Estimation method, training method, storage medium, and estimation device

Patent metadata

Field	Value
Publication number	US-11352105-B2
Application number	US-202016984318-A
Country	US
Kind code	B2
Filing date	Aug 4, 2020
Priority date	Aug 14, 2019
Publication date	Jun 7, 2022
Grant date	Jun 7, 2022

Abstract

An estimation method executed by a computer, the estimation method includes estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship; selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and generating the machine learning model based on the selected training data.

First claim

What is claimed is:

1. An estimation method executed by a computer, the estimation method comprising:
estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship;
selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and
generating the machine learning model based on the selected training data,
wherein the accumulation period includes a period in which a time during which navigation at a speed lower than a predetermined navigation speed was kept is accumulated.

2. The estimation method according to claim 1 , wherein the estimation method comprising using the generated machine learning model to estimate the amount of fuel consumption of the target ship according to constraint conditions that relate to the target ship; and the accumulation period includes a period in which a berthing time is accumulated.

3. The estimation method according to claim 1 , wherein the estimating process includes the fouling degree estimates the fouling degree by performing weighting according to a seawater temperature in the accumulation period.

4. The estimation method according to claim 1 , wherein a search for a route of the target ship is made based on the estimated amount of fuel consumption, and the found route is output.

5. A training method executed by a computer, the training method comprising:
estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship;
selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and
generating the machine learning model based on the selected training data,
wherein the accumulation period includes a period in which a time during which navigation at a speed lower than a predetermined navigation speed was kept is accumulated.

6. A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process comprising:
estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship;
selecting one piece of training data that has a fouling degree that resembles the estimated fouling degree, from among a plurality pieces of training data; and
generating a machine learning model for estimating an amount of fuel consumption due to navigation, based on the selected training data,
wherein the accumulation period includes a period in which a time during which navigation at a speed lower than a predetermined navigation speed was kept is accumulated.

7. An estimation device, comprising: a memory; and a processor coupled to the memory and the processor configured to: estimate a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship, select one piece of training data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of training data; and generate a machine learning model for estimating an amount of fuel consumption due to navigation, based on the selected training data,
wherein the accumulation period includes a period in which a time during which navigation at a speed lower than a predetermined navigation speed was kept is accumulated.

8. The estimation device according to claim 7 , wherein the accumulation period includes a period in which a berthing time is accumulated.

9. The estimation device according to claim 7 , wherein the processor is configured to estimate the fouling degree includes processing of estimating the fouling degree by performing weighting according to a seawater temperature in the accumulation period.

10. The estimation device according to claim 7 , wherein a search for a route of the target ship is made based on the estimated amount of fuel consumption, and the found route is output.

Assignees

• Fujitsu Ltd

Inventors

• Umemiya Shigeyoshi
• Yamaumi Masashi
• Ikeda Takuro

Classifications

• B63B59/04

  Preventing hull fouling (anti-fouling paints C09D5/16) · CPC title

• G06N20/00

  Machine learning · CPC title

• B63B79/30 Primary

  for diagnosing, testing or predicting the integrity or performance of vessels · CPC title

• B63B59/00 Primary

  Hull protection specially adapted for vessels; Cleaning devices specially adapted for vessels {(inhibiting corrosion of metals by anodic or cathodic protection C23F13/00)} · CPC title

• B63B79/20

  using models or simulation, e.g. statistical models or stochastic models · CPC title