WO2022269342A1 - 塗装評価装置及び塗装評価方法 - Google Patents
塗装評価装置及び塗装評価方法 Download PDFInfo
- Publication number
- WO2022269342A1 WO2022269342A1 PCT/IB2022/000312 IB2022000312W WO2022269342A1 WO 2022269342 A1 WO2022269342 A1 WO 2022269342A1 IB 2022000312 W IB2022000312 W IB 2022000312W WO 2022269342 A1 WO2022269342 A1 WO 2022269342A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- evaluation
- surface roughness
- coating
- painted
- Prior art date
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 202
- 239000011248 coating agent Substances 0.000 title claims abstract description 119
- 238000000576 coating method Methods 0.000 title claims abstract description 119
- 230000003746 surface roughness Effects 0.000 claims abstract description 153
- 239000000463 material Substances 0.000 claims abstract description 130
- 238000013210 evaluation model Methods 0.000 claims abstract description 88
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims description 27
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000013461 design Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 238000010422 painting Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000010365 information processing Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/8422—Investigating thin films, e.g. matrix isolation method
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
- G01B11/303—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces using photoelectric detection means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/8422—Investigating thin films, e.g. matrix isolation method
- G01N2021/8427—Coatings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Definitions
- the present invention relates to a coating evaluation device and a coating evaluation method.
- the present invention has been made in view of the above problems, and its object is to provide a coating evaluation device and a coating evaluation method that can accurately evaluate the sharpness of a painted surface.
- a coating evaluation apparatus and a coating evaluation method store material information representing the material of a coated surface, shape information representing the curved shape of the coated surface, or surface roughness information representing the surface roughness of the coated surface. get. Then, using an evaluation model that outputs an evaluation value for the sharpness of the painted surface in response to input including material information, shape information, and surface roughness information, we can handle combinations of material information, shape information, and surface roughness information. Estimate the evaluation value to be used.
- FIG. 1 is a block diagram showing the configuration of a coating evaluation device according to one embodiment of the present invention.
- FIG. 2 is a flow chart showing processing of the coating evaluation device according to one embodiment of the present invention.
- the coating evaluation apparatus includes a shape obtaining section 11 , a surface roughness obtaining section 17 and a controller 100 .
- the coating evaluation device may include the material acquisition unit 13 , the image acquisition unit 21 and the output unit 400 .
- the shape acquisition unit 11 , the material acquisition unit 13 , the surface roughness acquisition unit 17 , the image acquisition unit 21 and the output unit 400 are connected to the controller 100 .
- the shape acquisition unit 11 acquires shape information representing the curved shape of the painted surface to be evaluated for coating. More specifically, the shape acquisition unit 11 may acquire design data relating to the shape of the painted surface as shape information.
- design data includes CAD (Computer-aided design) data.
- the design data is not limited to this as long as it represents the degree of curvature (curvature) of the coated surface and the degree of inclination of the coated surface with respect to a surface roughness acquisition unit described later.
- the shape acquisition unit 11 may acquire the stored design data of the painted surface from a database (not shown), or may acquire the design data of the painted surface from an external connection device (not shown) via a wired/wireless network. may be acquired. In addition, the shape acquisition unit 11 may acquire design data based on user input.
- the shape acquisition unit 11 may acquire measurement data obtained by measuring the coated surface as shape information.
- various devices such as a 3D scanner can be used.
- the material acquisition unit 13 acquires material information representing the material of the painted surface. More specifically, the material acquisition unit 13 obtains, as the material information of the coated surface, the type of material that constitutes the coated surface, the film thickness (coating thickness) of each layer that constitutes the coated surface, the optical characteristics (material reflectance, Acquire design data such as material transmittance, material refractive index), brightness, saturation, and hue. In addition, the material acquisition unit 13 may acquire information such as the amount, shape, and orientation of the luster material contained in the coating as the material information of the coated surface.
- the material acquisition unit 13 may acquire the stored material information of the painted surface from a database (not shown), or may acquire the material information of the painted surface from an external connection device (not shown) via a wired/wireless network. may be acquired. Alternatively, the material acquisition unit 13 may acquire material information based on user input.
- the material acquisition unit 13 acquires measurement data such as film thickness, optical characteristics, brightness, chroma, and hue for each layer constituting the coated surface obtained by measuring the coated surface as material information.
- the material acquisition unit 13 includes various devices such as a film thickness meter, a spectrophotometer, a color difference meter, a reflectance meter, and a refractive index meter.
- the surface roughness acquisition unit 17 acquires surface roughness information representing the surface roughness of the coated surface. More specifically, the surface roughness acquisition unit 17 may acquire the surface roughness obtained by measuring the coated surface as the surface roughness information.
- the surface roughness acquisition unit 17 may be a laser microscope.
- the surface roughness acquisition unit 17 may acquire surface roughness information of the painted surface stored from a database (not shown), or may acquire surface roughness information from an externally connected device (not shown) via a wired or wireless network. It is also possible to acquire the surface roughness information of the coated surface.
