the deformation temperature prediction method according to the present invention in the deformation temperature prediction method by a deformation temperature prediction device, includes a first prediction step of predicting the deformation temperature from the formulation information and elastic modulus of the resin material.

[0007] Furthermore, the deformation temperature prediction device according to the present invention is It includes a prediction unit that predicts the deformation temperature from the formulation information and elastic modulus of the resin material.

[0008] Furthermore, the program according to the present invention is A computer for a deformation temperature prediction device that predicts the deformation temperature of resin materials, A prediction unit that predicts the deformation temperature from the formulation information and elastic modulus of the resin material. To make it function as such. [Effects of the Invention]

[0009] According to the present invention, the accuracy of qualitative deformation temperature prediction is improved. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the configuration of the deformation temperature prediction device. [Figure 2] This is a flowchart of the deformation temperature prediction process. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described below with reference to the drawings. However, the scope of the present invention is not limited to those described in the following embodiments and drawings.

[0012] <Deformation Temperature Prediction Device 1> First, the configuration of the deformation temperature prediction device 1 will be explained using Figure 1. The deformation temperature prediction device 1 is an information processing device that predicts the deformation temperature of a resin composite material. Specifically, the deformation temperature prediction device 1 is an information processing device that predicts the deformation temperature from the formulation information and elastic modulus of the resin material. Resin composite materials include polycarbonate or styrene-based resin composite materials. Resin composite materials may use recycled materials in part or all of the resin material.

[0013] Next, the configuration of the deformation temperature prediction device 1 will be explained using Figure 1. As shown in Figure 1, the deformation temperature prediction device 1 includes a control unit 11, an operation unit 12, a communication unit 13, a storage unit 14, and a display unit 15.

[0014] The control unit 11 is composed of a CPU (Central Processing Unit), RAM (Random Access Memory), etc. The CPU of the control unit 11 reads various programs stored in the memory unit 14, loads them into the RAM, executes various processes according to the loaded programs, and controls the operation of each part of the deformation temperature prediction device 1.

[0015] The control unit 11 functions as a first prediction unit (prediction unit) that predicts the deformation temperature (first prediction) from the formulation information and elastic modulus of the resin material. The control unit 11 functions as a second prediction unit that predicts the flexural modulus (second prediction) from the formulation information of the resin material. Formulation information includes the type and proportion of resin used, and the type and proportion of additives. Furthermore, formulation information may include information obtained by irradiating the resin with electromagnetic waves and detecting the electromagnetic waves generated from the resin. Additionally, formulation information may be obtained from the thermal properties of the resin. The modulus of elasticity is a material property that represents the resistance to deformation. It is the proportionality constant between stress and strain applied to a material, and it is a force that affects deflection when a load is applied. Examples of modulus of elasticity include the flexural modulus, tensile modulus, and compressive modulus. The deformation temperature is the temperature at which a certain amount of deformation is reached when a load is applied. Examples of deformation temperatures include the deflection temperature and the Vicat softening temperature.

[0016] The first and second predictions are performed using analytical models such as machine learning models. The first analysis model for prediction is assumed to be learned such that when formulation information of a resin material and the elastic modulus are input as input information, the deformation temperature is output as output information. For example, the type and ratio of the resin and the type and ratio of the additive are learned by the analysis model as formulation information. For example, the flexural elastic modulus is measured with a tensilon under the conditions of JIS 7127, and the heat deflection temperature is subjected to an HDT tester 3M-2 manufactured by Toyo Seiki Seisakusho Co., Ltd., conditioned at 23°C and 50% RH for 48 hours, and for the conditioned test piece, the heat deflection temperature (load 1.80 MPa) is measured in accordance with ISO 75-1, 2, and the measured value is learned by the analysis model. The second analysis model for prediction is assumed to be learned such that when formulation information is input as input information, the flexural elastic modulus is output as output information.

[0017] Note that the control unit 11 functioning as the first prediction unit may predict the deformation temperature using the manufacturing conditions of the resin material as well. Also, the control unit 11 functioning as the second prediction unit may predict the flexural elastic modulus using the manufacturing conditions of the resin material as well. The manufacturing conditions are kneading conditions. Also, the manufacturing conditions may be sorting, cleaning, drying of recycled materials, and kneading conditions. In this case, it is assumed that the manufacturing conditions of the resin material are added as the input information of the first and second analysis models for prediction.

