Intelligent energy efficiency management system and method for dredger

Abstract

The invention discloses an intelligent energy efficiency management system for a dredger. The intelligent energy efficiency management system comprises a data sensing layer used for collecting dredging related parameters through various sensors and monitoring equipment; the database layer is used for preprocessing, filtering and storing the dredging related parameters acquired by the data sensing layer; the decision-making layer is used for analyzing and evaluating the data in the energy efficiency analysis database and outputting auxiliary decision-making parameters; the application layer is used for visually displaying dredging related parameters and auxiliary decision-making data; and the user layer is used for setting user accounts according to different user roles, formulating different access permissions and management permissions and managing system control strategies. The energy efficiency intelligent analysis management of the whole ship is realized through an intelligent means, so that the construction energy consumption of the dredging ship is effectively reduced, and in the practical engineering application, the dredging operation ship is actually controlled by the aid of the decision-making parameters, and the measured oil consumption per ten thousand cubic meters is reduced by 2-4 tons.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent dredging, and in particular relates to an intelligent energy efficiency management system and method for a dredger. Background Art

[0002] The main task of a dredger is to carry out underwater earthwork construction, which mainly includes: deepening, widening and clearing existing waterways and ports, digging new waterways, ports and canals, dredging the foundation trenches of docks, shipyards, ship locks and other hydraulic structures, and throwing the excavated mud and sand into the deep sea or filling it in land depressions to create farmland. Unlike conventional ships, the energy consumption of dredgers is mainly in the construction process of the dredging ship, and is affected by external environmental factors and construction parameters. External environmental factors cannot be changed, and the adjustment of construction parameters becomes the main means to reduce the working energy consumption of dredgers.

[0003] In the prior art, during the operation of a dredger, construction parameters mainly rely on manual adjustment. However, in actual implementation, the manually adjusted construction parameters cannot enable the dredger to perform dredging operations with the lowest energy consumption. Therefore, when external environmental conditions cannot be changed, it has become an urgent problem to realize intelligent analysis and management of the energy efficiency of the entire ship through intelligent means, thereby effectively reducing the energy consumption of dredging ship construction. Summary of the invention

[0004] In order to realize intelligent analysis and management of the energy efficiency of the whole ship through intelligent means, thereby effectively reducing the energy consumption of dredging ship construction, the present invention provides the following technical solutions:

[0005] An intelligent energy efficiency management system for a dredger, characterized by comprising:

[0006] Data perception layer: used to collect dredging related parameters through various sensors and monitoring equipment;

[0007] Database layer: used to pre-process, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database;

[0008] Decision-making layer: used to analyze and evaluate the data in the energy efficiency analysis database and output auxiliary decision-making parameters;

[0009] Application layer: used to visualize dredging related parameters and auxiliary decision-making data;

[0010] User layer: used to set up user accounts according to different user roles, formulate different access rights and management rights, and manage system control policies.

[0011] Furthermore, the data perception layer includes a construction parameter perception module, an environmental parameter perception module, and a dredging energy efficiency perception module;

[0012] The construction parameter perception module is used to monitor and collect construction parameters, the environmental parameter perception module is used to monitor and collect environmental parameters, and the dredging energy efficiency perception module is used to monitor and collect dredging energy efficiency parameters.

[0013] Furthermore, the database layer is used to process, filter and store the construction parameters, environmental parameters and dredging energy efficiency parameters respectively to form construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors;

[0014] The database layer includes a data preprocessing module, a data filtering module and a data storage module;

[0015] The data preprocessing module is used to adjust the format and structure of parameters;

[0016] The data filtering module is used to remove invalid or erroneous parameters;

[0017] The data storage module is used to store the processed parameters according to the database structure to form an energy efficiency analysis database;

[0018] The energy efficiency analysis database includes construction parameter factors, environmental parameter factors and dredging energy efficiency factors after preprocessing and filtering.

