JP7651375B2 - Three-dimensional model creation support system, program and recording medium - Google Patents

Description

The present invention relates to a three-dimensional model creation support system, a program, and a recording medium.

In recent years, power plants and chemical plants have been using 3D-CAD (Three-Dimension Computer-Aided Design) to manage their assets.

However, some of these plants were built a long time ago, do not have 3D CAD models, and asset management is still carried out using paper documents.

In recent years, services have become commonplace that use laser measurement to obtain three-dimensional point cloud data and use that data to create 3D models of plants. In the following, three dimensions may be referred to as "3D" and two dimensions as "2D."

Current laser measurement devices are capable of acquiring highly accurate three-dimensional point cloud data. Devices have also been developed that can acquire color information using a camera at the same time as acquiring coordinate data. This makes it possible to display colored three-dimensional point cloud data. This makes it easy for the human eye to identify pipes, equipment, and the like.

However, this point cloud data is not a 3D model with attributes. Therefore, in order to use it for asset management using tag information for equipment and piping, it is necessary to convert this point cloud data into a 3D model with attributes.

The typical method for converting such data into a 3D model is for an operator to convert the point cloud data into a 3D model manually while displaying the data on a screen. This makes the conversion process extremely labor-intensive.

On the other hand, in recent years, there is technology that uses software to recognize the shapes of pipes and other objects from point cloud data and convert them into attribute-free 3D models. In addition, technology has been developed that automatically assigns attributes to attribute-free 3D models.

For example, Patent Document 1 discloses a layout design support device that compares end point connection information of logical connection data, which is the logical connection relationship between plant equipment, with end point connection information of geometric shape data, which is graphic shape information in three-dimensional space, and automatically generates a logical connection/geometric shape correspondence table composed of correspondence relationship data that associates logical connection data and geometric shape data for which the end point connection information matches.

Patent No. 4940267

Conventional technology for converting point cloud data into 3D models only targets relatively simple shapes such as pipes and steel materials.

In addition, in Patent Document 1, it is difficult to convert all devices such as valves into 3D models. In addition, it is difficult to accurately convert all piping into 3D models, so it is necessary to correct the created piping model or create additional piping models that could not be created automatically.

The objective of the present invention is to reduce the user's workload and efficiently create 3D models with attributes.

The three-dimensional model creation support system of the present invention includes a partial asset CAD model creation device that creates a partial asset CAD model having attribute data using data of an oblique view showing a portion of an asset, and a three-dimensional pattern matching device that identifies the position of the partial asset CAD model by pattern matching between the partial asset CAD model and a three-dimensional image of the asset, and creates an asset CAD model with attributes by placing the partial asset CAD model in three-dimensional space.

The present invention reduces the workload of the user and enables efficient creation of 3D models with attributes.

FIG. 1 is a configuration diagram illustrating an example of a three-dimensional model creation support system according to a first embodiment. FIG. 2 is an isometric view showing an example of piping in a plant. FIG. 4 is a flow diagram showing a method for creating a piping model and a valve model. FIG. 13 is a diagram showing an example of extracted line segments of a pipe. FIG. 2 is a perspective view showing a partial asset CAD model. 1 is a table showing an example of an attribute database relating to piping. FIG. 13 is a diagram showing an example of three-dimensional image data of an entire asset. FIG. 1 is a flow diagram illustrating a method for 3D pattern matching. FIG. 13 is a perspective view showing an example of a partial piping model in which a virtual outer diameter is set. FIG. 2 is a perspective view illustrating an example of an asset CAD model with attributes. FIG. 11 is a configuration diagram illustrating an example of a three-dimensional model creation support system according to a second embodiment. FIG. 1 is a diagram showing an example of creating a 3D image from multiple 2D images. FIG. 2 is a perspective view showing a 3D image recognized as a valve. FIG. 13 is a perspective view showing the result of arranging the valves and instruments. FIG. 13 is an isometric view showing an example in which information on the connection destination of a pipe is added. FIG. 13 is a diagram showing a point cloud corresponding to a cross-sectional shape of a piping model.

A preferred embodiment of this disclosure is described below.

It is preferable that the three-dimensional model creation support system further includes an attribute database having attribute data and management numbers of asset parts. The partial asset CAD model creation device then obtains the management number displayed in the oblique view, obtains attribute data associated with the management number of the part from the attribute database, and adds the attribute data to the partial asset CAD model.

