KR20240061527A - High Density Polyethylene Vessel Life Prediction Apparatus and Method thereof - Google Patents

Abstract

The present invention proposes a device and method for determining the degree of damage and predicting the lifespan of ships built with high-density polyethylene (HDPE) material. The life prediction device of the present invention includes an input model that receives an image of high-density polyethylene damaged by exposure to ultraviolet rays, a judgment model that determines the degree of damage to the high-density polyethylene based on the input image of the high-density polyethylene, and a judgment result. Accordingly, it is configured to include a prediction model that predicts life information of the high-density polyethylene.

Description

High Density Polyethylene Vessel Life Prediction Apparatus and Method thereof}

The present invention relates to a device and method that can determine the degree of damage and predict the lifespan of a ship built with high-density polyethylene (HDPE) material using machine learning.

Recently, as the problem of global warming has become more serious worldwide, interest in green ship technology is high. Existing hulls of small and medium-sized ships and leisure ships are manufactured using fiber-reinforced composite materials to reduce weight and secure mobility. However, it is not easy to secure process technology to improve manufacturing productivity, and in particular, there is a problem in solving the environmental pollution problem that occurs when ship hulls are dismantled.

Accordingly, a plan to manufacture ships using high-density polyethylene (HDPE) material has recently been proposed. High-density polyethylene is 100% reusable, and it is a lightweight material that reduces greenhouse gas emissions from ships through fuel savings. In addition, high profits can be expected when the ship is dismantled, allowing the initial purchase cost to be recovered and contributing to the prevention of marine environmental pollution.

Shipbuilding using high-density polyethylene materials is also consistent with domestic and international carbon neutral policies. Accordingly, there has been an increasing trend in recent years to build ships using high-density polyethylene materials. For example, Prior Document 1 (Korean Patent No. 10-2238643) involves constructing a watertight bulkhead of a ship using high-density polyethylene, while Prior Document 2 (No. 10-2022-0039538) uses non-recyclable fiber-reinforced plastic (FRP). It is a structure that builds ships using polyethylene materials to solve the shortcomings of fishing boats built with aluminum materials, which have weaknesses in ship cost and maintenance.

However, the above-mentioned prior literature only builds ships using high-density polyethylene materials and does not disclose any structure for detecting damage to such high-density polyethylene materials.

As is well known, high-density polyethylene has the disadvantage of being very vulnerable to sunlight due to its weather resistance. In other words, when a polymer is exposed to UV rays, the polymer chain is cut and the oxidized substances generated from this react to reduce the crystallinity of the polymer, thereby reducing the strength of the polymer. For example, Figure 1 is a diagram showing an example of changes in high-density polyethylene material due to exposure to ultraviolet rays. Looking at this, (a) is a picture showing the first high-density polyethylene, and (b) is a picture after exposure to ultraviolet rays for about 500 hours. It can be seen that changes occur as the exposure time to ultraviolet rays increases.

Therefore, recently, products with improved resistance to sunlight have been released by adding highly UV-stable carbon black or antioxidant substances to high-density polyethylene, and these products are being used as building materials for ships, etc.

However, because ships are still built only with high-density polyethylene, it has been difficult to accurately determine the extent of damage to ships built with high-density polyethylene. Therefore, it was not possible to properly handle ship maintenance and prevent the problem of increased economic and time costs due to repairs after the ship was damaged.

Korean Patent No. 10-2238643 (2021. 04. 05) Korean Patent Publication No. 10-2022-0039538 (2022. 03. 29)

The purpose of the present invention was to solve the above problems, and to determine the degree of damage (corrosion, etc.) to high-density polyethylene caused by ultraviolet rays, and to provide a method for predicting the lifespan of ships built with high-density polyethylene material. .

Another object of the present invention is to provide a method for easily managing the maintenance of a ship by predicting its lifespan.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

To achieve this purpose, a life prediction device for a high-density polyethylene ship according to an embodiment of the present invention includes an input model that receives an image of high-density polyethylene damaged by exposure to ultraviolet rays (UV); A judgment model that determines the degree of damage to the high-density polyethylene based on the input image of the high-density polyethylene; and a prediction model that predicts lifespan information of the high-density polyethylene according to the judgment result.

