Dredger energy efficiency calculation method based on energy efficiency analysis and evaluation model

Abstract

The present invention relates to the technical field of dredger energy efficiency monitoring, and disclosed is a dredger energy efficiency calculation method based on an energy efficiency analysis and evaluation model. The present invention solves the problem of inaccurate evaluation of dredger energy efficiency caused by errors in existing dredger energy efficiency calculation methods. The method comprises: automatically collecting and monitoring parameters of main energy-consuming devices such as a main engine, an auxiliary engine and a boiler, and a dredging shaft power device of a dredger, a CO2 emission, and a dredger water area environment, and establishing an energy efficiency analysis database; introducing a correlation analysis algorithm to analyze the correlation of various factors, so as to obtain the degree of correlation between various parameters; on the basis of the type of the dredger, separately constructing a trailing suction hopper dredger energy efficiency evaluation model and a cutter suction dredger energy efficiency evaluation model; and for a single voyage, taking the oil consumption per 10,000 cubic meters of soil under various operating conditions as an optimization objective of the energy efficiency evaluation model, and establishing a dredger energy consumption evaluation level on the basis of the optimization objective, thereby providing energy efficiency-assisted decision-making for dredging operations, and thus completing an intelligent energy efficiency management system.

Description

Energy Efficiency Calculation Method for Dredgers Based on Energy Efficiency Analysis and Evaluation Model Technical Field

[0001] This invention relates to the field of dredger energy efficiency testing technology, specifically a method for calculating dredger energy efficiency based on an energy efficiency analysis and evaluation model. Background Technology

[0002] With the rapid development of the domestic economy and maritime transport, port and waterway construction and maintenance projects have grown rapidly, and dredgers are the most widely used type of construction vessel. Cutter suction dredgers are characterized by large operating capacity, high power, and high energy consumption. The annual energy consumption of one cutter suction dredger is equivalent to that of a medium-sized port, and its energy cost is relatively high, accounting for about 40% or more of the total cost. Therefore, the energy efficiency labeling system is an important measure to promote energy conservation, emission reduction, and quality control in China. Practice has proven that establishing and implementing the energy efficiency labeling system in my country is an inevitable requirement for deepening energy conservation management, a fundamental solution to improve energy conservation requirements from the source and promote energy-saving technologies, an important measure for the government to transform its functions, strengthen the supervision and management of energy-consuming products, and regulate the energy-consuming product market, and an effective way to promote energy conservation through marketization and continuously improve the energy efficiency level of energy-consuming products.

[0003] However, existing methods for calculating the energy efficiency of dredgers typically involve detecting and calculating various data points, analyzing the difference between the calculated values ​​and standard values, and thus obtaining an assessment of the dredger's energy efficiency. Due to the complexity of the data, the calculations are prone to errors, making it difficult to ensure the accuracy of the dredger energy efficiency assessment.

[0004] Therefore, it does not meet the existing requirements, so we propose a method for calculating the energy efficiency of dredgers based on an energy efficiency analysis and evaluation model. Summary of the Invention

[0005] The purpose of this invention is to provide a method for calculating the energy efficiency of dredgers based on an energy efficiency analysis and evaluation model. This method automatically collects and detects data on the main energy-consuming equipment of the dredger, such as the main engine, auxiliary engines, and boiler, as well as the power of the dredging shaft, CO2 emissions, and environmental parameters of the vessel's waters, and establishes an energy efficiency analysis database. A correlation analysis algorithm is introduced to analyze the correlation between various factors, obtaining the degree of correlation between each parameter. Based on the type of dredger, energy efficiency evaluation models for trailing suction hopper dredgers and cutter suction dredgers are constructed. For a single dredger, the fuel consumption per 10,000 cubic meters of soil under various working conditions is used as the optimization target of the energy efficiency evaluation model, and based on this, a vessel energy consumption evaluation level is established. This provides auxiliary decision-making for dredging operations' energy efficiency, thereby completing an intelligent energy efficiency management system and solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The energy efficiency calculation method for dredgers based on energy efficiency analysis and evaluation models includes the following steps:

[0008] S1. Automatically collect and detect data parameters of dredger combustion consumption, dredging shaft power equipment, CO2 emissions, and the ship's aquatic environment to obtain various energy efficiency data of the dredger.

[0009] S2. After preprocessing the collected dredger energy efficiency data, removing abnormal data, and ensuring the validity of the dredger energy efficiency data, establish an energy efficiency analysis database.

[0010] S3. Introduce a correlation analysis algorithm to analyze the correlation of various factors in the energy efficiency data of dredgers, obtain the degree of correlation between each parameter and the oil consumption per cubic meter of soil, and then measure the degree of correlation between each parameter.

[0011] S4. Based on the different working states of dredgers, establish energy efficiency assessment models for trailing suction hopper dredgers and cutter suction dredgers respectively. Specifically, this includes: for trailing suction hopper dredgers, constructing energy efficiency assessment models for single-ship dredging cycles, dredging and dumping cycles, dredging and blowing cycles, and navigation cycles; inputting the corresponding characteristic parameters for training and testing; and outputting energy efficiency calculation results and automatically generating reports for ship cycles, daily cycles, monthly cycles, and annual cycles. For cutter suction dredgers, constructing energy efficiency assessment models for single-vehicle travel cycles and anchor displacement ship cycles; inputting the corresponding characteristic parameters for training and testing; and outputting energy efficiency calculation results and automatically generating reports for ship cycles, daily cycles, monthly cycles, and annual cycles.