It is desirable for the partial asset CAD model creation device to obtain dimensions from the dimension lines displayed in the oblique view and create a partial asset CAD model according to the dimensions.

It is desirable for the three-dimensional pattern matching device to set a virtual outer diameter of the partial asset CAD model, identify a position where the number of points contained within the partial asset CAD model having the virtual outer diameter is the largest, and place the partial asset CAD model at the identified position.

It is desirable for the three-dimensional pattern matching device to set virtual cross-sectional dimensions of a specified portion of the partial asset CAD model, divide the partial asset CAD model having the cross-sectional dimensions into regions, identify a position where the number of points contained within the partial asset CAD model having the divided cross-sectional dimensions is the largest, and place the partial asset CAD model at the identified position.

It is desirable for the three-dimensional pattern matching device to set virtual cross-sectional dimensions of a specified portion of the partial asset CAD model, identify a position where the error in the distance between the cross-sectional contour of the partial asset CAD model having the cross-sectional dimensions and the point cloud is minimal, and place the partial asset CAD model at the identified position.

The three-dimensional model creation support system may include a partial asset CAD model creation device that creates a partial asset CAD model having attribute data using data of a perspective view showing a part of an asset having piping and at least one of a valve and equipment, a valve/equipment recognition device that acquires position information of valves and equipment from two-dimensional or three-dimensional image data of the asset, and a three-dimensional pattern matching device that identifies the position of the partial asset CAD model by pattern matching between the partial asset CAD model and the three-dimensional image of the asset, and creates an asset CAD model with attributes by arranging the partial asset CAD model in three-dimensional space. The three-dimensional pattern matching device then limits the range of pattern matching from the position information of the valves and equipment acquired by the valve/equipment recognition device and the relative position information of the valves and equipment acquired from the partial asset CAD model.

The following describes the examples with reference to the drawings.

Figure 1 is a configuration diagram showing an example of a three-dimensional model creation support system according to the first embodiment.

As shown in this diagram, the three-dimensional model creation support system includes a partial asset CAD model creation device 2 and a 3D asset pattern matching device 6 (three-dimensional pattern matching device). Asset isometric data 1 is used for predetermined processing in the partial asset CAD model creation device 2. The partial asset CAD model 3 is created in the partial asset CAD model creation device 2, and is used for predetermined processing in the 3D asset pattern matching device 6. The 3D asset pattern matching device 6 creates an attributed asset CAD model 7 using the partial asset CAD model 3 and 3D image data 5 (three-dimensional image data). The attributed asset CAD model 7 is linked to an attribute database 4.

In the following, image data may simply be referred to as "image." Additionally, "recognition" refers to identifying pipes, valves, equipment, etc. using numerical data such as two-dimensional or three-dimensional points, lines, and figures.

The above devices constituting the 3D model creation support system may all be built into one computer device, or each device may be built into a separate computer device. Each of the above processes is carried out by processing a program recorded on one or more memories or other recording media built into the computer device using one or more central processing units (CPUs) built into the computer device. The program may also be recorded on a recording medium such as a memory stick that is removable from the computer device. The program is for causing the computer device to execute a specified process. The recording medium is computer-readable and has the program recorded on it.

The asset isometric drawing data 1 is input and recorded in one or more memories or other recording media built into the computer device. The partial asset CAD model 3 created from the asset isometric drawing data 1 by a predetermined process, and the attributed asset CAD model 7 finally created, etc. are recorded in one or more memories or other recording media built into the computer device. Note that input to the recording media may be performed via a communication means such as the Internet.

Asset isometric drawing data 1 is data of an isometric drawing of an asset, and is data capable of displaying a three-dimensional drawing of the asset as viewed from diagonally above. Hereinafter, an isometric drawing will be abbreviated as an "isometric drawing." An isometric drawing may be an isometric projection drawing. Also, an isometric drawing may be collectively referred to as an "oblique drawing."

The partial asset CAD model creation device 2 creates a 3D model from the assets included in the asset isometric data 1. Usually, only a portion of the asset is recorded, such as in a piping model, so the partial asset is converted into CAD. The detailed method of CAD conversion will be described later. Also, since the asset isometric data 1 usually includes the management number of the target part, a management number can be assigned to the CAD converted model. In the example of piping, the piping number is assigned as the management number.