According to this embodiment, the judgment model and prediction model may be performed using machine learning, and the machine learning may be a convolutional neural network (CNN).

According to this embodiment, it may further include an image table that stores images of the high-density polyethylene that is damaged depending on the time of exposure to ultraviolet rays.

According to this embodiment, the image table may further include information on the degree of UV damage and life expectancy of the high-density polyethylene.

A method for predicting the lifespan of a high-density polyethylene ship according to another embodiment of the present invention includes receiving image information of high-density polyethylene used in ship construction; Identifying the degree of damage by machine learning the image information of the high-density polyethylene; And a step of predicting the lifespan of the ship according to the degree of damage.

According to this embodiment, the machine learning uses a convolutional neural network (CNN).

According to this embodiment, the convolutional neural network (CNN) performs three convolution operations and two max pooling operations.

According to this embodiment, the step of measuring the hardness value by exposing a high-density polyethylene specimen of a predetermined size to ultraviolet rays at regular intervals may be included.

According to this embodiment, the step of determining the degree of damage may further include matching a damaged image of the high-density polyethylene according to the hardness value and determining the degree of damage of the high-density polyethylene based on the hardness value. .

According to the present invention, the lifespan of a ship can be predicted and active repair and management can be performed, thereby ensuring the reliability of high-density polyethylene ships.

According to the present invention, high-density polyethylene is 100% reusable and is a lightweight material, which has the effect of reducing greenhouse gas emissions through fuel savings.

According to the present invention, the initial purchase cost of a high-density polyethylene ship can be recovered when the ship is dismantled, and it has the effect of contributing to the prevention of marine environmental pollution.

According to the present invention, the lifespan can be predicted by applying to ships that can be built using high-density polyethylene material, and the effect of facilitating maintenance and repair of ships, etc. and preventing marine accidents can be expected.

Figure 1 is a diagram showing an example of changes in high-density polyethylene material due to exposure to ultraviolet rays.
Figure 2 is a configuration diagram of a high-density polyethylene ship life prediction device according to an embodiment of the present invention.
Figure 3 is a diagram showing a learning model that classifies the degree of damage to high-density polyethylene material using a convolutional neural network according to an embodiment of the present invention.
Figure 4 is a flowchart illustrating a method for predicting the lifespan of a high-density polyethylene ship according to the first embodiment of the present invention.
Figure 5 is a flowchart illustrating a method for predicting the lifespan of a high-density polyethylene ship according to a second embodiment of the present invention.

Since the present invention can be modified in various ways and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all transformations, equivalents, and substitutes included in the spirit and technical scope of the present invention. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

The terms used in the present invention are only used to describe specific embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Spatially relative terms such as below, beneath, lower, above, upper, etc. facilitate the correlation between one element or component and other elements or components as shown in the drawing. It can be used to describe. Spatially relative terms should be understood as terms that include different directions of the element during use or operation in addition to the direction shown in the drawings. For example, when an element shown in a drawing is turned over, an element described as below (below, beneath) another element may be placed above (upper) the other element. Accordingly, the illustrative term below may include both downward and upward directions. Elements can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

As used in the present invention, expressions indicating a part such as “part” or “part” mean that the corresponding component is a device that can include a specific function, software that can include a specific function, or a device that can include a specific function. It means that it can represent a combination of and software, but it cannot be said that it is necessarily limited to the expressed functions. This is only provided to help a more general understanding of the present invention, and is provided to those with ordinary knowledge in the field to which the present invention pertains. Various modifications and variations are possible from this description.

Accordingly, the spirit of the present invention should not be limited to the described embodiments, and the scope of the patent claims described below as well as all things that are equivalent or equivalent to the scope of this patent claim shall fall within the scope of the spirit of the present invention. .