- the shape acquisition unit 11 may acquire surface roughness information based on user input.
- the image acquisition unit 21 acquires a captured image of the painted surface to be evaluated for painting. More specifically, the image acquisition unit 21 is a digital camera equipped with a solid-state imaging device such as CCD or CMOS, and acquires a digital image by imaging the coated surface.
- a solid-state imaging device such as CCD or CMOS
- the image acquisition unit 21 captures an image of the painted surface to be evaluated for painting by setting the focal length, the angle of view of the lens, the vertical and horizontal angles of the camera, and the like.
- the controller 100 is a general-purpose computer equipped with a CPU (Central Processing Unit), memory, storage device, input/output unit, and the like.
- CPU Central Processing Unit
- a computer program (painting evaluation program) is installed in the controller 100 to function as a paint evaluation device.
- the controller 100 functions as a plurality of information processing circuits provided in the coating evaluation apparatus.
- a plurality of information processing circuits provided in the coating evaluation apparatus by software is shown. It is also possible to configure Also, a plurality of information processing circuits may be configured by individual hardware.
- the controller 100 includes an evaluation model setting section 120 , an evaluation value estimation section 130 and a position specifying section 140 .
- the evaluation model setting unit 120 sets an evaluation model that outputs an evaluation value of the sharpness of the painted surface.
- the evaluation value of sharpness is determined by, for example, at least one of the smoothness of the painted surface, the ratio of diffuse reflection to the reflected light on the painted surface, and the resolution of the image reflected on the painted surface. is an indicator.
- the evaluation value of sharpness of the evaluated painted surface is a numerical value previously given to the evaluated painted surface by another sharpness evaluation method.
- the evaluation model setting unit 120 may set an evaluation model that outputs an evaluation value of the sharpness of the painted surface in response to input including shape information and surface roughness information.
- the evaluation model is generated by machine learning based on teacher data consisting of a set of shape information of the evaluated painted surface, surface roughness information of the evaluated painted surface, and evaluation value of clarity of the evaluated painted surface. Learning model.
- the evaluation model setting unit 120 may set an evaluation model that outputs an evaluation value of the sharpness of a painted surface in response to inputs including surface roughness information and material information.
- the evaluation model is generated by machine learning based on teacher data consisting of a set of surface roughness information of the evaluated painted surface, material information of the evaluated painted surface, and an evaluation value of clarity of the evaluated painted surface. Learning model.
- the evaluation model setting unit 120 may set an evaluation model that outputs an evaluation value for the sharpness of the painted surface in response to input including material information and shape information.
- the evaluation model is a learning model generated by machine learning based on training data consisting of the material information of the evaluated painted surface, the shape information of the evaluated painted surface, and the evaluation value of the clarity of the evaluated painted surface. is.
- the evaluation model setting unit 120 may set an evaluation model that outputs an evaluation value of the sharpness of the painted surface in response to inputs including material information, shape information, and surface roughness information.
- the evaluation model is teacher data consisting of a set of material information of the evaluated painted surface, shape information of the evaluated painted surface, surface roughness information of the evaluated painted surface, and an evaluation value of clarity of the evaluated painted surface.
- Techniques for generating learning models by machine learning include, for example, neural networks, support vector machines, Random Forest, XGBoost, LightGBM, PLS regression, Ridge regression, and Lasso regression. is mentioned.
- a method of generating a learning model by machine learning is not limited to the examples given here.
- the evaluation model setting unit 120 may set an evaluation model by performing machine learning based on teacher data acquired from a database (not shown).
- the evaluation model may be stored in advance in a database (not shown), and the evaluation model setting unit 120 may set the evaluation model acquired from the database.
- the evaluation model may be configured by a neural network including an input layer and an output layer. More specifically, a neural network typically has an input layer, multiple hidden layers, and an output layer, each layer (input layer, hidden layer, output layer) containing multiple neurons. .
- the input layer includes shape information representing the curved shape of the painted surface and surface roughness information representing the surface roughness of the painted surface as input data processed via each hidden layer. Also, the neurons in the output layer are assigned the sharpness evaluation values of the painted surface assigned to the input data by the neural network. That is, the output data output from the output layer is the evaluation value of the sharpness of the painted surface.
- the evaluation model setting unit 120 trains the neural network that constitutes the evaluation model to reproduce the given teacher data.
- the neural network calculates the shape information and the surface roughness. It is trained by machine learning so that when input data including degree information is input, an evaluation value of the sharpness of the painted surface is output as output data.
- the neural network When teacher data consisting of a set of surface roughness information of the evaluated painted surface, material information of the evaluated painted surface, and an evaluation value of sharpness of the evaluated painted surface is given, the neural network generates the surface roughness information and It is trained by machine learning so that when input data including material information is input, an evaluation value of the sharpness of the painted surface is output as output data.
