A data-driven prediction method for ship energy consumption

A prediction method and data-driven technology, applied in special data processing applications, ship construction, ship design, etc., can solve problems such as inability to effectively evaluate and predict ship energy consumption, long cycle time, and complex influencing factors

Active Publication Date: 2021-09-10
HARBIN ENG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are several problems in the above methods: First, excessive reliance on the ship dynamics model, but due to the many links in the ship power energy conversion process and the complex influencing factors, it is difficult to establish an accurate mathematical model, and the model parameters have a great impact on the prediction effect of ship energy consumption , it is impossible to effectively evaluate and predict ship energy consumption; second, the mathematical models of different ships are different, and the method parameter settings of the energy consumption prediction process are also different, resulting in poor versatility of the energy consumption prediction method based on the ship dynamics model; Third, when predicting the energy consumption of a long route (such as a route with a voyage time of several days), the amount of calculation is huge, and the dynamic model has a long cycle of combining the test results to correct the model, sometimes it is difficult to meet the actual ship application requirements

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A data-driven prediction method for ship energy consumption
  • A data-driven prediction method for ship energy consumption
  • A data-driven prediction method for ship energy consumption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] Flow chart of the present invention is as figure 2 As shown, firstly, a desired route is given, which is composed of any number of waypoints, each waypoint contains latitude and longitude information, and the expected engine speed data of each route sub-segment needs to be set, and the entire navigation area needs different time Sea state information, including wave height, wave direction, wave cycle and other information, and specify the ship departure time for time synchronization with sea state information; then establish a high-dimensional matrix of the ship’s steady-state speed on the water, a high-dimensional matrix of engine power and The engine fuel consumption model is used to construct the offline basic model; a series of matrices of the offline basic model are used to complete the linearization of the model through high-dimensional linear interpolation; the energy consumption model is completed by setting the desired route and the linearization model Real-ti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of ship energy consumption prediction, and in particular relates to a data-driven ship energy consumption prediction method. The present invention includes obtaining the expected route, departure time and sea state information of the ship; constructing an offline basic model, including the ship's steady-state speed model on the water, the engine power model and the engine fuel consumption model; High-dimensional linear interpolation of the discrete grid matrix; one-dimensional linear interpolation of the discrete grid matrix of the engine fuel consumption model; real-time deduction of the ship energy consumption model. Supported by a set of data matrix, the present invention realizes fast calculation of energy consumption of a ship's long voyage. The data matrix in the method can be obtained in various ways, and it is convenient and quick to replace. The present invention does not affect the idea of ​​the original ship dynamics simulation model, and coexists with the dynamics simulation mode in the actual simulation verification evaluation system, and each is responsible for different types of simulation calculations.

Description

technical field [0001] The invention belongs to the technical field of ship energy consumption prediction, and in particular relates to a data-driven ship energy consumption prediction method. Background technique [0002] With the rapid development of my country's national economy, the pace of globalization in various fields is getting faster and faster. The construction of ship transportation is becoming more and more important to my country's society and economy. The energy consumption of ships is an important factor in the economy of ship transportation, which is directly related to ship transportation. At the same time, ship energy consumption has a greater impact on ship management efficiency and environmental pollution. Therefore, the research and analysis of ship energy consumption has important theoretical research and engineering practice significance, especially in the aspect of ship energy consumption prediction. Effective ship energy consumption prediction has br...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): B63B71/10B63B71/20B63B71/00G06F30/15G06F30/20
CPCB63B71/00B63B71/10B63B71/20G06F30/15G06F30/20G06F2111/10G06F2119/06
Inventor 王立鹏张智朱齐丹夏桂华苏丽王学武马文龙张佳鹏
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products