[0012] S5. Taking the fuel consumption of 10,000 cubic meters of soil under various working conditions as the optimization target of the energy efficiency assessment model for a single dredger trip, a ship energy consumption assessment level is established based on this. The energy efficiency calculation results of the current dredger output by the energy efficiency assessment model are then compared with the ship energy consumption assessment level to obtain the current energy efficiency assessment result of the dredger.

[0013] Furthermore, the combustion consumption of the dredger in S1 includes: real-time fuel consumption, operating fuel consumption, fuel consumption per unit time, and fuel consumption per unit nautical mile; real-time fuel consumption specifically includes: real-time fuel consumption of the main engine, auxiliary engine, and boiler, in tons; real-time fuel consumption specifically includes: operating fuel consumption of the trailing suction hopper dredger, including: navigation fuel consumption, dredging fuel consumption, dumping fuel consumption, and reclamation fuel consumption; operating fuel consumption of the cutter suction dredger includes: dredging fuel consumption, in tons.

[0014] Furthermore, the CO2 emissions in S1, i.e., the carbon emissions during the combustion of fossil fuels, are calculated using the following formula: E m =∑ i F i .EF i ;

[0015] In the formula: i represents the fuel type; F ii represents the fuel consumption, in J; EF i E represents the carbon dioxide (CO2) emission factor of fuel i, expressed in kg / J. m This represents the amount of carbon dioxide (CO2) emitted, expressed in kg.

[0016] Furthermore, after calculating the CO2 emissions, the CO2 emissions are measured and calculated based on fuel consumption and supply. The calculation formula is as follows: m c =FC×C GHG (1)

[0017] Where: m c FC represents the measured value of CO2 emission factors, and C represents energy consumption. GHG This represents the greenhouse gas emission coefficient.

[0018] Furthermore, after calculating the CO2 emissions, the CO2 emissions are measured and calculated based on fuel consumption and supply. The calculation formula is as follows: m c =DL×C GHG (2)

[0019] Where: m c DL represents the detectable level of CO2 emission factors, and C represents the dynamic activity level. GHG This represents the greenhouse gas emission coefficient.

[0020] Furthermore, the collected dredger energy efficiency data is preprocessed to remove outlier data, including:

[0021] The collected energy efficiency data of dredgers is preprocessed to remove abnormal data.

[0022] Retrieve the removed abnormal data and obtain the amount of data corresponding to the abnormal data;

[0023] Extract the amount of energy efficiency data for dredgers after removing outliers;

[0024] Obtain the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data;

[0025] When the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data is greater than a preset ratio threshold, the specific data value corresponding to each abnormal data is retrieved.

[0026] Based on the quantitative relationship between the abnormal data and the normal data, an abnormal data index coefficient is obtained; wherein, the abnormal data index coefficient is obtained by the following formula:

[0027] Among them, G 01 Z represents the coefficient of the abnormal data index; m represents the number of abnormal data points; n represents the number of abnormal data points that were judged as abnormal due to garbled characters; T represents the number of abnormal data points that were judged as abnormal because their values ​​did not meet the normal value requirements; r T represents the data acquisition time corresponding to the r-th garbled data; r-1 T represents the data acquisition time corresponding to the (r-1)th garbled data; c Indicates the minimum allowed interval for generating garbled data; X r This represents the data value corresponding to the r-th abnormal data point that does not conform to normal values; X cr T represents the boundary value with the smallest data difference from the r-th abnormal data point within the normal data range corresponding to the r-th abnormal data point; xr T represents the data acquisition time corresponding to the r-th abnormal data point that does not conform to the normal value; nr This represents the closest data collection time of the garbled data to the data collection time corresponding to the r-th abnormal data that does not conform to the normal value;

[0028] The evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients.

[0029] When the abnormal data evaluation parameters exceed the preset evaluation parameter threshold, an alarm is triggered to detect abnormal data quality in the dredger's energy efficiency data.

[0030] Furthermore, evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients.

[0031] Extract the data weight values ​​corresponding to the abnormal data;

[0032] The abnormal data weight index coefficient is obtained using the data weight value corresponding to the abnormal data; wherein, the abnormal data weight index coefficient is obtained by the following formula:

[0033] Among them, G 02 The coefficient represents the weighting index for outlier data; m represents the number of data points that were identified as outlier due to garbled characters; n represents the number of data points that were identified as outlier due to their values ​​not conforming to normal numerical requirements; g mr This represents the weight value corresponding to the r-th garbled data; g nmax This represents the maximum weight that appears in outlier data that does not conform to normal values; g nr This represents the weight value corresponding to the r-th outlier that does not conform to normal values; g m01rand g m02r This represents the weight value corresponding to the garbled data collected before and after the r-th abnormal data point that does not conform to normal values; g mp This represents the average weight of the garbled data; g np This represents the weighted average of outlier data that does not conform to normal values; g z This represents the sum of the weighted values ​​corresponding to all data types in the dredger energy efficiency data.

[0034] The abnormal data evaluation parameters are obtained by combining the abnormal data weight index coefficient with the abnormal data index coefficient.

[0035] The abnormal data evaluation parameters are obtained using the following formula:

[0036] Where G represents the outlier evaluation parameter; G 01 G represents the coefficient of the outlier index; 02 This represents the coefficient of the weighting index for outlier data.

[0037] Furthermore, in S3, a correlation analysis algorithm is introduced to analyze the correlation of various factors in the dredger energy efficiency data, specifically as follows:

[0038] Let X1, X2, ..., X p and Y1, Y2, ..., Y q These are two types of parameters that need to be assessed for correlation, with X and Y corresponding to two sets of random variables.