- the neural network When teacher data consisting of a set of material information of the evaluated painted surface, shape information of the evaluated painted surface, and an evaluation value of clarity of the evaluated painted surface is given, the neural network includes the material information and the shape information. It is trained by machine learning so that when input data is input, an evaluation value of the sharpness of the painted surface is output as output data.
- the neural The network is trained by machine learning so that when input data including material information, shape information, and surface roughness information are input, the evaluation value of the sharpness of the painted surface is output as output data.
- an evaluation model is generated that performs machine learning based on teacher data and outputs an evaluation value for the sharpness of the painted surface in response to the input.
- the evaluation value estimation unit 130 uses the set evaluation model to estimate the evaluation value corresponding to the input.
- the set evaluation model was generated by machine learning based on teacher data consisting of a set of shape information of the evaluated painted surface, surface roughness information of the evaluated painted surface, and an evaluation value of the clarity of the evaluated painted surface.
- the evaluation value estimation unit 130 inputs shape information and surface roughness information to the evaluation model. Then, the evaluation value estimating section 130 sets the value output from the evaluation model as the evaluation value corresponding to the combination of the shape information and the surface roughness information.
- the evaluation value corresponding to the combination of the shape information and the surface roughness information is an estimated evaluation value regarding the sharpness of the painted surface.
- the set evaluation model was generated by machine learning based on teacher data consisting of a set of surface roughness information of the evaluated painted surface, material information of the evaluated painted surface, and evaluation value of clarity of the evaluated painted surface.
- the evaluation value estimation unit 130 inputs surface roughness information and material information to the evaluation model. Then, the evaluation value estimating section 130 sets the value output from the evaluation model as the evaluation value corresponding to the combination of the surface roughness information and the material information.
- the evaluation value corresponding to the combination of the surface roughness information and the material information is an estimated evaluation value regarding the sharpness of the painted surface.
- the set evaluation model is a learning model generated by machine learning based on teacher data consisting of a set of material information of the evaluated painted surface, shape information of the evaluated painted surface, and an evaluation value of the clarity of the evaluated painted surface.
- the evaluation value estimation unit 130 inputs material information and shape information to the evaluation model. Then, the evaluation value estimation unit 130 sets the value output from the evaluation model as the evaluation value corresponding to the combination of the material information and the shape information.
- the evaluation value corresponding to the combination of the material information and the shape information is an estimated evaluation value regarding the sharpness of the painted surface.
- the set evaluation model is teaching data in which the material information of the evaluated painted surface, the shape information of the evaluated painted surface, the surface roughness information of the evaluated painted surface, and the evaluation value of the clarity of the evaluated painted surface are combined. If the learning model is generated by machine learning based on the evaluation model, the evaluation value estimation unit 130 inputs shape information, surface roughness information, and material information to the evaluation model. Then, the evaluation value estimating section 130 sets the value output from the evaluation model as the evaluation value corresponding to the combination of the shape information, the surface roughness information, and the material information. An evaluation value corresponding to the combination of shape information, surface roughness information, and material information is an estimated evaluation value relating to sharpness of the painted surface.
- the position specifying unit 140 associates the captured image and the shape information with the surface roughness information, and records the position on the painted surface from which the surface roughness information was acquired. More specifically, the captured image and the shape information when the surface roughness information is obtained are linked to the surface roughness information and recorded in a database (not shown) or the like. Thereby, the position on the painted surface when the surface roughness information is acquired is specified.
- the position specifying unit 140 records the position on the painted surface where the surface roughness information and the material information are acquired in association with the captured image, so that the position on the painted surface when the surface roughness information and the material information are acquired. It may also specify a position.
- the output unit 400 outputs the estimated evaluation value regarding the sharpness of the painted surface.
- the surface roughness acquisition unit 17 acquires surface roughness information representing the surface roughness of the coated surface to be evaluated for coating.
- the shape acquisition unit 11 may acquire shape information representing the curved shape of the painted surface.
- the material acquisition unit 13 may acquire material information representing the material of the coated surface.
- the image acquisition unit 21 may acquire a captured image of the coated surface.
- step S104 the position specifying unit 140 acquires surface roughness information by associating the captured image and shape information with the surface roughness information and recording the position on the coating surface where the surface roughness information was acquired. Identify the actual position on the painted surface.
- the position specifying unit 140 records the position on the painted surface where the surface roughness information and the material information are acquired in association with the captured image, so that the painted surface when the surface roughness information and the material information are acquired. It may specify the upper position.
- step S111 the evaluation value estimation unit 130 estimates an evaluation value. More specifically, evaluation value estimation section 130 calculates an output from the evaluation model corresponding to the input to the evaluation model. Then, the value output from the evaluation model is estimated as the evaluation value corresponding to the input to the evaluation model.
- the evaluation model is a learning generated by machine learning based on teacher data consisting of a set of shape information of the evaluated painted surface, surface roughness information of the evaluated painted surface, and an evaluation value of the clarity of the evaluated painted surface.