[0019] Furthermore, the decision-making layer includes: an energy efficiency key factor determination module, an energy efficiency evaluation model establishment module, and an auxiliary decision-making data output module;

[0020] The energy efficiency key factor determination module is used to determine the environmental parameter key factor and the construction parameter key factor from the construction parameter factor and the environmental parameter factor;

[0021] The energy efficiency evaluation model establishment module is used to divide different working conditions according to key factors of environmental parameters, and establish an energy consumption prediction model that maps the relationship between key factors of construction parameters and dredging energy efficiency factors under different working conditions;

[0022] The auxiliary decision data output module is used to perform inverse calculation on the energy consumption prediction model to find auxiliary decision parameters.

[0023] Furthermore, the energy efficiency key factor determination module performs dimensionality reduction processing on the environmental parameter factors and construction parameter factors in the energy efficiency analysis database through the principal component analysis algorithm, and then calculates the correlation between the environmental parameter factors and the construction parameter factors and the dredging energy efficiency factors through the Pearson correlation coefficient algorithm, and outputs the influence of each environmental parameter factor and the construction parameter factor on the dredging energy efficiency factor in the form of percentage. The factors with the greatest influence on the dredging energy efficiency factor are the environmental parameter key factors and the construction parameter key factors;

[0024] Furthermore, the energy efficiency evaluation model establishment module divides the working conditions according to the key factors of environmental parameters determined by the key factors of energy efficiency determination module, and establishes an energy consumption prediction model that maps the relationship between the key factors of construction parameters and the dredging energy efficiency factors under different working conditions through the deep learning Transformer algorithm.

[0025] The auxiliary decision data output module performs inverse calculation on the energy consumption prediction model through a particle swarm optimization algorithm to find the global optimal energy efficiency construction parameters of the energy consumption prediction model, which are the auxiliary decision parameters.

[0026] Furthermore, the dredging energy efficiency factor is the fuel consumption per 10,000 cubic meters of soil.

[0027] Furthermore, the application layer includes a report generation module and a visualization display module;

[0028] The report generation module generates energy consumption reports and periodic reports based on statistical calculations of dredging related parameters monitored by the data perception layer;

[0029] The energy consumption report includes statistics on energy consumption, time, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and fuel consumption per 10,000 cubic meters of soil under different working conditions.

[0030] The periodic report counts energy consumption, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and fuel consumption per 10,000 cubic meters of soil in different time periods;

[0031] The visual display module is used to display the energy consumption report and cycle report generated by the report calculation module, and the auxiliary decision parameters generated by the auxiliary decision data output module.

[0032] Furthermore, the user layer includes browsing users, construction users and system administrators, wherein browsing users only have browsing permissions, construction users can set and operate construction-related parts of the system, and system administrators have the highest permissions and can set and operate the entire system.

[0033] An intelligent energy efficiency management method for a dredger comprises the following steps:

[0034] S1-Data Awareness:

[0035] Collect dredging related parameters through various sensors and monitoring equipment;

[0036] The dredging related parameters include construction parameters, environmental parameters and dredging energy efficiency parameters;

[0037] S2-Database creation:

[0038] Preprocess, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database including construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors;

[0039] S3-Key Factor Determination:

[0040] Combining the principal component analysis algorithm and the Pearson correlation coefficient algorithm, the key factors of environmental parameters and construction parameters that have a great impact on the dredging energy efficiency factor are determined;

[0041] S4-Working Condition Division:

[0042] According to the key factors of different environmental parameters, the ship is divided into different working conditions;

[0043] S5-Model Building:

[0044] Under each working condition, an energy consumption prediction model is established to map the key factors of environmental parameters and dredging energy efficiency factors;

[0045] S6-Decision support:

[0046] Perform inverse calculation on the energy consumption prediction model to find its global optimal energy efficiency construction parameters, which are auxiliary decision-making parameters;

[0047] S7-Dredging Control:

[0048] The auxiliary decision parameters are used to control the dredging of ships.