[0039] In the formula: p is the total number of vectors in group X, and q is the total number of vectors in group Y;

[0040] Two sets of vectors to be evaluated: X = (X1, X2, ..., X...) p ) T Y = (Y1, Y2, ..., Y) q ) T (p≤q), merge the two sets of parameters into a single vector (X). T Y T ) = (X1, X2, ..., X p Y1, Y2, ..., Y q ) T The covariance matrix of the merged parameter variables is:

[0041] Wherein: Σ 11 =Cov(X, X), Σ 22 =Cov(Y,Y),

[0042] Find two random variables X = (X1, X2, ..., X...) as parameters. p ) T Y = (Y1, Y2, ..., Y) q ) T The linear combination of (p≤q) is: And maximize the correlation coefficient ρ(U1, V1) of the linear combination U1 and V1 that vary from X and Y;

[0043] The coefficients of each linear combination expression are:

[0044] Furthermore, in S4, an energy efficiency evaluation model is constructed for a single-ship dredging cycle, dredging and dumping cycle, dredging and dredging cycle, and navigation cycle for the trailing suction hopper dredger. Taking a single ship trip as the cycle, the time and fuel consumption for dredging, dumping, dredging and dredging, and navigation are statistically analyzed respectively. The formula for calculating the cycle fuel consumption is as follows:

[0045] In the formula: M is the fuel consumption of the trailing suction hopper, T is the fuel consumption time of the trailing suction hopper; i represents the amount of mud dredged when the trailing suction hopper is dredging, the amount of mud dumped when the trailing suction hopper is dumping mud, the amount of mud filled when the trailing suction hopper is filling, and the mileage when the trailing suction hopper is sailing, respectively.

[0046] Furthermore, in S4, an energy efficiency evaluation model is constructed for the single-vehicle travel cycle and the anchor-moving vessel cycle of the cutter suction dredger. Using operating conditions as a distinction, the time and fuel consumption for the single-vehicle travel, anchor-moving vessel, and pile replacement processes are statistically analyzed separately. The formula for calculating cycle fuel consumption is:

[0047] In the formula: M is the fuel consumption of the cutter suction dredger, T is the fuel consumption time of the cutter suction dredger; i represents the single vehicle travel distance of the cutter suction dredger, the anchor displacement distance of the cutter suction dredger, and the voyage distance of the cutter suction dredger.

[0048] Furthermore, the method for establishing the ship energy consumption assessment level in S5 is as follows: by calculating the historical CO2 emissions per unit volume of earthwork carried by the dredger, the calculation formula is as follows:

[0049] In the formula: C Fj CO2 emission factor; FC j Total ship fuel consumption, in tons (t); M D The volume of earthwork is expressed in tons (t); j represents the type of fuel.

[0050] Furthermore, after obtaining the historical CO2 index range in S5, a total of 5 levels are established for ship energy consumption assessment based on the historical data range, namely:

[0051] Low energy consumption: Level 1-2, marked with a green label; Medium energy consumption: Level 3-4, marked with a yellow-brown label; High energy consumption: Level 5, marked with a red label.

[0052] Compared with the prior art, the beneficial effects of the present invention are:

[0053] This invention automatically collects and detects the main energy-consuming equipment of dredgers, such as the main engine, auxiliary machinery, and boiler, as well as the power of the dredging shaft, CO2 emissions, and environmental parameters of the vessel's waters, and establishes an energy efficiency analysis database. It introduces a correlation analysis algorithm to analyze the correlation between various factors and obtain the degree of correlation between each parameter. Based on the type of dredger, it constructs energy efficiency evaluation models for trailing suction hopper dredgers and cutter suction dredgers respectively. For a single dredger, the energy consumption per 10,000 cubic meters of soil under various working conditions is used as the optimization target of the energy efficiency evaluation model, and based on this, a vessel energy consumption evaluation level is established. This provides auxiliary decision-making for dredging operations, thereby completing an intelligent energy efficiency management system. Detailed Implementation

[0054] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] To address the current method of calculating dredger energy efficiency, which typically involves detecting and calculating various data points and analyzing the difference between the calculated values ​​and standard values ​​to obtain an assessment of the dredger's energy efficiency; however, due to the complexity of the data and the inherent error in the calculations, it is difficult to ensure the accuracy of the dredger energy efficiency assessment. Therefore, this embodiment provides the following technical solution:

[0056] The energy efficiency calculation method for dredgers based on energy efficiency analysis and evaluation models includes the following steps:

[0057] S1. Automatically collect and detect data parameters of dredgers' combustion consumption, dredging shaft power equipment, CO2 emissions, and the ship's aquatic environment to obtain various energy efficiency data of the dredgers. Among them, the combustion consumption of dredgers includes: real-time fuel consumption, operating fuel consumption, fuel consumption per unit time, and fuel consumption per unit nautical mile. Real-time fuel consumption specifically includes: real-time fuel consumption of main engine, auxiliary engine, and boiler, in tons (t). Real-time fuel consumption specifically includes: operating fuel consumption of trailing suction hopper dredgers, including: navigation fuel consumption and dredging fuel consumption. Fuel consumption for dredging and reclamation; the operating fuel consumption of a cutter suction dredger includes: dredging fuel consumption, in tons (t); specifically, fuel consumption per unit time is divided into: operating fuel consumption per unit time and total operating fuel consumption per unit time. Operating fuel consumption per unit time is: cycle fuel consumption. The calculation method for operating fuel consumption per unit time is: by statistically analyzing the operating time and fuel consumption of each operation stage. The calculation steps have been described in detail in step S4. The calculation method for total operating fuel consumption is: by statistically analyzing total fuel consumption and total operating time. The calculation formula is: Fuel consumption per nautical mile refers to the fuel consumption of a ship per nautical mile during a voyage. The calculation formula is as follows:

[0058] The above calculation method yields various parameters of dredger combustion consumption, providing data support for evaluating the energy efficiency of dredgers, ensuring the authenticity of the output results of the energy efficiency evaluation model, and thus improving the accuracy of dredger energy efficiency assessment.