- the evaluation value estimation unit 130 inputs a combination of shape information and surface roughness information to the evaluation model. Then, the evaluation value estimating section 130 estimates an evaluation value corresponding to the combination of the shape information and the surface roughness information.
- the evaluation model is a learning model generated by machine learning based on training data consisting of a set of shape information of the evaluated painted surface, material information of the evaluated painted surface, and an evaluation value of the clarity of the evaluated painted surface.
- the evaluation value estimation unit 130 inputs a combination of shape information and material information to the evaluation model. Then, the evaluation value estimating section 130 estimates an evaluation value corresponding to the combination of the shape information and the material information.
- the evaluation value estimation unit 130 inputs a combination of shape information, surface roughness information, and material information to the evaluation model.
- the evaluation value estimator 130 estimates an evaluation value corresponding to a combination of shape information, surface roughness information, and material information.
- step S113 the output unit 400 outputs the evaluation value estimated by the evaluation value estimation unit 130.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment include shape information representing the curved shape of the coated surface and surface roughness information representing the surface roughness of the coated surface. , and using an evaluation model that outputs an evaluation value for the sharpness of the painted surface in response to input including shape information and surface roughness information, an evaluation value corresponding to the combination of shape information and surface roughness information is calculated presume.
- the evaluation model includes the shape information of the evaluated painted surface, the surface roughness information of the evaluated painted surface, and the sharpness of the evaluated painted surface. It may be a learning model generated by machine learning based on teacher data having a set of evaluation values. As a result, it is possible to accurately evaluate the sharpness of the painted surface using the evaluation model generated from the teaching data on the evaluated painted surface having various curved surface shapes.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment may acquire the design data of the coated surface as shape information, or the measurement data obtained by measuring the coated surface. may be acquired as shape information. Accordingly, it is possible to accurately evaluate the sharpness of the painted surface in consideration of the curved shape of the painted surface.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment acquire the captured image of the coated surface, associate the captured image and shape information with the surface roughness information, and acquire the surface roughness information. It may also record the position on the painted surface. Thereby, the position on the painted surface when the surface roughness information is acquired is specified. In addition, it is possible to accurately evaluate the sharpness of the painted surface.
- the coating evaluation apparatus, the coating evaluation method, and the coating evaluation program according to the present embodiment acquire material information representing the material of the coating surface, An evaluation model for outputting an evaluation value of surface sharpness may be used to estimate an evaluation value corresponding to a combination of shape information, surface roughness information, and material information.
- An evaluation model for outputting an evaluation value of surface sharpness may be used to estimate an evaluation value corresponding to a combination of shape information, surface roughness information, and material information.
- the evaluation model includes material information of the evaluated painted surface, shape information of the evaluated painted surface, surface roughness information of the evaluated painted surface,
- the learning model may be a learning model generated by machine learning based on teacher data having a set of evaluation values of sharpness of the painted surface that has been evaluated. As a result, it is possible to accurately evaluate the sharpness of the painted surface by using the evaluation model generated from the teaching data on the evaluated painted surface composed of various curved surface shapes and various materials.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment acquire surface roughness information representing the surface roughness of the coated surface and material information representing the material of the coated surface. Using an evaluation model that outputs an evaluation value of sharpness of a painted surface in response to an input including information and material information, an evaluation value corresponding to a combination of surface roughness information and material information is estimated.
- the evaluation model includes surface roughness information of the evaluated painted surface, material information of the evaluated painted surface, and sharpness of the evaluated painted surface. It may be a learning model generated by machine learning based on teacher data having a set of evaluation values. As a result, it is possible to accurately evaluate the sharpness of the painted surface using the evaluation model generated from the teaching data on the evaluated painted surface having various surface roughness and material aspects.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment acquire design data relating to at least one of coating thickness, material reflectance, brightness, saturation, and hue of the coating surface as material information.
- the material of the coated surface can be considered in more detail, and the sharpness of the coated surface can be evaluated with high accuracy.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment are at least one of the coating thickness of the coated surface, the material reflectance, the brightness, the saturation, and the hue obtained by measuring the coated surface. may be acquired as the material information.
- the material of the coated surface can be considered in more detail, and the sharpness of the coated surface can be evaluated with high accuracy.
- the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment acquire the captured image of the coated surface, link it to the captured image, and acquire surface roughness information and material information on the coated surface It may also record the position. Thereby, the position on the painted surface when the surface roughness information and the material information are acquired is specified. In addition, it is possible to accurately evaluate the sharpness of the painted surface.
- the evaluation value of the sharpness of the painted surface is the smoothness of the painted surface, the ratio of diffuse reflection to the reflected light on the painted surface, It may be an index determined by at least one of resolution of an image reflected on a painted surface. In this way, criteria for evaluating sharpness of painted surfaces are specified.
- the evaluation model used in the coating evaluation device, coating evaluation method, and coating evaluation program according to the present embodiment may be configured by a neural network including an input layer and an output layer.