[0018] The operation unit 12 is a keyboard equipped with cursor keys, numeric input keys, various function keys, etc., a pointing device such as a mouse, a touch panel laminated on the surface of the display unit 15, etc. The operation unit 12 is configured to be operable by an operator. Also, the operation unit 12 outputs various signals based on the operations performed by the operator to the control unit 11.

[0019] The communication unit 13 is capable of transmitting and receiving various signals and various data to and from other devices etc. that are communicatively connected via a communication network.

[0020] The memory unit 14 is composed of non-volatile semiconductor memory or a hard disk, and stores various programs executed by the control unit 11, parameters necessary for program execution, and various data. The memory unit 14 stores the analysis models for the first and second predictions described above.

[0021] The display unit 15 is composed of a monitor such as an LCD (Liquid Crystal Display) and displays various screens, etc., according to the instructions of the display signals input from the control unit 11.

[0022] <Deformation temperature prediction processing> Next, using Figure 2, we will explain the deformation temperature prediction process performed in the deformation temperature prediction device 1, which predicts the deformation temperature of a resin composite material. Here, the modulus of elasticity is defined as the bending modulus of elasticity, and the deformation temperature is defined as the temperature of deflection under load.

[0023] First, the control unit 11 acquires formulation information and / or manufacturing conditions (step S1). For example, the control unit 11 may acquire formulation information and / or manufacturing conditions from the operation unit 12, which is operated by the user.

[0024] Next, the control unit 11 inputs the formulation information and / or manufacturing conditions acquired in step S1 into a second prediction analysis model to predict the flexural modulus (step S2; second prediction step).

[0025] Next, the control unit 11 inputs the bending modulus predicted in step S2 into the analysis model for the first prediction and predicts the load deflection temperature (step S3; first prediction step, prediction step).

[0026] Next, the control unit 11 outputs the load deflection temperature predicted in step S3 (step S4). For example, the control unit 11 outputs the load deflection temperature to the display unit 15, allowing the user to confirm the predicted load deflection temperature.

[0027] Thus, by predicting the deformation temperature not only from the formulation information of the resin material but also from the formulation information and the elastic modulus of the resin material, the accuracy of qualitative deformation temperature prediction is improved, as will be described later.

[0028] <Examples> [Table 1] The improvement in the accuracy of deformation temperature prediction is explained using the patterns shown in Table I. Pattern 1 is a conventional prediction method, in which deformation temperature is predicted directly from formulation information. Input 1 of Pattern 1 is the input information of a conventional analysis model, and 100 samples were prepared with different resin types and proportions, and additive types and proportions. The load deflection temperature was measured for each sample, and an analysis model was constructed to predict the load deflection temperature using 80 data points. Output 1 of Pattern 1 is the output information of the conventional analysis model. The load deflection temperature, which is Output 1, was predicted using the 20 unused data points. The model was evaluated using the root mean squared error (Root Mean Squared Error) between the predicted and measured values ​​using the 20 predicted data points. Pattern 2 is the prediction method described above. Using the same sample as in Pattern 1, data on the flexural modulus was prepared. Input 1 of Pattern 2 included the same resin type, proportion, and additive type and proportion as in Pattern 1, plus the flexural modulus measured in advance. An analytical model was constructed to predict the load deflection temperature using 80 data points. The load deflection temperature, output 2, was predicted using the 20 unused data points. Input 1 of Pattern 3 is the input information for the analysis model for the first prediction. Using the same data as in Pattern 2, an analysis model for the first prediction was constructed to predict the flexural modulus. Output 1 of Pattern 3 is the flexural modulus, which is the output information of the analysis model for the first prediction. Input 2 of Pattern 3 is the input information for the analysis model for the second prediction. Using the type and proportion of resin, the type and amount of additives, and the flexural modulus predicted by the analysis model for the first prediction as input 2, an analysis model for the second prediction was constructed to predict the load deflection temperature. The load deflection temperature, which is output 3, was predicted using 20 unused data points. Output 3 of Pattern 3 is the output information of the analysis model for the second prediction. Pattern 4 was performed similarly to Pattern 3, but with the manufacturing condition information added to the input information. Pattern 5 was performed similarly to Pattern 4, by adding infrared absorption spectrum information of the material as information obtained by irradiating it with electromagnetic waves. [Table 2] As shown in Table II, Pattern 2 shows improved prediction accuracy compared to Pattern 1, the conventional method. Furthermore, improved prediction accuracy can also be observed in Pattern 3, which uses predicted values ​​without using measured values ​​for the elastic modulus. It can also be confirmed that prediction accuracy can be further improved by using information on manufacturing conditions and electromagnetic waves.