[0059] CO2 emissions, i.e., carbon emissions from the combustion of fossil fuels, are calculated using the following formula: E i =∑ i F i .EF i ;

[0060] In the formula: i represents the fuel type; F i i represents the fuel consumption, in J; EF i E represents the carbon dioxide (CO2) emission factor of fuel i, expressed in kg / J. m This represents the amount of carbon dioxide (CO2) emitted, expressed in kg.

[0061] In this embodiment: the CO2 emission factor in the above formula is used to convert the carbon content of the fuel consumed by the ship into the amount of CO2 released, and it is a dimensionless conversion factor; given the low operability and poor accuracy of actual CO2 measurement, the IPCC proposed the concept of CO2 emission factor in the "IPCC Greenhouse Gas Guidelines and Best Practices Guidelines", and gave two methods for detecting and calculating CO2 emissions.

[0062] Method 1: This is a simple algorithm based on fuel consumption and supply. The calculation formula is as follows: m c =FC×CGHG (1)

[0063] Where: m c FC represents the measured value of CO2 emission factors, and C represents energy consumption. GHG Greenhouse gas emission coefficient;

[0064] Method 2: Greenhouse gas emissions are calculated by analyzing fuel supply and consumption, and the composition of technological forms. The calculation formula is as follows: m c =DL×C GHG (2)

[0065] Where: m c DL represents the detectable level of CO2 emission factors, and C represents the dynamic activity level. GHG This represents the greenhouse gas emission coefficient.

[0066] Specifically, the IPCC recommends using Method 1 to calculate CO2 emissions from maritime transport, where the greenhouse gas emission factor can also be called the carbon emission factor. Based on molecular mass, the carbon emission factors for fuels are as follows: C F =C Carbon％ ×3.664;

[0067] Table 1: Carbon content and carbon emission factors of various fuels

[0068] Where, hourly emissions = m c / hr, hourly emissions = m c / day, hourly emissions = m c / n.

[0069] Secondly, CO2 emissions also include EEOI, which is the amount of CO2 emitted per unit of transport work by a ship. According to the "Guideline for Voluntary Application of EEOI by Ships," the theoretical formula for calculating EEOI is as follows:

[0070] The formula for calculating the average ship energy efficiency index across multiple voyages is as follows:

[0071] In the formula: C Fj FC represents CO2 emission factor; D represents ship mileage in nm; j Total ship fuel consumption, in tons (t); meters (m³) cargo The cargo capacity is expressed in tons (t); j represents the fuel type; and i represents the number of flight segments.

[0072] The sailing distance in the formula refers to the total number of nautical miles actually sailed by a ship during a certain voyage or time period, usually using the sailing distance recorded in the ship's log. At the same time, the calculation of EEOI also requires the following preparations: First, the calculation period of EEOI needs to be determined, and relevant ship operation data such as the ship's total fuel consumption, cargo volume, and sailing distance within this period need to be collected and finally calculated.

[0073] In this embodiment, the dredger energy efficiency data also includes: propulsion power, which mainly refers to the total power of the propulsion system, i.e., the power of the left propulsion motor + the power of the right propulsion motor; fuel efficiency, which refers to how many grams of fuel the diesel generator set consumes per kilowatt-hour, and then converting the unit to tons (t) gives the fuel cost, with the unit being t / kWh; slip rate, slip rate = (theoretical speed - actual speed) ÷ theoretical speed; theoretical speed = total speed × propeller pitch ÷ time; fuel consumption per 10,000 cubic meters of soil, the calculation of which varies depending on the dredger. In this project, the calculation of fuel consumption per 10,000 cubic meters of soil is differentiated by the dredger's operating conditions. For trailing suction hopper dredgers, it is divided into real-time fuel consumption per 10,000 cubic meters of soil during dredging and fuel consumption per 10,000 cubic meters of soil during the dredging and dumping cycle; for cutter suction dredgers, it is real-time fuel consumption per 10,000 cubic meters of soil during dredging; the formula for calculating fuel consumption per 10,000 cubic meters of soil is:

[0074] S2. Preprocess the collected dredger energy efficiency data, removing outliers to ensure its validity, and then establish an energy efficiency analysis database. Specifically, after collecting and detecting the aforementioned data, the data can be cleaned to remove erroneous, duplicate, and missing data, thus ensuring its validity. The cleaned data is then stored, categorized by factors and types, forming the energy efficiency analysis database. This database includes current valid data and historical valid data from the dredger. Historical valid data can be used to train and test the subsequently constructed energy efficiency analysis and evaluation model, ensuring the accuracy of the model's calculations. The model can also be further trained and tested using current valid data, updating and iterating the model's feature set to ensure it continuously updates as the data changes, thus guaranteeing the real-time performance and accuracy of the energy efficiency analysis and evaluation model.

[0075] Specifically, the collected dredger energy efficiency data is preprocessed to remove outlier data, including:

[0076] The collected energy efficiency data of dredgers is preprocessed to remove abnormal data.