Hereinafter, the present invention will be described in more detail based on the embodiments shown in the drawings.

Figure 2 is a configuration diagram of a high-density polyethylene ship life prediction device according to an embodiment of the present invention.

Referring to FIG. 2, the lifespan prediction device 10 may be configured to include an input model 100, a judgment model 200, and a prediction model 300.

The input model 100 is a model that receives an image of high-density polyethylene caused by ultraviolet rays (UV). Here, the image could be part of an actual ship built from high-density polyethylene.

The judgment model 200 is a model that determines the degree of damage to high-density polyethylene based on the input image of the high-density polyethylene. The judgment model 200 determines the degree of damage by performing machine learning on the image of the high-density polyethylene. According to this embodiment, machine learning for the judgment model can use a convolutional neural network (CNN). An explanation of the convolutional neural network will be discussed with reference to Figure 3 below.

As another example of the judgment model 200, an image of high-density polyethylene damaged by ultraviolet rays may be provided. At this time, the damaged high-density polyethylene must consider the ultraviolet ray exposure time, and provide damage information of the high-density polyethylene for each ultraviolet ray exposure time, so that the input model 100 can accurately learn the degree of damage to the high-density polyethylene only from the input image.

The prediction model 300 is a model that predicts the lifespan of a ship based on the degree of damage to high-density polyethylene by the judgment model 200. To predict the lifespan of a ship, additional information can be provided that provides the expected lifespan (usable time) of the ship depending on the degree of damage to the high-density polyethylene.

Figure 3 is a diagram showing a learning model that classifies the degree of damage to high-density polyethylene material using a convolutional neural network according to an embodiment of the present invention.

Referring to Figure 3, images of high-density polyethylene damaged by ultraviolet rays are provided, as shown in Figure 3(a). These images may have different degrees of damage due to different exposure times to ultraviolet rays.

In Figure 3(b), the convolutional neural network determines the degree of damage to high-density polyethylene using the images.

The convolutional neural network applied in this embodiment may include one image patch layer, two hidden layers (first hidden layer/second hidden layer), and a final layer. And these layers perform the first to third convolution operations and the first and second max pooling operations located between the convolution operations. By performing the above computational process, the convolutional neural network provides the degree of damage to high-density polyethylene. For example, as shown in Figure 3(c), the degree of damage can be classified from 1 to 10.

In this embodiment, the lifespan of a ship built with high-density polyethylene material can be predicted using this damage level information.

Figure 4 is a flowchart explaining a method for predicting the lifespan of a high-density polyethylene ship according to the first embodiment of the present invention.

In the first embodiment of the present invention, an image of a high-density polyethylene material according to the time of exposure to ultraviolet rays, information on the degree of damage corresponding to the image, and information on predicting the lifespan of the ship according to the damage may be provided in a table form (S100) . And, for example, this table format can be organized as shown in [Table 1].

HDPE image (image based on UV exposure time) degree of damage life expectancy One 3 to 6 months 2 1 to 2 years .
.
. .
.
. .
.
. 10 Within 3 years

The input model 100 receives an image of high-density polyethylene (S110). The high-density polyethylene image may be an image taken directly of a predetermined part of the ship if the image shown in Table 1 above can be obtained through a specific photographic means, or it may be an image taken with an electron microscope, etc. by acquiring a specimen of a predetermined part. . And the images are at least two of the ships. For example, it may be the stern, stern, hull, deck, etc. of a ship.

The image of the ship received by the input model 100 is transmitted to the judgment model 200. The judgment model 200 performs machine learning using a convolutional neural network and determines the degree of damage according to the machine learning results (S120). At this time, it is also possible to determine the degree of damage using [Table 1] without performing machine learning. And the degree of damage is provided correspondingly for each image, as shown in [Table 1] above.

The prediction model 300 predicts the lifespan of the ship according to the degree of damage identified by the judgment model 200 (S130) and provides the prediction to the ship owner (user). At this time, the predicted lifespan information of the ship may be the entire ship or a part of the ship. Therefore, the shipowner can maintain the entire ship or only a part of it that has reached its end of life.