The partial asset CAD model 3 is a model created by the partial asset CAD model creation device 2. In the piping example, it is a 3D-CAD model of a continuous line of piping with a certain piping number. In addition, the partial asset CAD model 3 is assigned the piping number as attribute data.

In the attribute database 4, attribute data for each part of an asset is recorded along with the part's management number. In the case of piping, the management number is the piping number, and attribute information (attribute data) such as the outer diameter, thickness, and material of the piping is recorded in association with the piping number. Therefore, a 3D-CAD model that has a piping number can obtain all related attributes by linking with the attribute database 4.

The 3D image data 5 is three-dimensional image data of the entire asset. For example, it can be created from multiple images taken from a drone.

The 3D asset pattern matching device 6 matches the partial asset CAD model 3 with the 3D image data 5, and places the partial asset CAD model 3 in the three-dimensional space in which the 3D image data 5 is rendered. Since the position information of the partial asset CAD model 3 is usually unknown, it is placed in a location where the shape matches the 3D image.

The attributed asset CAD model 7 is created by arranging all partial asset CAD models 3. Since the partial asset CAD models 3 are assigned partial asset management numbers as attributes, the attributed asset CAD models 7, which are a collection of partial asset CAD models 3, are also assigned management numbers. Therefore, by linking with the attribute database 4, it becomes an attributed asset model that includes other attribute data.

Below, an example plant is described in detail for this embodiment.

Figure 2 is an isometric drawing showing an example of plant piping.

This diagram shows the data created from asset isometric data 1 in Figure 1. Plant isometric drawings are often used for piping installation, so they are generally created by extracting a continuous line of piping and drawing it.

For the sake of explanation, the directions are defined by the x-axis, y-axis, and z-axis shown in the figure. The construction of an isometric drawing is the most basic drawing method. That is, the vertical z-axis points upward in the figure, and the x-axis and y-axis are each tilted 30 degrees from the horizontal direction in the figure, with the angle between them being 120 degrees.

Most of the pipes are arranged along the x-axis, y-axis, or z-axis. Although the bent parts of the pipes are technically bent pipes, in this embodiment, the bent pipe parts are depicted as schematic right-angled pipes. If there are valves in the middle of the pipes, they are also displayed in the isometric drawing. In addition, dimensions necessary for construction, such as the length of the straight pipe section, the length to the branch pipe, and the position from the end to the valve, are displayed with dimension lines. Both ends of the dimension lines are arrows, and the leader lines of the dimension lines are lines. However, the thickness of the lines differs from that of pipes so that they can be distinguished from pipes. In addition, the pipe numbers are displayed on the pipes.

In Figure 2, the "PAS-01-300" displayed on the pipe at the far right is the pipe number. Note that in recent years, isometric drawings are often created using CAD software, but here we focus on isometric drawings created on paper.

The partial asset CAD model creation device 2 creates a partial asset CAD model 3, which is a three-dimensional CAD model, from the isometric drawing.

In this example, the model targets piping and valves, so the following steps were followed to create a piping model and then a valve model.

Figure 3 is a flow diagram showing how to create a piping model and a valve model.

As shown in this figure, the isometric drawing shown in Figure 2 is digitized using image recognition, and only those line segments whose thickness is the same as that of the piping are extracted (step S21).

Figure 4 shows an example of the results of step S21, showing only the extracted pipe lines.

Next, one end point is selected (designated A in Figure 4) and its coordinates are set to (0,0,0). The coordinates of the other points (designated B, C, D, E, and F in Figure 4) are determined from the inclination and length of the extracted line segment on the drawing (step S22).

For example, if the horizontal rightward direction of line segment AB on the paper is 0 degrees, then point B is at an angle of 210 degrees from point A and has a length of 58 mm. The direction of 210 degrees is the negative direction of the x-axis in three-dimensional coordinates, so the coordinates of B are (-58, 0, 0).