[0077] Retrieve the removed abnormal data and obtain the amount of data corresponding to the abnormal data;

[0078] Extract the amount of energy efficiency data for dredgers after removing outliers;

[0079] Obtain the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data;

[0080] When the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data is greater than a preset ratio threshold, the specific data value corresponding to each abnormal data is retrieved.

[0081] Based on the quantitative relationship between the abnormal data and the normal data, an abnormal data index coefficient is obtained; wherein, the abnormal data index coefficient is obtained by the following formula:

[0082] Among them, G 01 Z represents the coefficient of the abnormal data index; m represents the number of abnormal data points; n represents the number of abnormal data points that were judged as abnormal due to garbled characters; T represents the number of abnormal data points that were judged as abnormal because their values ​​did not meet the normal value requirements; r T represents the data acquisition time corresponding to the r-th garbled data; r-1 T represents the data acquisition time corresponding to the (r-1)th garbled data; c Indicates the minimum allowed interval for generating garbled data; X r This represents the data value corresponding to the r-th abnormal data point that does not conform to normal values; X cr T represents the boundary value with the smallest data difference from the r-th abnormal data point within the normal data range corresponding to the r-th abnormal data point; xr T represents the data acquisition time corresponding to the r-th abnormal data point that does not conform to the normal value; nr This represents the closest data collection time of the garbled data to the data collection time corresponding to the r-th abnormal data that does not conform to the normal value;

[0083] The evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients.

[0084] When the abnormal data evaluation parameters exceed the preset evaluation parameter threshold, an alarm is triggered to detect abnormal data quality in the dredger's energy efficiency data.

[0085] The technical benefits of the above solution are as follows: By preprocessing the energy efficiency data of dredgers, abnormal data is effectively eliminated. This abnormal data may arise from equipment malfunctions, sensor errors, human error, or data transmission problems, and its presence can severely affect the accuracy and reliability of data analysis. After removing this abnormal data, the remaining energy efficiency data is cleaner, providing a more solid foundation for subsequent data analysis and decision-making.

[0086] By calculating the ratio of outlier data to total data, the severity of outliers can be quantitatively assessed. When this ratio exceeds a preset threshold, it indicates a high proportion of outliers, potentially requiring further investigation or corrective action. This step helps to promptly identify and address potential data quality issues.

[0087] By retrieving the specific value of each anomalous data point and combining it with the quantitative relationship between anomalous and normal data, an anomalous data index coefficient (G01) is calculated. This coefficient considers not only the quantity of anomalous data (including garbled characters and abnormal data values), but also the time interval between their occurrences, the degree to which the data values ​​deviate from the normal range, and other factors, thus revealing the causes of anomalous data more comprehensively.

[0088] Anomaly evaluation parameters are calculated based on the weight values ​​and coefficients of outlier data. These parameters enable a more accurate assessment of the impact of outlier data on overall data quality. When the evaluation parameters exceed a preset threshold, the system automatically triggers a data quality anomaly alarm, promptly notifying relevant personnel to take measures to prevent the outlier data from adversely affecting subsequent analysis and decision-making.

[0089] The entire technical solution establishes an automated data quality monitoring and response mechanism. By monitoring the energy efficiency data of dredgers in real time, it promptly detects and handles abnormal data, ensuring the continuous stability of data quality. Simultaneously, through preset thresholds and automated alarm processes, it improves the efficiency and speed of data monitoring.

[0090] In summary, this technical solution significantly improves the quality monitoring and management level of dredger energy efficiency data through systematic data preprocessing, quantitative analysis, in-depth cause investigation, and precise impact assessment, providing more reliable and powerful support for data-driven decision-making.

[0091] Specifically, the evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients.

[0092] Extract the data weight values ​​corresponding to the abnormal data;

[0093] The abnormal data weight index coefficient is obtained using the data weight value corresponding to the abnormal data; wherein, the abnormal data weight index coefficient is obtained by the following formula:

[0094] Among them, G 02 This represents the weighting coefficient for outlier data; m represents the number of data points that were identified as outlier due to garbled characters; n represents the number of data points that were identified as outlier due to their values ​​not conforming to normal numerical requirements; g mr This represents the weight value corresponding to the r-th garbled data; g nmax This represents the maximum weight that appears in outlier data that does not conform to normal values; g nr This represents the weight value corresponding to the r-th outlier that does not conform to normal values; g m01r and g m02r This represents the weight value corresponding to the garbled data collected before and after the r-th abnormal data point that does not conform to normal values; g mp This represents the average weight of the garbled data; g np This represents the weighted average of outlier data that does not conform to normal values; g z This represents the sum of the weighted values ​​corresponding to all data types in the dredger energy efficiency data.

[0095] The abnormal data evaluation parameters are obtained by combining the abnormal data weight index coefficient with the abnormal data index coefficient.

[0096] The abnormal data evaluation parameters are obtained using the following formula:

[0097] Where G represents the outlier evaluation parameter; G 01 G represents the coefficient of the outlier index; 02 This represents the coefficient of the weighting index for outlier data.

[0098] The technical effect of the above solution is as follows: by introducing anomaly data weight values, this solution can more precisely assess the impact of anomaly data on overall data quality. Different types of anomaly data (such as garbled data, data that does not meet normal numerical requirements) and their respective importance in the overall dataset (reflected by weight values) are all taken into consideration, thus deriving a more comprehensive and accurate anomaly data evaluation parameter.

[0099] By utilizing the outlier weighting index coefficient (G02), this scheme can differentiate the severity of different types of outliers and their varying impacts on overall data quality. For example, outliers with higher weights may have a greater impact on overall data quality and therefore require more attention and priority processing. This differentiated approach improves the accuracy and efficiency of data quality monitoring.