[0049] The present invention realizes intelligent analysis and management of the energy efficiency of the whole ship through intelligent means, thereby effectively reducing the energy consumption of dredging ship construction. In actual engineering applications, auxiliary decision-making parameters are used to actually control the dredging operation ship, and it is measured that the fuel consumption per 10,000 cubic meters of soil is reduced by 2-4 tons, which varies according to different working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the overall structure of the intelligent energy efficiency management system for dredgers of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention is described clearly and completely with specific embodiments in conjunction with the accompanying drawings. It should be understood that the described embodiments are only used to illustrate the present invention, but not to limit the scope of the present invention.

[0052] Embodiment 1: An intelligent energy efficiency management system for dredgers, according to Figure 1 As shown, including:

[0053] Data perception layer: used to collect dredging related parameters through various sensors and monitoring equipment;

[0054] Database layer: used to pre-process, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database;

[0055] Decision-making layer: used to analyze and evaluate the data in the energy efficiency analysis database and output auxiliary decision-making parameters;

[0056] Application layer: used to visualize dredging related parameters and auxiliary decision-making data;

[0057] User layer: used to set user accounts according to different user roles, formulate different access rights and management rights, manage system control policies, and maintain system access security.

[0058] Furthermore, the data perception layer includes a construction parameter perception module, an environmental parameter perception module, and a dredging energy efficiency perception module;

[0059] The construction parameter sensing module is used to monitor and collect construction parameters;

[0060] The environmental parameter sensing module is used to monitor and collect environmental parameters;

[0061] The dredging energy efficiency sensing module is used to monitor and collect dredging energy efficiency parameters;

[0062] The dredging energy efficiency parameter in this embodiment is the fuel consumption per 10,000 cubic meters of soil W d ; The oil consumption of 10,000 cubic meters of soil W d The calculation formula is as follows:

[0063]

[0064] Among them, t0 represents the start time of dredging, t represents the current time, C represents the fuel consumption in the time period t-t0, and V represents the earthwork volume in the time period t-t0;

[0065] Furthermore, the construction parameters vary according to different types of dredging vessels;

[0066] For example, the construction parameters of a trailing suction dredger include: depth of the dredger head, speed, mud pump speed, high-pressure flushing pump speed, mud concentration, tank capacity, etc.; the construction parameter factors of a cutter suction dredger include: auger depth, auger speed, auger power, traverse speed, mud pump speed, mud concentration, etc.

[0067] The environmental parameters include: flow direction, wind speed and dredged soil quality of the construction waters.

[0068] Furthermore, the database layer is used to process, filter and store the construction parameters, environmental parameters and dredging energy efficiency parameters respectively to form construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors;

[0069] The database layer includes a data preprocessing module, a data filtering module and a data storage module;

[0070] The data preprocessing module is used to adjust the format and structure of the parameters to ensure the consistency of the parameters;

[0071] The data filtering module is used to remove invalid or erroneous parameters, such as values ​​outside the normal range, parameters with incorrect format, etc.;

[0072] The data storage module is used to store the processed parameters according to the database structure to ensure the queryability and maintainability of the data and form an energy efficiency analysis database;

[0073] The energy efficiency analysis database includes construction parameter factors, environmental parameter factors and dredging energy efficiency factors after preprocessing and filtering;

[0074] Furthermore, the decision-making layer includes: an energy efficiency key factor determination module, an energy efficiency evaluation model establishment module, and an auxiliary decision-making data output module;

[0075] The energy efficiency key factor determination module is used to determine the environmental parameter key factor and the construction parameter key factor from the construction parameter factor and the environmental parameter factor;

[0076] The energy efficiency evaluation model establishment module is used to divide different working conditions according to key factors of environmental parameters, and establish an energy consumption prediction model that maps the relationship between key factors of construction parameters and dredging energy efficiency factors under different working conditions;

[0077] The auxiliary decision-making data output module is used to perform inverse calculation on the energy consumption prediction model to find the optimal energy-efficient construction parameters with the lowest oil consumption per 10,000 cubic meters of soil as auxiliary decision-making parameters.

