Flame retardancy evaluation and prediction method, flame retardancy evaluation and prediction device, and program

Abstract

The goal is to improve the predictive accuracy of qualitative flame retardancy assessments. [Solution] A method for predicting the UL94V rank of a resin composite material using a flame retardancy evaluation and prediction device, comprising: a first prediction step (step S2) of predicting alternative properties from input formulation information and / or thermal property information; and a second prediction step (step S3) of predicting the UL94V rank from the alternative properties.

Description

Technical Field

[0006] , , ,

[0004] ,

[0005] , , , , , , ,

[0001] The present invention relates to a flame retardancy evaluation prediction method, a flame retardancy evaluation prediction device, and a program.

Background Art

[0002] Conventionally, flame retardancy is one of the important indicators for showing the specifications of resin composite materials. Flame retardancy is ranked in accordance with the standard of UL (Underwriters Laboratories Inc.) 94. UL94 is an evaluation method that includes a plurality of information such as the combustion time immediately after contacting the flame and the presence or absence of dripping substances. Therefore, the flame retardancy evaluation using UL94 is qualitative.

[0003] On the other hand, 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. Among them, Patent Document 1 describes a learning generation program that uses formulation conditions (mixing ratios of raw materials) as explanatory variables and physical property values (UL94 rank) as target variables.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] As described above, since the flame retardancy evaluation using UL94 is a qualitative evaluation including a plurality of information, it has been difficult to apply machine learning. Therefore, the prediction accuracy of the UL94 rank was low.

[0006] Therefore, the object of the present invention is to improve the predictive accuracy of qualitative flame retardancy evaluation. [Means for solving the problem]

[0007] To solve the aforementioned problems, the flame retardancy evaluation and prediction method according to the present invention is: A method for predicting the UL94V rank of a resin composite material using a flame retardancy evaluation and prediction device, A first prediction step predicts alternative properties from the input prescription information and / or thermal property information, A second prediction step predicts the UL94V rank from the aforementioned alternative characteristics, It has.

[0008] Furthermore, the flame retardancy evaluation and prediction device according to the present invention is A flame retardancy evaluation and prediction device for predicting the UL94V rank in resin composite materials, A first prediction unit predicts alternative characteristics from input prescription information and / or thermal characteristic information, A second prediction unit predicts the UL94V rank from the aforementioned alternative characteristics, It has.

[0009] Furthermore, the program according to the present invention is A computer for a flame retardancy evaluation and prediction device that predicts the UL94V rank in resin composite materials. A first prediction unit predicts alternative characteristics from the input prescription information and / or thermal characteristic information. A second prediction unit predicts the UL94V rank from the aforementioned alternative characteristics. To make it function as such. [Effects of the Invention]

[0010] According to the present invention, the predictive accuracy of qualitative flame retardancy evaluation is improved. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the configuration of a flame retardancy evaluation and prediction device. [Figure 2]It is a flowchart of a flame retardancy evaluation prediction process.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the scope of the present invention is not limited to those described in the following embodiments and drawings.

[0013] <Flame Retardancy Evaluation Prediction Device 1> First, the configuration of the flame retardancy evaluation prediction device 1 will be described using FIG. 1. The flame retardancy evaluation prediction device 1 is an information processing device that predicts the UL94V rank in a resin composite material. Specifically, the flame retardancy evaluation prediction device 1 is an information processing device that predicts the UL94V rank in two steps: predicting alternative characteristics from the formulation information and / or thermal characteristic information of the resin composite material, and predicting the UL94V rank from the alternative characteristics. The formulation information, thermal characteristic information, and alternative characteristics will be described later. The resin composite material is a resin composite material containing polycarbonate resin or the like.

[0014] Next, the configuration of the flame retardancy evaluation prediction device 1 will be described using FIG. 1. As shown in FIG. 1, the flame retardancy evaluation 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.

[0015] The control unit 11 is composed of a CPU (Central Processing Unit), a RAM (Random Access Memory), etc. The CPU of the control unit 11 reads out various programs stored in the storage unit 14 and expands them in the RAM, executes various processes according to the expanded programs, and controls the operations of each part of the flame retardancy evaluation prediction device 1.