[0100] By defining weight values ​​for outlier data, this approach allows for adjusting the weights of different data types according to actual needs, thus adapting to various application scenarios and data characteristics. This flexibility makes the technical solution more versatile and practical, capable of meeting the needs of different users and datasets.

[0101] By combining the outlier index coefficient (G01) and the outlier weight index coefficient (G02), an outlier evaluation parameter (G) is calculated using a formula, enabling a comprehensive assessment of outlier data. This evaluation parameter considers not only the quantity and type of outliers but also their importance and impact on overall data quality, providing strong support for subsequent data processing and decision-making.

[0102] When abnormal data evaluation parameters exceed preset thresholds, the system can automatically trigger a data quality anomaly alarm. This automated alarm and response mechanism can promptly detect and address data quality issues, preventing them from adversely affecting subsequent data analysis and decision-making. Simultaneously, it reduces the burden of manual monitoring and improves the efficiency and accuracy of data processing.

[0103] In summary, this technical solution significantly improves the accuracy and efficiency of data quality monitoring by introducing abnormal data weight values ​​and comprehensively evaluating abnormal data, providing more reliable and powerful support for data-driven decision-making.

[0104] S3. Introduce a correlation analysis algorithm to analyze the correlation of various factors in the energy efficiency data of dredgers, obtain the degree of correlation between each parameter and the oil consumption per cubic meter of soil, and then measure the degree of correlation between each parameter.

[0105] Specifically, after obtaining the various working states of the dredger through step S1, in order to avoid redundant parameters in the energy efficiency analysis and evaluation model, thereby increasing the complexity of the energy efficiency analysis and evaluation model calculation and reducing the accuracy of the energy efficiency analysis and evaluation model, it is necessary to analyze the correlation of various factors affecting the oil consumption of 10,000 cubic meters of soil.

[0106] A correlation analysis algorithm is introduced to analyze the correlation of various factors in the energy efficiency data of dredgers, specifically:

[0107] Let X1, X2, ..., X p and Y1, Y2, ..., Y qThese are two types of parameters that need to be assessed for correlation, with X and Y corresponding to two sets of random variables.

[0108] In the formula: p is the total number of vectors in group X, and q is the total number of vectors in group Y;

[0109] Two sets of vectors to be evaluated: X = (X1, X2, ..., X...) p ) T Y = (Y1, Y2, ..., Y) q ) T (p≤q), merge the two sets of parameters into a single vector (X). T Y T ) = (X1, X2, ..., X p Y1, Y2, ..., Y q ) T The covariance matrix of the merged parameter variables is:

[0110] Wherein: Σ 11 =Cov(X, X), Σ 22 =Cov(Y,Y),

[0111] Find two random variables X = (X1, X2, ..., X...) as parameters. p ) T Y = (Y1, Y2, ..., Y) q ) T The linear combination of (p≤q) is: And maximize the correlation coefficient ρ(U1, V1) of the linear combination U1 and V1 that vary from X and Y;

[0112] The coefficients of each linear combination expression are:

[0113] In summary, it is necessary to consider the two sets of variables (X1, X2, ..., X...) for each influencing parameter. p (Y1, Y2, ..., Y) and (Y1, Y2, ..., Y) q Find a corresponding linear combination, considering a principal component analysis-like approach (X1, X2, ..., X...). p A linear combination U and (Y1, Y2, ..., Y) q A linear combination V is merged into a vector, and the goal is to find the most probable correlation coefficient between V and V, so as to fully reflect the correlation between the two sets of variables. In this way, the problem of studying the correlation between two sets of random variables of influencing factors is transformed into studying the correlation between two random variables.

[0114] In this embodiment, taking a trailing suction hopper dredger as an example, the correlation between mud pump speed, high-pressure flushing pump speed, rake lip angle to ground, speed, overflow height, diesel engine speed, and fuel consumption per cubic meter of soil is studied, and the correlation coefficient is calculated. According to the correlation analysis theory, the positive or negative value of the correlation coefficient only represents the magnitude of the correlation between two related parameters, and the magnitude of the correlation coefficient indicates the strength of the correlation between the parameters. Therefore, in order to emphasize the strength of the correlation between each parameter, this algorithm uses the absolute value of the correlation coefficient between two parameters to represent the correlation between energy efficiency parameters. When the correlation coefficient is greater than 0.8, it indicates that the factor is highly correlated with fuel consumption per cubic meter of soil; if the correlation coefficient is between 0.8 and 0.5, it indicates a relatively large correlation; if the correlation coefficient is between 0.5 and 0.3, it indicates a correlation; if the correlation coefficient is less than 0.3, it is a slight correlation. Therefore, through correlation coefficient analysis, factors with a high impact on fuel consumption per cubic meter of soil can be identified, thereby realizing the analysis and evaluation of energy consumption.