Figure 5 is a flowchart illustrating a method for predicting the lifespan of a high-density polyethylene ship according to a second embodiment of the present invention.

The second embodiment is a method of predicting the lifespan of a ship using only machine learning. That is, table information such as [Table 1] of the first embodiment described above is not required.

In the life prediction method, the input model (100) receives an image of high-density polyethylene (S200). Similarly to the first embodiment, the high-density polyethylene image may be an image taken directly of a predetermined part of the ship, or an image taken with an electron microscope, etc. by obtaining a specimen of a predetermined part, and may be a part of the ship.

The input model 100 transmits the input image to the judgment model 200.

Then, the judgment model 200 performs machine learning using artificial intelligence such as the convolutional neural network described in FIG. 3. Specifically, the judgment model trains high-density polyethylene images through machine learning, and determines the degree of damage to high-density polyethylene as a result of this machine learning (S210). The degree of damage can be divided into several levels depending on the training results.

When information on the degree of damage is provided by the judgment model 200, the prediction model 300 performs machine learning on the degree of damage and predicts the lifespan information of the image provided as a result (S220). Predicted lifespan information is provided to ship owners (users). The ship owner can maintain the ship based on the life information provided in this way.

Meanwhile, the present invention can conveniently predict the lifespan of a ship by providing a computer-readable recording medium on which a program for executing the method for predicting the lifespan of a ship shown in FIGS. 4 and 5 is recorded.

As described above, the present invention can identify the degree of damage to ships built with high-density polyethylene material and predict the lifespan of the ship according to the degree of damage, thereby facilitating maintenance of the ship.

As described above, the present invention is described with reference to the illustrated embodiments, but these are merely illustrative examples, and those of ordinary skill in the art to which the present invention pertains can make various modifications without departing from the gist and scope of the present invention. It will be apparent that variations, modifications, and equivalent other embodiments are possible. Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the attached claims.

100: input model
200: Judgment model
300: Prediction model

Claims (10)

An input model that receives images of high-density polyethylene damaged by exposure to ultraviolet (UV) rays;
A judgment model that determines the degree of damage to the high-density polyethylene based on the input image of the high-density polyethylene; and
A high-density polyethylene ship life prediction device, characterized in that it includes a prediction model that predicts life information of the high-density polyethylene according to the judgment result. According to paragraph 1,
The judgment model and prediction model can be performed using machine learning,
The machine learning is a convolutional neural network (CNN), a high-density polyethylene ship life prediction device. According to paragraph 1,
A life prediction device for a high-density polyethylene ship, which may further include an image table for storing images of the high-density polyethylene damaged depending on the time of exposure to ultraviolet rays. According to paragraph 3,
The image table is,
A life prediction device for a high-density polyethylene ship, which may further include the degree of UV damage and life prediction information of the high-density polyethylene. Receiving image information of high-density polyethylene used in ship construction;
Identifying the degree of damage by machine learning the image information of the high-density polyethylene; and
A method for predicting the lifespan of a high-density polyethylene ship, comprising the step of predicting the lifespan of the ship according to the degree of damage. According to clause 5,
The machine learning is a method of predicting the lifespan of a high-density polyethylene ship using a convolutional neural network (CNN). According to clause 6,
The convolutional neural network (CNN) is a method for predicting the lifespan of a high-density polyethylene ship, which performs three convolution operations and two max pooling operations. According to clause 5,
A method for predicting the lifespan of a high-density polyethylene ship, further comprising measuring the hardness value by exposing a high-density polyethylene specimen of a predetermined size to ultraviolet rays at regular intervals. According to clause 5,
The step of determining the degree of damage further includes matching a damaged image of the high-density polyethylene according to the hardness value and determining the degree of damage to the high-density polyethylene based on the hardness value. Method for predicting the lifespan of a high-density polyethylene ship. . A computer-readable recording medium on which a computer program for performing the method according to any one of claims 5 to 9 is recorded on a computer.

Images