[0029] <Effects> As described above, the deformation temperature prediction method includes a first prediction step (step S3) in which the deformation temperature is predicted from the formulation information and elastic modulus of the resin material, in the deformation temperature prediction method (deformation temperature prediction process) using a deformation temperature prediction device. Therefore, the accuracy of qualitative deformation temperature prediction improves.

[0030] Furthermore, the deformation temperature prediction method includes a second prediction step (step S2) in which the flexural modulus is predicted from the formulation information of the resin material. Therefore, a predicted value can be used for the modulus of elasticity.

[0031] Furthermore, in the deformation temperature prediction method, the second prediction step (step S2) may further predict the flexural modulus using the manufacturing conditions of the resin material, and the first prediction step (step S3) may further predict the deformation temperature using the manufacturing conditions of the resin material. Therefore, the accuracy of qualitative deformation temperature prediction is further improved.

[0032] Furthermore, the deformation temperature prediction device 1 includes a prediction unit (control unit 11) that predicts the deformation temperature from the formulation information and elastic modulus of the resin material. Therefore, the accuracy of qualitative deformation temperature prediction improves.

[0033] Furthermore, the program causes the computer of the deformation temperature prediction device 1, which predicts the deformation temperature of the resin material, to function as a prediction unit (control unit 11) that predicts the deformation temperature from the formulation information and elastic modulus of the resin material. Therefore, the accuracy of qualitative deformation temperature prediction improves.

[0034] Although the present invention has been described in detail based on embodiments above, it goes without saying that the present invention is not limited to the above embodiments and can be modified as appropriate without departing from the spirit of the invention. For example, the above description disclosed an example in which a hard disk or semiconductor non-volatile memory was used as a computer-readable medium for the program according to the present invention, but the invention is not limited to this example. Portable recording media such as CD-ROMs can be used as other computer-readable media.

[0035] Furthermore, the detailed configuration and operation of each device can be modified as appropriate, without departing from the spirit of the invention. [Explanation of Symbols]

[0036] 1. Deformation temperature prediction device 11 Control Unit (First Prediction Unit (Prediction Unit), Second Prediction Unit) 12 Control section 13 Communications Department 14 Storage section 15. Representation Section

Claims

1. In a deformation temperature prediction method using a deformation temperature prediction device, A deformation temperature prediction method comprising a first prediction step of predicting the deformation temperature from the formulation information and elastic modulus of a resin material.

2. The deformation temperature prediction method according to claim 1, wherein the modulus of elasticity is the bending modulus.

3. The deformation temperature prediction method according to claim 1, wherein the deformation temperature is the load deflection temperature.

4. The deformation temperature prediction method according to claim 2, comprising a second prediction step of predicting the flexural modulus from the formulation information of the resin material.

5. The second prediction step further predicts the flexural modulus using the manufacturing conditions of the resin material, The deformation temperature prediction method according to claim 4, wherein the first prediction step further predicts the deformation temperature using the manufacturing conditions of the resin material in combination.

6. The deformation temperature prediction method according to claim 1, wherein the formulation information is the type and proportion of resin used and the type and proportion of additives.

7. The deformation temperature prediction method according to claim 1, wherein the formulation information includes information obtained by irradiating a resin with electromagnetic waves and detecting the electromagnetic waves generated from the resin.

8. The deformation temperature prediction method according to claim 1, wherein the formulation information is information obtained from the thermal properties of the resin.

9. The deformation temperature prediction method according to claim 5, wherein the manufacturing conditions are kneading conditions.

10. The deformation temperature prediction method according to claim 5, wherein the manufacturing conditions are the sorting, washing, drying, and mixing conditions of the recycled material.

11. The deformation temperature prediction method according to claim 1, wherein a part or all of the resin material is recycled material.

12. The deformation temperature prediction method according to claim 1, wherein the resin material includes polycarbonate or a styrene-based resin.

13. A deformation temperature prediction device equipped with a prediction unit that predicts the deformation temperature from the formulation information and elastic modulus of the resin material.

14. A computer for a deformation temperature prediction device that predicts the deformation temperature of resin materials, A prediction unit that predicts the deformation temperature from the formulation information and elastic modulus of the resin material. A program that makes it function as such.

Images