[0115] S4. Based on the different working states of dredgers, establish energy efficiency assessment models for trailing suction hopper dredgers and cutter suction dredgers respectively. Specifically, this includes: for trailing suction hopper dredgers, constructing energy efficiency assessment models for single-ship dredging cycles, dredging and dumping cycles, dredging and blowing cycles, and navigation cycles; inputting the relevant characteristic parameters for training and testing; and outputting energy efficiency calculation results and automatically generating reports for each ship cycle, daily cycle, monthly cycle, and annual cycle. For cutter suction dredgers, constructing energy efficiency assessment models for single-vehicle travel cycles and anchor displacement cycles; inputting the relevant characteristic parameters for training and testing; and outputting energy efficiency calculation results and automatically generating reports for each ship cycle, daily cycle, monthly cycle, and annual cycle. Specifically, after creating the energy efficiency assessment models for trailing suction hopper dredgers and cutter suction dredgers respectively, it is also necessary to select historical energy efficiency data for both types of dredgers from the energy efficiency analysis database, and classify the two types of data separately. The model is divided into training and testing sets. The training and testing sets of the trailing suction hopper dredger are then sequentially imported into the trailing suction hopper dredger energy efficiency assessment model for training and testing until the test results match the training results. This establishes the feature set of the trailing suction hopper dredger energy efficiency assessment model and ensures the accuracy of the model's analysis. Similarly, the training and testing sets of the cutter suction dredger are sequentially imported into the cutter suction dredger energy efficiency assessment model for training and testing until the test results match the training results. This establishes the feature set of the cutter suction dredger energy efficiency assessment model and ensures the accuracy of the model's analysis. After the feature sets of both the trailing suction hopper dredger and cutter suction dredger energy efficiency assessment models are established, the energy efficiency of the current dredger is correlated with the model's performance. The main component data is then imported into the corresponding energy efficiency analysis and assessment model for analysis and calculation, and the energy efficiency calculation results of the current dredger are output.

[0116] In S4: An energy efficiency evaluation model is constructed for trailing suction hopper dredgers, including dredging cycle, dredging and dumping cycle, dredging and dredging cycle, and navigation cycle. Taking a single dredging cycle as the basis, the time and fuel consumption for dredging, dumping, dredging and dredging, and navigation are statistically analyzed. The formula for calculating cycle fuel consumption is as follows:

[0117] Where: m c denoted as CO2 emission factor, M as trailing suction hopper fuel consumption, T as trailing suction hopper fuel consumption time, and i as the amount of mud dredged, the amount of mud dumped, the amount of mud filled, and the mileage traveled during navigation, respectively.

[0118] In S4: Energy efficiency evaluation models for the single-vehicle travel cycle and anchor-movement vessel cycle of cutter suction dredgers are constructed. Based on different operating conditions, the time and fuel consumption for the single-vehicle travel, anchor-movement vessel cycle, and pile replacement process are statistically analyzed separately. The formula for calculating cycle fuel consumption is:

[0119] Where: m c M represents the CO2 emission factor, T represents the cutter suction dredger fuel consumption, and T represents the cutter suction dredger fuel consumption time. i represents the single vehicle travel distance of the cutter suction dredger and the anchor displacement distance of the cutter suction dredger, respectively.

[0120] S5. Using the fuel consumption per 10,000 cubic meters of soil under various operating conditions as the optimization objective of the energy efficiency assessment model for a single dredger trip, an energy consumption assessment level for the vessel is established based on this. The energy efficiency calculation results of the current dredger output by the energy efficiency assessment model are then compared with the vessel energy consumption assessment level to obtain the current energy efficiency assessment result for the dredger. The method for establishing the vessel energy consumption assessment level is as follows: The CO2 emissions per unit volume of soil historically emitted by the dredger are calculated using the following formula:

[0121] In the formula: C Fj CO2 emission factor; FC j Total ship fuel consumption, in tons (t); M D The volume of earthwork is expressed in tons (t); j represents the type of fuel.

[0122] After obtaining the historical CO2 emission index range, a total of 5 levels were established for ship energy consumption assessment based on the historical data range, namely:

[0123] Low energy consumption: Level 1-2, marked with a green label; Medium energy consumption: Level 3-4, marked with a yellow-brown label; High energy consumption: Level 5, marked with a red label.

[0124] Specifically, the dredging energy efficiency index of the current dredger is calculated using the above formula. Based on this index, and combined with the current energy efficiency label, the energy consumption level of the vessel is classified. After classifying the levels, the energy efficiency parameters of the current dredger are evaluated and analyzed according to the energy efficiency analysis and evaluation model. If the output index after analysis by the energy efficiency analysis and evaluation model is at level 1-2, the current dredger is considered to have low energy consumption and is displayed as a green label; if the output index is at level 3-4, the current dredger is considered to have medium energy consumption and is displayed as a yellow-brown label; if the output index is at level 5, the current dredger is considered to have high energy consumption and is displayed as a red label. Based on the label, the energy efficiency status of the current dredger is quickly determined, thereby providing auxiliary decision-making for dredging operation energy efficiency and completing the intelligent energy efficiency management system of the dredger.

[0125] Working principle: The system automatically collects and monitors the main energy-consuming equipment of the dredger, such as the main engine, auxiliary machinery, and boiler, as well as the power of the dredging shaft, CO2 emissions, and environmental parameters of the vessel's waters, and establishes an energy efficiency analysis database. A correlation analysis algorithm is introduced to analyze the correlation between various factors, obtaining the degree of correlation between each parameter. Based on the type of dredger, energy efficiency assessment models for trailing suction hopper dredgers and cutter suction dredgers are constructed. For a single dredger, the fuel consumption per 10,000 cubic meters of soil under various working conditions is used as the optimization target for the energy efficiency assessment model, and based on this, a vessel energy consumption assessment level is established. This provides auxiliary decision-making for dredging operations, thereby completing the intelligent energy efficiency management system.