[0016] The control unit 11 functions as a first prediction unit that predicts alternative characteristics (first prediction) from the input formulation information and / or thermal characteristic information. The control unit 11 functions as a second prediction unit that predicts the UL94V rank from the alternative properties predicted by the first prediction unit (second prediction). The formulation information includes at least one of the blending ratio of raw materials and the manufacturing conditions of the composite material. The thermal property information includes at least one selected from the glass transition temperature, melting point, softening point, softening rate, solidification point, weight loss start temperature, decomposition start temperature, decomposition rate, decomposition end temperature, weight loss end temperature, residual ratio at each temperature, and char yield. The alternative properties include at least one selected from the limiting oxygen index, melt viscosity, fluidity, and combustion rate.

[0017] The first prediction and the second prediction are executed using an analysis model such as a machine learning model. The analysis model for the first prediction is assumed to be learned such that when the formulation information and / or the thermal property information is input as input information, the alternative properties are output as output information. Here, the melt viscosity and fluidity in the alternative properties can be measured from the pellets of the resin composite material. Also, the limiting oxygen index and combustion rate in the alternative properties can be measured from the molded body of the resin composite material. The analysis model for the second prediction is assumed to be learned such that when the alternative properties are input as input information, the UL94V rank is output as output information. Note that it is not limited to the case where only the alternative properties are input as input information, and the formulation information and / or the thermal property information may be input in addition to the alternative properties.

[0018] Here, the measurement methods of various information in the pre-learning when predicting the flammability (conforming to UL94V) using the alternative properties will be described. (1) Flammability evaluation After drying the polycarbonate resin composite material at 120°C for 4 hours, a strip-shaped test piece is molded, and a combustion test is carried out in accordance with the "UL94 Combustion Test Evaluation Method" to obtain the UL94V rank. (2) Alternative properties These are characteristic values ​​obtained by methods such as the critical oxygen index (compliant with ISO 4589-2), the melt flow rate method (compliant with ISO 1133), or the spiral flow method, and there is at least one of the above. (3) Thermal characteristics These are characteristic values ​​obtained by methods such as simultaneous thermogravimetric and differential thermal analysis (TG-DTA), differential scanning calorimetry (DSC), and dynamic viscoelasticity analysis.

[0019] The control unit 11 functions as a first generation unit that generates second prescription information (first generation) based on the UL94V rank predicted by the analysis model for second prediction. The control unit 11 functions as a second generation unit that generates second thermal characteristic information (second generation) based on the UL94V rank predicted by the second prediction analysis model.

[0020] The first and second generation processes are performed using analytical models such as machine learning models. The first generation analysis model is assumed to be trained to output prescription information when prescription information and UL94V rank are input. The input prescription information is the possible (designable) prescription information. The output prescription information is the prescription information that satisfies the UL94V rank required by the user. The analysis model for the second generation is assumed to be trained to output thermal property information when UL94V rank is input. The output thermal property information is the thermal property information that satisfies the UL94V rank required by the user.

[0021] The operation unit 12 includes a keyboard equipped with cursor keys, number input keys, various function keys, a pointing device such as a mouse, and a touch panel laminated on the surface of the display unit 15. The operation unit 12 is configured to be operable by the operator. The operation unit 12 also outputs various signals to the control unit 11 based on the operations performed by the operator.

[0022] The communication unit 13 is capable of sending and receiving various signals and data with other devices connected via a communication network.

[0023] 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 prediction, second prediction, first generation, and second prediction described above.

[0024] 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.

[0025] <Flame retardancy evaluation and prediction processing> Next, using Figure 2, we will explain the flame retardancy evaluation prediction process performed in the flame retardancy evaluation prediction device 1 to predict the UL94V rank of resin composite materials.

[0026] First, the control unit 11 acquires formulation information and / or thermal property information (step S1). For example, the control unit 11 may acquire prescription information and / or thermal property information from the operation unit 12, which is operated by the user. Alternatively, the control unit 11 may acquire thermal property information from a measuring device that measures thermal property information via the communication unit 13.