Next, line segment BC is inclined at 150 degrees on the paper and has a length of 30 mm. Line segment BC is in the positive direction of the y-axis in three-dimensional coordinates, so the coordinates of point C are (-58, 30, 0). In a similar manner, the coordinates of points D, E, and F can be found. However, the lengths are lengths on the paper, and differ from the actual lengths. The ratio between the actual length and the length on the paper is constant, so the actual length can be obtained by converting the coordinates at a constant ratio. In this example, the actual length is 100 times the length on the paper, so if the actual coordinates are A (0, 0, 0), then B (-5800, 0, 0) will be obtained.

Next, the outer diameter of the pipe to be created is determined (step S23). The pipe number displayed along the pipe in the isometric drawing is read using OCR technology, and the corresponding outer diameter is determined. In this embodiment, the last digit of the pipe number indicates the outer diameter. In the example of Figure 2, the 300 in the pipe number "PAS-01-300" indicates the outer diameter. However, this means that the nominal diameter is 300A, so the actual outer diameter is 318.5 mm.

Next, a piping model is created from the coordinates obtained in step S22 and the outer diameter obtained in step S23 (step S24). Using this information, a 3D-CAD model of the piping can be created using the API (Application Programming Interface) of a general 3D-CAD system.

Finally, the valve model is placed on the created piping model (step S25). The position coordinates of the valve can be identified in the same way as the method used to find the end points of the piping in step S22. Once the valve position is known, the valve model can be placed using the API of the CAD software.

The valve model differs depending on the type of valve. In this example, the valve model was selected from the type of valve number displayed in the isometric drawing. In the example in Figure 2, VG represents a gate valve, so a model of a gate valve is placed.

As described above, the partial asset CAD model 3 of Figure 1 can be created using the method shown in Figure 3.

Figure 5 is an oblique view of the partial asset CAD model created in this example.

In the above example, the pipe dimensions are the length of the lines that represent the pipes, but in some isometric drawings, easier-to-read views are prioritized, and lines of different lengths from the actual dimensions are drawn, with the correct dimensions displayed as dimension values. Therefore, instead of reading the length of each line, the dimension values can be read using the OCR function and converted into coordinate values.

Next, we will explain the attribute database 4 in Figure 1.

In the attribute database 4, attribute data for each part of the asset is recorded along with the part's management number.

Figure 6 shows an example of an attribute database 4 related to piping.

In this diagram, attribute information such as the outer diameter, wall thickness, and material of the pipes are displayed in a table, with the pipe number used as an index.

The 3D image data 5 (Figure 1) is three-dimensional image data of the entire asset. In this embodiment, the 3D image data 5 was created from multiple images taken by a drone.

Figure 7 shows an example of 3D image data 5.

As shown in this figure, in addition to the pipe 11, there is point cloud data for the tank 12a, pump 12b, and valve 13.

In the 3D asset pattern matching device 6, the partial asset CAD model 3 is matched with the 3D image data 5, and the partial asset CAD model 3 is placed in the three-dimensional space in which the 3D image data 5 is rendered. Since the position information of the partial asset CAD model 3 is usually unknown, it is placed in a location where the shape matches the 3D image using the following method.

Figure 8 is a flow diagram showing a method for 3D pattern matching.

A virtual outer diameter is set for the center line of the created partial piping model as a constant multiple of the outer diameter (step S61).

Figure 9 shows an example of a partial piping model with a virtual outer diameter set.

In this figure, the virtual outer diameter is set to 1.5 times the outer diameter. The partial piping model is a piping 75 with a virtual outer diameter arranged around a straight pipe center line 71.

Here, the center line refers to the line that connects the centers of the cross sections of the pipes in the 3D image. The center line is a line segment that is not cut by valves installed in the middle of the pipes, and connects one device at one end of the pipe to another device at the other end. Note that a line made up of multiple connected line segments is called a "broken line."

The piping model with the virtual outer diameter is placed on the 3D image of Figure 7, and the number of points included in the virtual outer diameter is counted (step S62). Note that the orientation of the piping model with the outer diameter is aligned with the orientation on the 3D image, with reference to the isometric drawing.

The piping model having the virtual outer diameter is translated, and the number of points included in the virtual outer diameter is counted (step S63).

The target space is comprehensively searched, and the piping model is placed at the position with the largest number of points (step S64).

If there are multiple locations where the number of point clouds is the largest, the virtual outer diameter of the pipe is reduced by a predetermined value ΔD, and the numbers of point clouds at the multiple target locations are compared to identify the location with the largest number of point clouds (step S65).