- a neural network including an input layer and an output layer.
- shape information representing the curved shape of the painted surface and surface roughness information representing the surface roughness of the painted surface, input data to be input to the input layer, and an evaluation value of the sharpness of the painted surface The evaluation model may be learned by associating the output data output from the output layer with each other.
- the evaluation model used in the coating evaluation device, the coating evaluation method, and the coating evaluation program according to the present embodiment includes shape information representing the curved shape of the coated surface, surface roughness information representing the surface roughness of the coated surface, and coating Acquire training data consisting of evaluation values for the clarity of the surface, perform machine learning based on the training data, and evaluate the clarity of the painted surface for input including shape information and surface roughness information. may be generated by configuring to output
- an evaluation model that expresses the relationship between the shape information and surface roughness information of the painted surface and the evaluation value of the sharpness of the painted surface.
- the evaluation model used in the coating evaluation device, coating evaluation method, and coating evaluation program according to the present embodiment may be configured by a neural network including an input layer and an output layer.
- a neural network including an input layer and an output layer.
- the evaluation model may be learned by associating the output data output from the layer with each other.
- the evaluation model used in the coating evaluation apparatus, coating evaluation method, and coating evaluation program according to the present embodiment is composed of surface roughness information representing the surface roughness of the coated surface, material information representing the material of the coated surface, Acquire teacher data that sets the evaluation value of the sharpness of the painted surface, perform machine learning based on the teacher data, and calculate the sharpness evaluation value of the painted surface for the input including surface roughness information and material information It may be generated by configuring to output.
- an evaluation model that expresses the relationship between the surface roughness information and material information of the painted surface and the evaluation value of the vividness of the painted surface.
- Processing circuitry includes programmed processors, electrical circuits, etc., as well as devices such as application specific integrated circuits (ASICs) and circuit components arranged to perform the described functions. etc. are also included.
- ASICs application specific integrated circuits
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Abstract
Description
図1を参照して、本実施形態に係る塗装評価装置の構成例を説明する。図1に示すように、塗装評価装置は、形状取得部11と、面粗度取得部17と、コントローラ100とを備える。その他、塗装評価装置は、材質取得部13と、画像取得部21と、出力部400とを備えるものであってもよい。形状取得部11、材質取得部13、面粗度取得部17、画像取得部21、出力部400は、コントローラ100と接続される。
次に、本実施形態に係る塗装評価装置の処理手順を、図2のフローチャートを参照して説明する。なお、図2のフローチャートで示される処理が開始される前に、評価モデル設定部120によって評価モデルが既に設定されているものとする。
以上詳細に説明したように、本実施形態に係る塗装評価装置、塗装評価方法、塗装評価プログラムは、塗装面の湾曲形状を表す形状情報、及び、塗装面の表面粗さを表す面粗度情報を取得し、形状情報及び面粗度情報を含む入力に対して塗装面の鮮映性の評価値を出力する評価モデルを用いて、形状情報及び面粗度情報の組合せに対応する評価値を推定する。