[0027] Next, the control unit 11 inputs the formulation information and / or thermal property information acquired in step S1 into the analysis model for first prediction and predicts alternative properties (step S2; first prediction step).

[0028] Next, the control unit 11 inputs the alternative characteristics predicted in step S2 into the analysis model for the second prediction and predicts the UL94V rank (step S3; second prediction step).

[0029] Next, the control unit 11 outputs the UL94V rank predicted in step S3 (step S4). For example, the control unit 11 outputs the UL94V rank to the display unit 15, allowing the user to confirm the predicted UL94V rank.

[0030] In this way, predicting the UL94V rank in two stages (step S3 and step S4) improves the accuracy of qualitative flame retardancy assessment, as will be explained later.

[0031] <Examples> [Table 1] The improvement in the prediction accuracy of flame retardancy assessment is explained using the patterns shown in Table I. In all patterns, the accuracy rate calculated from the predicted data was used to evaluate the model. Pattern 1 is a conventional prediction method, where the UL94V rank is predicted directly from the formulation information. Input 1 of Pattern 1 is the input information of the conventional analysis model, which is formulation information with varying resin types and mixing ratios, and additive types and mixing ratios. The UL94V rank of each sample was evaluated, and a classification system was created to predict the UL94V rank. Output 1 of Pattern 1 is the output information of the conventional analysis model. Output 1, which is UL94V, was predicted using data not used to create the classification system. Pattern 2 is the prediction method described above. Using the sample from Pattern 1, measurements of alternative characteristics were also prepared. Alternative characteristics are characteristic values ​​obtained by methods such as the critical oxygen index (compliant with ISO 4589-2), the melt flow rate method (compliant with ISO 1133), and the spiral flow method, and represent at least one measurement from the above. Input 1 of Pattern 2 is the prescription information, and Output 1 is the alternative characteristic described above. Input 2 of Pattern 2 is the alternative characteristic which is Output 1 of Pattern 2, and Output 2 is the UL94V rank. In Pattern 3, thermal property measurements were also prepared using the sample from Pattern 1. Thermal property refers to characteristic values ​​obtained by methods such as simultaneous thermogravimetric and differential thermal analysis (TG-DTA), differential scanning calorimetry (DSC), and dynamic viscoelasticity analysis. Input 1 in Pattern 3 is the thermal property, and Output 1 is the surrogate property. Input 2 in Pattern 3 is the surrogate property which is Output 1 in Pattern 3, and Output 2 is the UL94V rank. In Pattern 4, Input 1 is formulation information and thermal properties, and Output 1 is alternative properties. In Pattern 4, Input 2 is the alternative property that is Output 1 of Pattern 4, and Output 2 is the UL94V rank. Input 1 and Output 1 of Pattern 5 are the same as in Pattern 2. Input 2 of Pattern 5 is prescription information and the alternative characteristic which is Output 1 of Pattern 5, and Output 2 is the UL94V rank. Input 1 and Output 1 of Pattern 6 are the same as in Pattern 3. Input 2 of Pattern 6 is prescription information and the alternative characteristic which is Output 1 of Pattern 6, and Output 2 is the UL94V rank. Input 1 and Output 1 of Pattern 7 are the same as in Pattern 4. Input 2 of Pattern 7 is formulation information and thermal characteristics, and Output 1 of Pattern 7 is alternative characteristics, with Output 2 being UL94V. [Table 2] As shown in Table II, patterns 2, 3, and 4 demonstrate improved prediction accuracy compared to the conventional prediction method, pattern 1. Furthermore, patterns 6 and 7 show even greater improvements in prediction accuracy.

[0032] <Other> After the flame retardancy evaluation prediction process described above, the control unit 11 may execute the first generation step (described above) and output the formulation information to the display unit 15 or the like. This makes it easier for users to recreate formulation information for resin composite materials and create resin composite materials that meet the desired UL94V rating.