Step S65 is repeated until the virtual outer diameter is equal to the outer diameter (step S66). If it cannot be identified, it is placed in one of the multiple candidates.

If the partial piping model is in the correct position, all point cloud data will be contained within the virtual outer diameter model, maximizing the number of point clouds.

Here, the point cloud is counted in a cylindrical region having a virtual outer diameter, but the cross section may be a square, and the length of one side of the square may be a constant multiple of the outer diameter of the pipe. Furthermore, instead of counting the number of point clouds in the region, the cylinder or rectangular parallelepiped may be divided into N parts in the longitudinal direction, and the presence or absence of a point cloud in each divided region may be determined. In other words, the virtual cross-sectional dimensions of a specific portion of a partial asset CAD model such as a partial piping model are set (for example, if the cross-sectional shape is a square, a rectangular parallelepiped is assumed in which the length of one side of the square is a constant multiple of the outer diameter of the pipe, and the length of one side is set as the representative dimension of the virtual cross section (i.e., the virtual cross-sectional dimension)). The partial asset CAD model having the cross-sectional dimensions is divided into regions, and the position at which the number of point clouds contained inside the partial asset CAD model having the divided cross-sectional dimensions is maximized is identified, and the partial asset CAD model is placed at the identified position.

By repeating the above steps for all partial asset models, an attributed asset CAD model 7 can be created.

Figure 10 is an oblique view showing an example of an attributed asset CAD model 7 created in this embodiment.

As described above, in this embodiment, an attributed asset CAD model 7 can be created by utilizing an isometric drawing. This is a main model of the plant excluding structures such as pipe supports that support the pipes, and a 3D model can be created more efficiently than the conventional manual model creation.

Example 2 is a case where the target asset is a plant facility consisting of piping, valves, equipment, etc.

Figure 11 is a configuration diagram showing an example of a three-dimensional model creation support system in this embodiment.

In this diagram, the three-dimensional model creation support system includes a partial plant CAD model creation device 22, a valve/equipment recognition device 26, and a 3D pattern matching device 27.

The piping isometric data 21 (piping perspective view data) is used for predetermined processing in the partial plant CAD model creation device 22. The partial plant CAD model 23 is created by the partial plant CAD model creation device 22 and is used for predetermined processing in the 3D pattern matching device 27. The 2D/3D image data 25 (two-dimensional/three-dimensional image data) is used for predetermined processing in the valve/equipment recognition device 26. The 3D pattern matching device 27 creates an attributed plant CAD model 28 using the partial plant CAD model 23 and data processed by the valve/equipment recognition device 26 using the 2D/3D image data 25. The attributed plant CAD model 28 is linked to the attribute database 24.

Note that, because Example 1 also uses a plant facility as an example, Example 2 has many commonalities with Example 1. The differences are the 2D/3D image data 25, the valve/equipment recognition device 26, and the 3D pattern matching device 27. These will be explained further below.

The 2D/3D image data 25 includes 2D image data of the same part photographed from multiple angles, and 3D image data created based on the 2D images. These are stored in a recording medium such as a database. Here, along with the data of each point in the 3D images, the corresponding relationship of the 2D image data used to create them is also stored. The 2D image data includes the image file name and the format of the two-dimensional coordinates on the image file.

Figure 12 shows an example of creating a 3D image from multiple 2D images.

In this diagram, a 3D image is created from N 2D images.

The valve/equipment recognition device 26 recognizes valves and equipment from 2D or 3D images of the plant and obtains position information of the recognized valves and equipment. In this embodiment, the valves were recognized using 2D images.

The specific steps are shown below.

Valves and equipment are recognized from the 2D images used (step S251). The widely used method of recognizing objects in the images is deep learning. By learning images of valves and equipment in advance, images of valves and equipment can be identified from all 2D images.

Using the correspondence between the 3D images and the 2D images stored in the 2D/3D image data 25, a 3D image corresponding to the image of the valve and equipment identified on the 2D image is identified (step S252).

Note that the 2D images corresponding to the 3D image of a certain valve are spread across multiple image files. Furthermore, there is not a one-to-one correspondence between points in the 3D image and points in the 2D image. Therefore, among the pixels of the valve image recognized in a certain 2D image data, only a portion of the pixels correspond to the 3D image. However, by recognizing the valve and equipment in all 2D images used to create the 3D image and identifying the corresponding 3D image, it is possible to identify the 3D image of the valve in the 3D image. Note that a method of finding the corresponding 3D image may be a method of determining whether the corresponding 2D image is within the area identified in step S251 for all points of the 3D image.