13 材質取得部
17 面粗度取得部
21 画像取得部
100 コントローラ
120 評価モデル設定部
130 評価値推定部
140 位置特定部
400 出力部
Claims (21)
- 塗装面の湾曲形状を表す形状情報を取得する形状取得部と、
前記塗装面の表面粗さを表す面粗度情報を取得する面粗度取得部と、
コントローラと、を備える塗装評価装置であって、
前記コントローラは、
前記形状情報及び前記面粗度情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記形状情報及び前記面粗度情報の組合せに対応する評価値を推定すること
を特徴とする塗装評価装置。 - 請求項1に記載の塗装評価装置であって、
前記評価モデルは、
評価済塗装面の形状情報、前記評価済塗装面の面粗度情報、前記評価済塗装面の鮮映性の評価値を組とする教師データに基づく機械学習によって生成された学習モデルであること
を特徴とする塗装評価装置。 - 請求項1に記載の塗装評価装置であって、
前記形状取得部は、前記塗装面の設計データを前記形状情報として取得すること
を特徴とする塗装評価装置。 - 請求項1に記載の塗装評価装置であって、
前記形状取得部は、前記塗装面を計測して得られた計測データを前記形状情報として取得すること
を特徴とする塗装評価装置。 - 請求項1に記載の塗装評価装置であって、
前記塗装面の撮像画像を取得する画像取得部を更に備え、
前記コントローラは、
前記撮像画像及び前記形状情報を前記面粗度情報に紐づけて、前記面粗度情報を取得した前記塗装面上の位置を記録すること
を特徴とする塗装評価装置。 - 請求項1に記載の塗装評価装置であって、
前記塗装面の材質を表す材質情報を取得する材質取得部を更に備え、
前記コントローラは、
前記材質情報、前記形状情報、前記面粗度情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記形状情報、前記面粗度情報、前記材質情報の組合せに対応する評価値を推定すること
を特徴とする塗装評価装置。 - 請求項6に記載の塗装評価装置であって、
前記評価モデルは、
評価済塗装面の前記材質情報、前記評価済塗装面の形状情報、前記評価済塗装面の面粗度情報、前記評価済塗装面の鮮映性の評価値を組とする教師データに基づく機械学習によって生成された学習モデルであること
を特徴とする塗装評価装置。 - 塗装面の表面粗さを表す面粗度情報を取得する面粗度取得部と、
前記塗装面の材質を表す材質情報を取得する材質取得部と、
コントローラと、を備える塗装評価装置であって、
前記コントローラは、
前記面粗度情報及び前記材質情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記面粗度情報及び前記材質情報の組合せに対応する評価値を推定すること
を特徴とする塗装評価装置。 - 請求項8に記載の塗装評価装置であって、
前記評価モデルは、
評価済塗装面の面粗度情報、前記評価済塗装面の材質情報、前記評価済塗装面の鮮映性の評価値を組とする教師データに基づく機械学習によって生成された学習モデルであること
を特徴とする塗装評価装置。 - 請求項8に記載の塗装評価装置であって、
前記材質取得部は、前記塗装面の塗装厚み、材料反射率、明度、彩度、色相の少なくともいずれかに関する設計データを前記材質情報として取得すること
を特徴とする塗装評価装置。 - 請求項8に記載の塗装評価装置であって、
前記材質取得部は、前記塗装面を計測して得られた、前記塗装面の塗装厚み、材料反射率、明度、彩度、色相の少なくともいずれかに関する計測データを前記材質情報として取得すること
を特徴とする塗装評価装置。 - 請求項8に記載の塗装評価装置であって、
前記塗装面の撮像画像を取得する画像取得部を更に備え、
前記コントローラは、
前記撮像画像に紐づけて、前記面粗度情報及び前記材質情報を取得した前記塗装面上の位置を記録すること
を特徴とする塗装評価装置。 - 請求項1~12のいずれか一項に記載の塗装評価装置であって、
前記塗装面の鮮映性の評価値は、前記塗装面の平滑度、前記塗装面での反射光に占める拡散反射の割合、前記塗装面に映りこむ像の解像度、の少なくとも1つによって決定される指標であること
を特徴とする塗装評価装置。 - 塗装面の湾曲形状を表す形状情報を取得し、
前記塗装面の表面粗さを表す面粗度情報を取得し、
前記形状情報及び前記面粗度情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記形状情報及び前記面粗度情報の組合せに対応する評価値を推定すること
を特徴とする塗装評価方法。 - 塗装面の湾曲形状を表す形状情報を取得する形状取得部と、
前記塗装面の表面粗さを表す面粗度情報を取得する面粗度取得部と、
を制御するコンピュータに、
前記形状取得部を用いて前記形状情報を取得するステップと、
前記面粗度取得部を用いて前記面粗度情報を取得するステップと、
前記形状情報及び前記面粗度情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記形状情報及び前記面粗度情報の組合せに対応する評価値を推定するステップと、
を実行させるための塗装評価プログラム。 - 入力層及び出力層を含むニューラルネットワークによって構成された評価モデルであって、
塗装面の湾曲形状を表す形状情報及び前記塗装面の表面粗さを表す面粗度情報を含み、前記入力層に入力される入力データと、
前記塗装面の鮮映性の評価値を含み、前記出力層から出力される出力データと、
を互いに関連付けて学習させたこと
を特徴とする評価モデル。 - 塗装面の湾曲形状を表す形状情報、前記塗装面の表面粗さを表す面粗度情報、前記塗装面の鮮映性の評価値を組とする教師データを取得し、
前記教師データに基づく機械学習を行って、前記形状情報及び前記面粗度情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを生成すること
を特徴とする評価モデル生成方法。 - 塗装面の表面粗さを表す面粗度情報を取得し、
前記塗装面の材質を表す材質情報を取得し、
前記面粗度情報及び前記材質情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記面粗度情報及び前記材質情報の組合せに対応する評価値を推定すること
を特徴とする塗装評価方法。 - 塗装面の表面粗さを表す面粗度情報を取得する面粗度取得部と、
前記塗装面の材質を表す材質情報を取得する材質取得部と、
を制御するコンピュータに、
前記面粗度取得部を用いて前記面粗度情報を取得するステップと、
前記材質取得部を用いて前記材質情報を取得するステップと、
前記面粗度情報及び前記材質情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを用いて、前記面粗度情報及び前記材質情報の組合せに対応する評価値を推定するステップと、
を実行させるための塗装評価プログラム。 - 入力層及び出力層を含むニューラルネットワークによって構成された評価モデルであって、
塗装面の表面粗さを表す面粗度情報及び前記塗装面の材質を表す材質情報を含み、前記入力層に入力される入力データと、
前記塗装面の鮮映性の評価値を含み、前記出力層から出力される出力データと、
を互いに関連付けて学習させたこと
を特徴とする評価モデル。 - 塗装面の表面粗さを表す面粗度情報、前記塗装面の材質を表す材質情報、前記塗装面の鮮映性の評価値を組とする教師データを取得し、
