JP-7854655-B2 - Quantitative evaluation device, quantitative evaluation program, and learning model generation program

JP7854655B2JP 7854655 B2JP7854655 B2JP 7854655B2JP-7854655-B2

Inventors

小川耕平
堤親平
上杉徳照
中島智晴

Assignees

株式会社栗本鐵工所
公立大学法人大阪

Dates

Publication Date: 20260507
Application Date: 20220913
Priority Date: 20210916

Claims (10)

A quantitative evaluation device used for inspecting the quality of the casting surface of cast iron pipes, A memory means for storing a learning model generated by machine learning using image data of multiple casting surfaces that have been pre-classified into multiple stages as training data, An image acquisition means for acquiring image data of the casting surface of a cast iron pipe to be inspected, A quantitative evaluation device comprising: an image acquisition means that inputs image data acquired by the image acquisition means into the learning model, and an evaluation determination means that evaluates and determines a level or numerical value based on the output from the model as the degree of appearance of the casting surface of the cast iron pipe to be inspected.
The quantitative evaluation apparatus according to claim 1, wherein the evaluation determination means evaluates and determines the degree of appearance of the casting surface by selecting a level greater than the number of classes in the training data, or a numerical value within a continuous, stepless range.
The quantitative evaluation apparatus according to claim 1, wherein the training data of the learning model includes, as augmented data, trimmed image data obtained by removing the edges of the original image data of the casting surface.
The cast iron pipes subject to inspection were manufactured by the die centrifugal casting method. The quantitative evaluation apparatus according to claim 1, wherein the training data of the learning model includes, as augmented data, rotated image data obtained by rotating the original image data of the casting surface within an angular range of less than 5°.
A quantitative evaluation device used for inspecting the quality of the casting surface of cast iron pipes, A storage means for storing a learning model generated by machine learning using image data that has been preprocessed, including adaptive histogram equalization and blurring by bilateral filtering, on image data of multiple casting surfaces that have been pre-classified into multiple stages, as training data, and An image acquisition means for acquiring image data of the casting surface of a cast iron pipe to be inspected, An adjustment means that performs input image adjustment processing, including the preprocessing, on the image data acquired by the image acquisition means, A quantitative evaluation device comprising: an evaluation determination means that inputs image data subjected to the input image adjustment process into the learning model, and evaluates and determines a level or numerical value based on the output from the learning model as the degree of appearance of the casting surface of the cast iron pipe to be inspected.
The training data of the learning model includes augmented data that has been randomly rotated, flipped, scaled, and translated. The quantitative evaluation apparatus according to claim 5, wherein the input image adjustment process includes data augmentation processing that randomly performs rotation, inversion, scaling, and movement.
A quantitative evaluation device used for inspecting the quality of the casting surface of cast iron pipes, A storage means for storing regression models and defective product classification models generated by machine learning using image data of multiple casting surfaces that have been pre-classified into multiple stages, as training data, An image acquisition means for acquiring image data of the casting surface of a cast iron pipe to be inspected, A quantitative evaluation device comprising: an image acquisition means that inputs image data acquired by the image acquisition means into the regression model and the defective product classification model; and an evaluation determination means that evaluates and determines a weighted average of the output values from the regression model and the output values from the defective product classification model as the degree of appearance of the casting surface of the cast iron pipe to be inspected.
A quantitative evaluation program used for inspecting the quality of the casting surface of cast iron pipes, The process involves reading a learning model, generated by machine learning using image data of multiple casting surfaces that have been pre-classified into multiple stages, from the memory unit, and The steps include: acquiring image data of the casting surface of the cast iron pipe to be inspected, A quantitative evaluation program that causes a computer to perform the steps of inputting acquired image data into the learning model, and evaluating and determining a level or numerical value based on the output from the learning model as the degree of appearance of the casting surface of the cast iron pipe to be inspected.
A learning model generation program for generating a learning model for inspecting the quality of the casting surface of cast iron pipes, The process involves inputting raw image data of multiple casting surfaces that have been pre-classified into multiple stages, and The steps include generating extended data based on the input original image data, A learning model generation program that causes a computer to perform a step of machine learning for each class, using at least a portion of the image data of multiple casting surfaces, including the original image data and the extended data, as training data.
A learning model generation program for generating a learning model for inspecting the quality of the casting surface of cast iron pipes, The process involves inputting raw image data of multiple casting surfaces that have been pre-classified into multiple stages, and The process involves generating training data by preprocessing the input original image data, including adaptive histogram equalization and blurring using a bilateral filter. A learning model generation program that has a computer perform the steps of machine learning on the generated training data for each class.