The position information of the valves and equipment is obtained from the coordinate data of the valves and equipment identified on the 3D image (step S253).

Figure 13 is a perspective view showing a 3D image recognized as a valve.

In this diagram, the area containing the valve is shown as a dashed rectangular parallelepiped 110. Equipment may also be shown as a similar rectangular parallelepiped.

Note that since the 3D image contains multiple valves and equipment, it is necessary to separate the 3D image identified in step S252 into individual valves and equipment. In this embodiment, the identified point clouds that are continuous and have an interval within a threshold are separated as a single valve or equipment.

In addition, any rectangular parallelepipeds created by this process whose volumes are smaller than a predetermined threshold value are excluded from the position information of valves and equipment. This process makes it possible to delete data that was mistakenly recognized as a valve or equipment in step S252.

By using the above method, it is possible to obtain three-dimensional position information for valves and equipment.

In this embodiment, the valves and equipment are recognized using 2D images, but they may be recognized using only 3D images. In other words, the process of step S252 may be performed using multiple 2D images of the 3D images taken from various viewpoints. In addition, if there is sufficient 3D data of the valves and equipment as training data, the valves and equipment may be identified by three-dimensional shape recognition.
Next, the 3D pattern matching device 27 will be described.

The 3D pattern matching device 27 uses the position information of the valves and equipment obtained by the valve/equipment recognition device 26 to determine which position on the 3D image the partial plant CAD model 23 corresponds to. By using the position information of the valves and equipment, the search range can be significantly shortened.

The specific processing procedure is shown below. Note that Figure 2 is used as the piping isometric data 21, and Figure 5 is used as the partial plant CAD model 23.

First, the position information of the valves and equipment obtained by the valve/equipment recognition device 26 is placed on the 3D image (step S261).

Figure 14 is a perspective view showing the arrangement of the valves and equipment.

In this diagram, the position information of tank 121, valves 122, 123, 124, 125, and pumps 126, 127 is displayed.

Next, the relative positions of the valves and equipment that can be obtained from the partial plant CAD model 23 are obtained (step S262). In the example of FIG. 2, for the placement positions (points on the piping center line) of the two valves VG-01-50 and VG-02-50, if VG-01-50 is set as the reference point (0,0,0), then VG-02-50 is (0,2400,0).

Here, the search range for pattern matching of the partial plant model is narrowed down using the position information of the valves and devices obtained in step S261 and the relative position information of the valves and devices obtained in step S262 (step S263). In other words, the range of pattern matching is limited.

In this example, as shown in FIG. 14, the area in which the valves may be placed is the area of valves 122, 123, 124, and 125. Furthermore, step S262 dictates that the relative positions of the two valves must be 2400 mm apart in the y-axis direction. Therefore, the coordinates (X1, Y1, Z1) of V1 are changed throughout the entire area of valves 122, 123, 124, and 125, and only conditions where (X1, Y1 + 2400, Z) is included in the area of valves 122, 123, 124, and 125 are included in the range of the search.

The search range is limited to that determined in step S263, and in the same manner as the matching method used in Example 1, a virtual outer diameter shown in FIG. 9 is set, and the position at which the number of points contained within the interior of the pipe 75 having the virtual outer diameter is maximized is identified (step S264).

In addition, it is possible to further narrow the search range in the following cases:

Figure 15 shows an example in which information about the pipe connection destination has been added to the isometric drawing in Figure 2.

As shown in FIG. 15, if there is equipment information at the destination of the pipe connection, the relative position information of the valve and the equipment can also be obtained in step S262, so that the search range can be further narrowed down in step S263.

Note that in Examples 1 and 2, a method using the virtual outer diameter shown in FIG. 9 is shown as a pattern matching method, but other methods are also possible.

Figure 16 shows the point cloud corresponding to the cross-sectional shape of the piping model.

As shown in this figure, the distance between the contour 140 of the cross section of the piping model and the point cloud 141 may be matched using a statistical method to minimize the error. The statistical method may be the least squares method, etc.