[0033] After the flame retardancy evaluation prediction process described above, the control unit 11 may execute the second generation step (described above) and output thermal characteristic information to the display unit 15 or the like. In this way, users can obtain thermal property information corresponding to their desired UL94V rank, making it easier to create resin composite materials that meet the desired UL94V rank.

[0034] <Effects> As described above, the flame retardancy evaluation prediction method (flame retardancy evaluation prediction process) is a method for predicting the UL94V rank of a resin composite material using a flame retardancy evaluation prediction device, and comprises a first prediction step (step S2) of predicting alternative properties from input formulation information and / or thermal property information, and a second prediction step (step S3) of predicting the UL94V rank from the alternative properties. Therefore, the accuracy of qualitative flame retardancy assessments is improved.

[0035] Furthermore, the flame retardancy evaluation and prediction device 1 is a flame retardancy evaluation and prediction device that predicts the UL94V rank of a resin composite material, and comprises a first prediction unit (control unit 11) that predicts alternative characteristics from input formulation information and / or thermal property information, and a second prediction unit (control unit 11) that predicts the UL94V rank from the alternative characteristics. Therefore, the accuracy of qualitative flame retardancy assessments is improved.

[0036] Furthermore, the program causes the computer of the flame retardancy evaluation prediction device 1, which predicts the UL94V rank of resin composite materials, to function as a first prediction unit (control unit 11) that predicts alternative characteristics from input formulation information and / or thermal property information, and a second prediction unit (control unit 11) that predicts the UL94V rank from the alternative characteristics. Therefore, the accuracy of qualitative flame retardancy assessments is improved.

[0037] 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.

[0038] 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]

[0039] 1. Flame retardancy evaluation and prediction device 11 Control Unit (First Prediction Unit, Second Prediction Unit, First Generation Unit, Second Generation Unit) 12 Control section 13 Communications Department 14 Storage section 15 Display section

Claims

1. A method for predicting the flame retardancy evaluation of resin composite materials using a flame retardancy evaluation prediction device, A first prediction step predicts alternative properties from the input prescription information and / or thermal property information, A second prediction step in which the UL94V rank is predicted from the aforementioned alternative characteristics, A flame retardancy evaluation and prediction method having the following characteristics.

2. The flame retardancy evaluation and prediction method according to claim 1, wherein the resin composite material includes polycarbonate resin.

3. The flame retardancy evaluation and prediction method according to claim 1, wherein the formulation information includes at least one of the following: the mixing ratio of raw materials and the manufacturing conditions of the composite material.

4. The flame retardancy evaluation and prediction method according to claim 1, wherein the thermal property information includes at least one selected from glass transition temperature, melting point, softening point, softening rate, solidification point, weight loss initiation temperature, decomposition initiation temperature, decomposition rate, decomposition termination temperature, weight loss termination temperature, residual rate at each temperature, and carbonization rate.

5. The flame retardancy evaluation and prediction method according to claim 1, wherein the alternative characteristic comprises at least one selected from critical oxygen index, melt viscosity, fluidity, and combustion rate.

6. Based on the UL94V rank predicted in the second prediction step, a first generation step is performed to generate second prescription information. The flame retardancy evaluation and prediction method according to claim 1, further comprising the above.

7. A second generation step in which second thermal characteristic information is generated based on the UL94V rank predicted in the second prediction step, The flame retardancy evaluation and prediction method according to claim 1, further comprising the above.

8. A flame retardancy evaluation and prediction device for predicting the UL94V rank in resin composite materials, A first prediction unit predicts alternative characteristics from input prescription information and / or thermal characteristic information, A second prediction unit predicts the UL94V rank from the aforementioned alternative characteristics, A flame retardancy evaluation and prediction device having the following features.

9. A computer for a flame retardancy evaluation and prediction device that predicts the UL94V rank in resin composite materials, A first prediction unit predicts alternative characteristics from the input prescription information and / or thermal characteristic information. A second prediction unit predicts the UL94V rank from the aforementioned alternative characteristics. A program that makes it function as such.

Images