Description

Applicable to Article 30, Paragraph 2 of the Patent Law. Published at the Knowledge Information Systems Seminar IV Poster Presentation (Zoom (breakout rooms)) held on January 26, 2021, at the Uesugi Laboratory, Department of Knowledge Information Systems, Faculty of Modern System Science, Osaka Prefecture University. This invention relates to a quantitative evaluation device, a quantitative evaluation program, and a learning model generation program used for inspecting the quality of the casting surface of cast iron pipes. More particularly, it relates to a quantitative evaluation device and program that quantitatively evaluates the appearance of the casting surface using a learning model, and to a learning model generation program that generates a learning model. One method for manufacturing cast iron pipes is die centrifugal casting. As shown in, for example, Japanese Patent Publication No. 2002-153962 (Patent Document 1), die centrifugal casting is a method of manufacturing pipes (cast iron pipes) by supplying molten metal to the inside of a cylindrical mold while rotating it around a horizontal axis, thereby applying centrifugal force to the molten metal. Unlike air-cooled sand mold centrifugal casting, this die centrifugal casting method uses water cooling for the mold (cylindrical mold). In casting methods such as die centrifugal casting, pinholes (including blowholes) may occur in the cast iron pipes. If a large number of pinholes occur, it will be treated as a cosmetic defect; therefore, a pinhole inspection of the casting surface is performed before shipment. From the perspective of inspecting defects on object surfaces, techniques have been conventionally proposed that involve generating a learning model by machine learning a large number of sample images, and then using that learning model to automatically determine defects on object surfaces, as disclosed in, for example, Japanese Patent Publication No. 2018-205123 (Patent Document 2), Japanese Patent Publication No. 2019-2788 (Patent Document 3), and WO2020/137151 (Patent Document 4). Japanese Patent Publication No. 2002-153962Japanese Patent Publication No. 2018-205123Japanese Patent Publication No. 2019-2788WO2020/137151 publication This figure schematically shows an overview of the quantitative evaluation system 1 in each embodiment of the present invention.This figure schematically illustrates the method for evaluating the appearance of the casting surface in each embodiment of the present invention.(A) is a functional block diagram showing the functional configuration of the learning device in each embodiment of the present invention, and (B) is a functional block diagram showing the functional configuration of the quantitative evaluation device in each embodiment of the present invention.This is a flowchart showing the method for generating a learning model in Embodiment 1 of the present invention.This is a schematic diagram illustrating step S1 in Figure 4.This flowchart shows a quantitative evaluation method for the appearance of the cast surface in each embodiment of the present invention.This is a flowchart showing the method for generating a learning model in Embodiment 2 of the present invention.(A) and (B) are diagrams showing the extended patterns of the original image data in Embodiment 2 of the present invention.Figures (A) to (C) show the evaluation results of the general-purpose performance of the learning models corresponding to the embodiments of each example.This figure shows an overview of ensemble learning performed by the learning device according to Embodiment 3 of the present invention.(A) is a flowchart showing the input image tuning process in Embodiment 3 of the present invention, and (B) is a graph showing the relationship between the type of preprocessing and the error.(A) and (B) are graphs showing the results of verifying the weights of defective product classes in the classification model.(A) and (B) are graphs showing the results of verifying the weights in ensemble learning.This graph shows the evaluation results of the ensemble learning model in Embodiment 3 of the present invention.The results of verifying whether or not data augmentation occurred during training and inference in Embodiment 3 of the present invention are shown.This is a diagram illustrating a ductile cast iron pipe manufactured by the die centrifugal casting method. Embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, identical or corresponding parts are denoted by the same reference numerals, and their descriptions will not be repeated. <Embodiment 1> (About the overview) First, an overview of the quantitative evaluation system 1 in this embodiment will be described with reference to Figures 1 and 2. Figure 1 is a schematic diagram showing an overview of the quantitative evaluation system 1, and Figure 2 is a schematic diagram showing a method for evaluating the appearance of the