前記教師データに基づく機械学習を行って、前記面粗度情報及び前記材質情報を含む入力に対して前記塗装面の鮮映性の評価値を出力する評価モデルを生成すること
を特徴とする評価モデル生成方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202280041949.9A CN117480383A (zh) | 2021-06-21 | 2022-06-13 | 涂装评价装置和涂装评价方法 |
JP2023529142A JPWO2022269342A1 (ja) | 2021-06-21 | 2022-06-13 | |
EP22826649.0A EP4361614A1 (en) | 2021-06-21 | 2022-06-13 | Coating evaluation device and coating evaluation method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2021/000416 WO2022269302A1 (ja) | 2021-06-21 | 2021-06-21 | 塗装評価装置及び塗装評価方法 |
IBPCT/IB2021/000416 | 2021-06-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022269342A1 true WO2022269342A1 (ja) | 2022-12-29 |
Family
ID=84544201
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2021/000416 WO2022269302A1 (ja) | 2021-06-21 | 2021-06-21 | 塗装評価装置及び塗装評価方法 |
PCT/IB2022/000312 WO2022269342A1 (ja) | 2021-06-21 | 2022-06-13 | 塗装評価装置及び塗装評価方法 |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2021/000416 WO2022269302A1 (ja) | 2021-06-21 | 2021-06-21 | 塗装評価装置及び塗装評価方法 |
Country Status (4)
Country | Link |
---|---|
EP (2) | EP4361613A4 (ja) |
JP (2) | JPWO2022269302A1 (ja) |
CN (2) | CN117501108A (ja) |
WO (2) | WO2022269302A1 (ja) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0326943A (ja) * | 1989-06-26 | 1991-02-05 | Nissan Motor Co Ltd | 塗装鮮映性測定方法 |
US4989984A (en) * | 1989-11-08 | 1991-02-05 | Environmental Research Institute Of Michigan | System for measuring optical characteristics of curved surfaces |
JPH06160300A (ja) * | 1992-11-17 | 1994-06-07 | Nissan Motor Co Ltd | ウェット鮮映性測定装置 |
JP2006234613A (ja) * | 2005-02-25 | 2006-09-07 | Toyota Motor Corp | 塗膜評価装置及び方法 |
JP2006266728A (ja) | 2005-03-22 | 2006-10-05 | Honda Motor Co Ltd | 塗膜外観の評価方法及び塗装物 |
JP2014149286A (ja) * | 2013-01-31 | 2014-08-21 | Nireco Corp | 面粗さ測定装置 |
JP2019500588A (ja) * | 2015-10-29 | 2019-01-10 | ビーエーエスエフ コーティングス ゲゼルシャフト ミット ベシュレンクテル ハフツングBASF Coatings GmbH | 塗料表面の質感パラメータを決定するための方法 |
CN110146034A (zh) * | 2019-06-20 | 2019-08-20 | 本钢板材股份有限公司 | 一种基于表面波纹度的冷轧薄钢板表面质量的判别方法 |
US20190287237A1 (en) * | 2016-12-01 | 2019-09-19 | Autaza Tecnologia LTDA-EPP | Method and system for automatic quality inspection of materials and virtual material surfaces |
US20190310193A1 (en) * | 2018-04-09 | 2019-10-10 | Hunter Associates Laboratory, Inc. | Uv-vis spectroscopy instrument and methods for color appearance and difference measurement |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3257182B2 (ja) * | 1993-09-27 | 2002-02-18 | 日産自動車株式会社 | 塗装処理装置及び塗装処理方法 |
JP3322034B2 (ja) * | 1994-10-24 | 2002-09-09 | 日産自動車株式会社 | 塗装品質解析装置 |
JP3358434B2 (ja) * | 1996-03-27 | 2002-12-16 | 日産自動車株式会社 | 塗装品質解析装置 |
JP2006308476A (ja) * | 2005-04-28 | 2006-11-09 | Tokyo Seimitsu Co Ltd | 表面粗さ/形状測定装置 |
WO2017175779A1 (ja) * | 2016-04-08 | 2017-10-12 | コニカミノルタ株式会社 | 光学測定装置、画像の生成方法および画像の生成プログラム |
-
2021
- 2021-06-21 WO PCT/IB2021/000416 patent/WO2022269302A1/ja active Application Filing
- 2021-06-21 JP JP2023529139A patent/JPWO2022269302A1/ja active Pending
- 2021-06-21 CN CN202180099260.7A patent/CN117501108A/zh active Pending
- 2021-06-21 EP EP21946909.5A patent/EP4361613A4/en active Pending
-
2022
- 2022-06-13 EP EP22826649.0A patent/EP4361614A1/en active Pending
- 2022-06-13 WO PCT/IB2022/000312 patent/WO2022269342A1/ja active Application Filing
- 2022-06-13 CN CN202280041949.9A patent/CN117480383A/zh active Pending