[0078] Furthermore, the energy efficiency key factor determination module performs dimensionality reduction processing on the environmental parameter factors and construction parameter factors in the energy efficiency analysis database through the principal component analysis algorithm, and then calculates the correlation between the environmental parameter factors and the construction parameter factors and the dredging energy efficiency factors through the Pearson correlation coefficient algorithm, and outputs the influence of each environmental parameter factor and the construction parameter factor on the dredging energy efficiency factor in the form of percentage. The environmental parameter key factors and the construction parameter key factors with the greatest influence on the dredging energy efficiency factor are the environmental parameter key factors and the construction parameter key factors;

[0079] Preferably, in this embodiment, the environmental parameter factors and construction parameter factors that have an impact on the dredging energy efficiency factor of more than 60% are used as environmental parameter key factors and construction parameter key factors; the principal component analysis algorithm and Pearson correlation coefficient algorithm are both algorithms that have been disclosed in the prior art and will not be described in detail.

[0080] Furthermore, the energy efficiency evaluation model establishment module divides the working conditions according to the key factors of the environmental parameters determined by the energy efficiency key factor determination module, and establishes an energy consumption prediction model that maps the relationship between the key factors of the construction parameters and the oil consumption of 10,000 cubic meters under different working conditions through the deep learning Transformer algorithm.

[0081] Furthermore, the auxiliary decision data output module performs inverse calculation on the energy consumption prediction model through a particle swarm optimization algorithm to find the global optimal energy efficiency construction parameters of the energy consumption prediction model, that is, the construction parameters with the minimum oil consumption per 10,000 cubic meters of soil, as auxiliary decision parameters.

[0082] Furthermore, the application layer includes a report generation module and a visualization display module;

[0083] The report generation module generates energy consumption reports and periodic reports based on statistical calculations of dredging related parameters monitored by the data perception layer;

[0084] The energy consumption report includes statistics on energy consumption, time, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and fuel consumption per 10,000 cubic meters of soil under different working conditions.

[0085] The periodic report counts energy consumption, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and oil consumption per 10,000 cubic meters of soil in different time periods. The generation of the energy consumption report and the periodic report are already disclosed in the prior art and will not be described in detail.

[0086] The visual display module is used to display the energy consumption report and cycle report generated by the report calculation module, and the auxiliary decision parameters generated by the auxiliary decision data output module.

[0087] Furthermore, the user layer includes browsing users, construction users and system administrators, wherein browsing users only have browsing permissions, construction users can set and operate construction-related parts of the system, and system administrators have the highest permissions and can set and operate the entire system.

[0088] An intelligent energy efficiency management method for a dredger comprises the following steps:

[0089] S1-Data Awareness:

[0090] Collect dredging related parameters through various sensors and monitoring equipment;

[0091] The dredging related parameters include construction parameters, environmental parameters and dredging energy efficiency parameters;

[0092] S2-Database creation:

[0093] Preprocess, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database including construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors;

[0094] S3-Key Factor Determination:

[0095] Combining the principal component analysis algorithm and the Pearson correlation coefficient algorithm, the key factors of environmental parameters and construction parameters that have a great impact on the dredging energy efficiency factor are determined;

[0096] S4-Working Condition Division:

[0097] According to the key factors of different environmental parameters, the ship is divided into different working conditions;

[0098] S5-Model Building:

[0099] Under each working condition, an energy consumption prediction model is established to map the key factors of environmental parameters and dredging energy efficiency factors;

[0100] S6-Decision support:

[0101] Perform inverse calculation on the energy consumption prediction model to find its global optimal energy efficiency construction parameters, which are auxiliary decision-making parameters;

[0102] S7-Dredging Control:

[0103] The auxiliary decision parameters are used to control the dredging of ships.