In addition, if the pipe is wrapped with insulation, the shape of the outer surface of the pipe including the insulation may be matched as the contour 140.

As shown in the above examples, by utilizing the position information of valves and equipment, the position of the partial plant model can be efficiently identified, and an attributed plant CAD model 28 can be created with a small number of steps.

1: Asset isometric data, 2: Partial asset CAD model creation device, 3: Partial asset CAD model, 4: Attribute database, 5: 3D image data, 6: 3D asset pattern matching device, 7: Asset CAD model with attributes, 11: Piping, 12a: Tank, 12b: Pump, 13: Valve, 21: Piping isometric data, 22: Partial plant CAD model creation device, 23: Partial plant CAD model, 24: Attribute database, 25: 2D/3D image data, 26: Valve/equipment recognition device, 27: 3D pattern matching device, 28: Plant CAD model with attributes, 71: Straight pipe centerline, 75: Piping.

Claims (9)

a partial asset CAD model creation device that creates a partial asset CAD model having attribute data by using data of a perspective view showing a part of an asset;
a three-dimensional pattern matching device that identifies a position of the partial asset CAD model by pattern matching between the partial asset CAD model and a three-dimensional image of the asset, and creates an attributed asset CAD model by placing the partial asset CAD model in a three-dimensional space. further comprising an attribute database having the attribute data and a management number of the part of the asset;
2. The three-dimensional model creation support system according to claim 1, wherein the partial asset CAD model creation device obtains a management number displayed in the oblique view, obtains the attribute data associated with the management number of the part from the attribute database, and adds the attribute data to the partial asset CAD model. The three-dimensional model creation support system according to claim 1, wherein the partial asset CAD model creation device obtains dimensions from dimension lines displayed in the oblique view and creates the partial asset CAD model according to the dimensions. The three-dimensional model creation support system according to claim 1, wherein the three-dimensional pattern matching device sets a virtual outer diameter of the partial asset CAD model, identifies a position where the number of points contained inside the partial asset CAD model having the virtual outer diameter is the largest, and places the partial asset CAD model at the identified position. The three-dimensional model creation support system according to claim 1, wherein the three-dimensional pattern matching device sets virtual cross-sectional dimensions of a predetermined portion of the partial asset CAD model, divides the partial asset CAD model having the cross-sectional dimensions into regions, identifies a position where the number of points contained within the divided partial asset CAD model having the cross-sectional dimensions is the largest, and places the partial asset CAD model at the identified position. The three-dimensional model creation support system of claim 1, wherein the three-dimensional pattern matching device sets virtual cross-sectional dimensions of a predetermined portion of the partial asset CAD model, identifies a position where an error in the distance between the outline of the cross-section of the partial asset CAD model having the cross-sectional dimensions and the point cloud is minimized, and places the partial asset CAD model at the identified position. a partial asset CAD model creation device that creates a partial asset CAD model having attribute data by using data of a perspective view showing a part of an asset including at least one of a piping and a valve and a device;
A valve/equipment recognition device that acquires position information of the valve and the equipment from two-dimensional or three-dimensional image data of the asset;
a three-dimensional pattern matching device that identifies a position of the partial asset CAD model by pattern matching between the partial asset CAD model and a three-dimensional image of the asset, and creates an attributed asset CAD model by arranging the partial asset CAD model in a three-dimensional space;
The three-dimensional pattern matching device is a three-dimensional model creation support system that limits the range of the pattern matching from the position information of the valve and the equipment acquired by the valve/equipment recognition device and the relative position information of the valve and the equipment acquired from the partial asset CAD model. On the computer,
A step of creating a partial asset CAD model having attribute data using data of a perspective view showing a part of an asset;
A program for executing a procedure of identifying the position of the partial asset CAD model by pattern matching between the partial asset CAD model and a three-dimensional image of the asset, and creating an attributed asset CAD model by placing the partial asset CAD model in a three-dimensional space. On the computer,
A step of creating a partial asset CAD model having attribute data using data of a perspective view showing a part of an asset;
A computer-readable recording medium having recorded thereon a program for executing a procedure for identifying the position of the partial asset CAD model by pattern matching between the partial asset CAD model and a three-dimensional image of the asset, and creating an attributed asset CAD model by placing the partial asset CAD model in a three-dimensional space.

Images