- 2022-06-13 JP JP2023529142A patent/JPWO2022269342A1/ja active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0326943A (ja) * | 1989-06-26 | 1991-02-05 | Nissan Motor Co Ltd | 塗装鮮映性測定方法 |
US4989984A (en) * | 1989-11-08 | 1991-02-05 | Environmental Research Institute Of Michigan | System for measuring optical characteristics of curved surfaces |
JPH06160300A (ja) * | 1992-11-17 | 1994-06-07 | Nissan Motor Co Ltd | ウェット鮮映性測定装置 |
JP2006234613A (ja) * | 2005-02-25 | 2006-09-07 | Toyota Motor Corp | 塗膜評価装置及び方法 |
JP2006266728A (ja) | 2005-03-22 | 2006-10-05 | Honda Motor Co Ltd | 塗膜外観の評価方法及び塗装物 |
JP2014149286A (ja) * | 2013-01-31 | 2014-08-21 | Nireco Corp | 面粗さ測定装置 |
JP2019500588A (ja) * | 2015-10-29 | 2019-01-10 | ビーエーエスエフ コーティングス ゲゼルシャフト ミット ベシュレンクテル ハフツングBASF Coatings GmbH | 塗料表面の質感パラメータを決定するための方法 |
US20190287237A1 (en) * | 2016-12-01 | 2019-09-19 | Autaza Tecnologia LTDA-EPP | Method and system for automatic quality inspection of materials and virtual material surfaces |
US20190310193A1 (en) * | 2018-04-09 | 2019-10-10 | Hunter Associates Laboratory, Inc. | Uv-vis spectroscopy instrument and methods for color appearance and difference measurement |
CN110146034A (zh) * | 2019-06-20 | 2019-08-20 | 本钢板材股份有限公司 | 一种基于表面波纹度的冷轧薄钢板表面质量的判别方法 |
Also Published As
Publication number | Publication date |
---|---|
EP4361613A1 (en) | 2024-05-01 |
EP4361613A4 (en) | 2024-05-29 |
CN117501108A (zh) | 2024-02-02 |
JPWO2022269302A1 (ja) | 2022-12-29 |
EP4361614A1 (en) | 2024-05-01 |
CN117480383A (zh) | 2024-01-30 |
WO2022269302A1 (ja) | 2022-12-29 |
JPWO2022269342A1 (ja) | 2022-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6635690B2 (ja) | 情報処理装置、情報処理方法及びプログラム | |
US20200116478A1 (en) | Methods for improving the accuracy of dimensioning-system measurements | |
JP6039008B2 (ja) | 着色評価装置及び着色評価方法 | |
JP4892480B2 (ja) | 適応三次元走査 | |
US7039486B2 (en) | Method and device for viewing, archiving and transmitting a garment model over a computer network | |
TW201812700A (zh) | 多維度尺寸量測系統及其方法 | |
CN111727412A (zh) | 用于设定照明条件的方法、装置、系统及程序以及存储介质 | |
JPH04291136A (ja) | 塗装面品質の自動評価方法および装置 | |
Marcin et al. | Hierarchical, three‐dimensional measurement system for crime scene scanning | |
JP7330970B2 (ja) | コンピュータ生成された参照物体を有するマシンビジョンシステム | |
JP2016527475A (ja) | 測定対象物の少なくとも1つの仮想画像を生成する方法及び装置 | |
JP2017044596A (ja) | 膜厚測定装置および膜厚測定方法 | |
JP5599849B2 (ja) | レンズ検査装置及びその方法 | |
CN106415198B (zh) | 图像记录方法和执行该方法的坐标测量机 | |
JP6237032B2 (ja) | 色と三次元形状の計測方法及び装置 | |
Stets et al. | Scene reassembly after multimodal digitization and pipeline evaluation using photorealistic rendering | |
WO2022269342A1 (ja) | 塗装評価装置及び塗装評価方法 | |
JP6564848B2 (ja) | 膜厚測定装置および膜厚測定方法 | |
JP2012068257A (ja) | 反射特性を分析するための方法 | |
Sebar et al. | A trustable 3D photogrammetry approach for cultural heritage | |
KR100544979B1 (ko) | 물체의 반사율 획득 시스템 및 물체 표현 방법 | |
IT202100016229A1 (it) | Apparato modulare per l'ispezione di prodotti industriali e metodi collegati | |
JP5967470B2 (ja) | 検査装置 | |
WO2022269300A1 (ja) | 塗装評価装置及び塗装評価方法 | |
WO2022269301A1 (ja) | 塗装評価装置及び塗装評価方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22826649 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023529142 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280041949.9 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022826649 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022826649 Country of ref document: EP Effective date: 20240122 |