[0104] Example 2: Engineering example of the intelligent energy efficiency management system for dredgers based on Example 1:

[0105] 1. Implementation process:

[0106] First, various sensors and monitoring equipment are used to collect construction parameters, environmental parameters and dredging energy efficiency parameters; the construction parameters in this project example include earthwork volume, speed, suction vacuum, discharge pressure, wave compensator height, high-pressure flushing pump speed, drag head angle to the ground, drag head depth; environmental parameters include average draft, water flow rate, mud concentration, and oil consumption per 10,000 cubic meters of earth is used as the dredging energy efficiency parameter;

[0107] Secondly, the principal component analysis algorithm and the Pearson correlation coefficient algorithm are used to calculate the correlation between the environmental parameters and the construction parameters and the dredging energy efficiency parameters, and the influence of the environmental parameter factors and the construction parameter factors on the dredging energy efficiency factors is output in percentage form. The influence of each factor on the fuel consumption of 10,000 cubic meters of soil in this engineering example is shown in Table 1 below:

[0108] Table 1 - The influence of various factors on the fuel consumption of 10,000 cubic meters of soil

[0109]

[0110]

[0111] Finally, through the deep learning Transformer algorithm, an energy consumption prediction model mapping construction parameters and 10,000 cubic meters of soil and oil consumption is established, and the energy consumption prediction model is inversely calculated through the particle swarm optimization algorithm (PSO) to find its global optimal energy-efficient construction parameters as auxiliary decision-making parameters to assist dredging control.

[0112] 2. Beneficial effects:

[0113] The auxiliary decision parameters are used to actually control the dredging operation ship. In this engineering example, it is measured that the fuel consumption per 10,000 cubic meters of soil is reduced by 2-4 tons, which varies according to different working conditions.

[0114] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention are within the scope of the technical solution of the present invention.

Claims

1. An intelligent energy efficiency management system for dredgers, characterized in that: include: Data perception layer: used to collect dredging related parameters through various sensors and monitoring equipment; Database layer: used to pre-process, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database; Decision-making layer: used to analyze and evaluate the data in the energy efficiency analysis database and output auxiliary decision-making parameters; Application layer: used to visualize dredging related parameters and auxiliary decision-making data; User layer: used to set up user accounts according to different user roles, formulate different access rights and management rights, and manage system control policies.

2. The intelligent energy efficiency management system for dredgers according to claim 1 is characterized in that: The data perception layer includes a construction parameter perception module, an environmental parameter perception module, and a dredging energy efficiency perception module; The construction parameter perception module is used to monitor and collect construction parameters, the environmental parameter perception module is used to monitor and collect environmental parameters, and the dredging energy efficiency perception module is used to monitor and collect dredging energy efficiency parameters.

3. The intelligent energy efficiency management system for dredgers according to claim 2 is characterized in that: The database layer is used to process, filter and store the construction parameters, environmental parameters and dredging energy efficiency parameters respectively to form construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors; The database layer includes a data preprocessing module, a data filtering module and a data storage module; The data preprocessing module is used to adjust the format and structure of parameters; The data filtering module is used to remove invalid or erroneous parameters; The data storage module is used to store the processed parameters according to the database structure to form an energy efficiency analysis database; The energy efficiency analysis database includes construction parameter factors, environmental parameter factors and dredging energy efficiency factors after preprocessing and filtering.

4. The intelligent energy efficiency management system for dredgers according to claim 3 is characterized in that: The decision-making layer includes: an energy efficiency key factor determination module, an energy efficiency evaluation model establishment module and an auxiliary decision-making data output module; The energy efficiency key factor determination module is used to determine the environmental parameter key factor and the construction parameter key factor from the construction parameter factor and the environmental parameter factor; The energy efficiency evaluation model establishment module is used to divide different working conditions according to key factors of environmental parameters, and establish an energy consumption prediction model that maps the relationship between key factors of construction parameters and dredging energy efficiency factors under different working conditions; The auxiliary decision data output module is used to perform inverse calculation on the energy consumption prediction model to find auxiliary decision parameters.

5. The intelligent energy efficiency management system for dredgers according to claim 4 is characterized in that: The energy efficiency key factor determination module performs dimensionality reduction processing on the environmental parameter factors and construction parameter factors in the energy efficiency analysis database through the principal component analysis algorithm, and then calculates the correlation between the environmental parameter factors and the construction parameter factors and the dredging energy efficiency factors respectively through the Pearson correlation coefficient algorithm, and outputs the influence of each environmental parameter factor and the construction parameter factor on the dredging energy efficiency factor in the form of percentage. The factors with the greatest influence on the dredging energy efficiency factor are the environmental parameter key factors and the construction parameter key factors.

6. The intelligent energy efficiency management system for dredgers according to claim 5 is characterized in that: The energy efficiency evaluation model establishment module divides the working conditions according to the key factors of environmental parameters determined by the key factors of energy efficiency determination module, and establishes an energy consumption prediction model that maps the relationship between the key factors of construction parameters and the dredging energy efficiency factors under different working conditions through a deep learning Transformer algorithm. The auxiliary decision data output module performs inverse calculation on the energy consumption prediction model through a particle swarm optimization algorithm to find the global optimal energy efficiency construction parameters of the energy consumption prediction model, which are the auxiliary decision parameters.

7. The intelligent energy efficiency management system for dredgers according to claim 3 is characterized in that: The dredging energy efficiency factor is the fuel consumption per 10,000 cubic meters of soil.

8. The intelligent energy efficiency management system for dredgers according to claim 1 is characterized in that: The application layer includes a report generation module and a visual display module; The report generation module generates energy consumption reports and periodic reports based on statistical calculations of dredging related parameters monitored by the data perception layer; The energy consumption report includes statistics on energy consumption, time, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and fuel consumption per 10,000 cubic meters of soil under different working conditions. The periodic report counts energy consumption, sailing distance, energy consumption per unit time, energy consumption per unit nautical mile, output, and fuel consumption per 10,000 cubic meters of soil in different time periods; The visual display module is used to display the energy consumption report and cycle report generated by the report calculation module, and the auxiliary decision parameters generated by the auxiliary decision data output module.

9. The intelligent energy efficiency management system for dredgers according to claim 1, characterized in that: The user layer includes browsing users, construction users and system administrators, wherein browsing users only have browsing permissions, construction users can set and operate construction-related parts of the system, and system administrators have the highest permissions and can set and operate the entire system.

10. A dredging vessel intelligent energy efficiency management method, comprising the following steps: S1-Data Awareness: Collect dredging related parameters through various sensors and monitoring equipment; The dredging related parameters include construction parameters, environmental parameters and dredging energy efficiency parameters; S2-Database creation: Preprocess, filter and store the dredging related parameters collected by the data perception layer to form an energy efficiency analysis database including construction parameter factors, environmental parameter factors and dredging energy efficiency parameter factors; S3-Key Factor Determination: Combining the principal component analysis algorithm and the Pearson correlation coefficient algorithm, the key factors of environmental parameters and construction parameters that have a great impact on the dredging energy efficiency factor are determined; S4-Working Condition Division: Different working conditions of ships are divided according to key factors of different environmental parameters; S5-Model Building: Under each working condition, an energy consumption prediction model is established to map the key factors of environmental parameters and dredging energy efficiency factors; S6-Decision support: Perform inverse calculation on the energy consumption prediction model to find its global optimal energy efficiency construction parameters, which are auxiliary decision-making parameters; S7-Dredging Control: The auxiliary decision parameters are used to control the dredging of ships.

Images