[0126] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0127] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

Claims

1. A method for calculating the energy efficiency of dredgers based on an energy efficiency analysis and evaluation model, comprising the following steps: S1. Automatically collect and detect data parameters of dredger combustion consumption, dredging shaft power equipment, CO2 emissions, and the ship's aquatic environment to obtain various energy efficiency data of the dredger. S2. After preprocessing the collected dredger energy efficiency data, removing abnormal data, and ensuring the validity of the dredger energy efficiency data, establish an energy efficiency analysis database. S3. Introduce a correlation analysis algorithm to analyze the correlation of various factors in the energy efficiency data of dredgers, obtain the degree of correlation between each parameter and the oil consumption per cubic meter of soil, and then measure the degree of correlation between each parameter. S4. Based on the different working states of dredgers, establish energy efficiency assessment models for trailing suction hopper dredgers and cutter suction dredgers respectively; the energy efficiency assessment models specifically include: An energy efficiency assessment model for trailing suction hopper dredgers was developed, encompassing the dredging cycle, dumping cycle, dredging-blowing cycle, and navigation cycle for a single dredging trip. Input the relevant feature parameters for training and testing, and output the energy efficiency calculation results and automatically generate reports on the ship cycle, daily cycle, monthly cycle, and annual cycle. An energy efficiency assessment model for cutter suction dredgers is constructed, which includes the single vehicle travel cycle and the anchor displacement vessel cycle. The model is trained and tested by inputting the relevant characteristic parameters, and the energy efficiency calculation results and automatic generation of vessel cycle, daily cycle, monthly cycle and annual cycle reports are output. S5. Taking the fuel consumption of 10,000 cubic meters of soil under various working conditions as the optimization target of the energy efficiency assessment model for a single dredger trip, a ship energy consumption assessment level is established based on this. The energy efficiency calculation results of the current dredger output by the energy efficiency assessment model are then compared with the ship energy consumption assessment level to obtain the current energy efficiency assessment result of the dredger.

2. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: The CO2 emissions in S1 are calculated using the following formula: E m =∑ i F i .EF i ; In the formula: i represents the fuel type; F i For fuel consumption, EF i E is the emission factor of carbon dioxide (CO2) from fuel i. m This refers to the emissions of carbon dioxide (CO2).

3. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 2, characterized in that: After calculating the CO2 emissions, the emissions are then measured and calculated based on fuel consumption and supply. The calculation formula is as follows: m c =FC×C GHG (1) Where: m c FC represents the measured value of CO2 emission factors, and C represents energy consumption. GHG This represents the greenhouse gas emission factor.

4. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 2, characterized in that: After calculating the CO2 emissions, the emissions are then measured and calculated based on fuel consumption and supply. The calculation formula is as follows: m c =DL×C GHG (2) Where: m c DL represents the detectable level of CO2 emission factors, and C represents the dynamic activity level. GHG This represents the greenhouse gas emission factor.

5. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: The collected energy efficiency data of dredgers was preprocessed to remove outlier data, including: The collected energy efficiency data of dredgers is preprocessed to remove abnormal data. Retrieve the removed abnormal data and obtain the amount of data corresponding to the abnormal data; Extract the amount of energy efficiency data for dredgers after removing outliers; Obtain the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data; When the ratio of the amount of data corresponding to the abnormal data to the amount of data corresponding to the energy efficiency data of the dredger after removing the abnormal data is greater than a preset ratio threshold, the specific data value corresponding to each abnormal data is retrieved. Based on the quantitative relationship between the abnormal data and the normal data, an abnormal data index coefficient is obtained; wherein, the abnormal data index coefficient is obtained by the following formula: Among them, G 01 Z represents the coefficient of the abnormal data index; m represents the number of abnormal data points; n represents the number of abnormal data points that were judged as abnormal due to garbled characters; T represents the number of abnormal data points that were judged as abnormal because their values ​​did not meet the normal value requirements; r T represents the data acquisition time corresponding to the r-th garbled data; r-1 T represents the data acquisition time corresponding to the (r-1)th garbled data; c Indicates the minimum allowed interval for generating garbled data; X r This represents the data value corresponding to the r-th abnormal data point that does not conform to normal values; X cr T represents the boundary value with the smallest data difference from the r-th abnormal data point within the normal data range corresponding to the r-th abnormal data point; xr T represents the data acquisition time corresponding to the r-th abnormal data point that does not conform to the normal value; nr This represents the closest data collection time of the garbled data to the data collection time corresponding to the r-th abnormal data that does not conform to the normal value; The evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients. When the abnormal data evaluation parameters exceed the preset evaluation parameter threshold, an alarm is triggered to detect abnormal data quality in the dredger's energy efficiency data.

6. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 5, characterized in that: The evaluation parameters for abnormal data are obtained by combining the data weight values ​​corresponding to the abnormal data with the abnormal data index coefficients. Extract the data weight values ​​corresponding to the abnormal data; The abnormal data weight index coefficient is obtained using the data weight value corresponding to the abnormal data; wherein, the abnormal data weight index coefficient is obtained by the following formula: Among them, G 02 This represents the weighting coefficient for outlier data; m represents the number of data points that were identified as outlier due to garbled characters; n represents the number of data points that were identified as outlier due to their values ​​not conforming to normal numerical requirements; g mr This represents the weight value corresponding to the r-th garbled data; g nmax This represents the maximum weight that appears in outlier data that does not conform to normal values; g nr This represents the weight value corresponding to the r-th outlier that does not conform to normal values; g m01r and g m02r This represents the weight value corresponding to the garbled data collected before and after the r-th abnormal data point that does not conform to normal values; g mp This represents the average weight of the garbled data; g np This represents the weighted average of outlier data that does not conform to normal values; g z This represents the sum of the weighted values ​​corresponding to all data types in the dredger energy efficiency data. The abnormal data evaluation parameters are obtained by combining the abnormal data weight index coefficient with the abnormal data index coefficient. The abnormal data evaluation parameters are obtained using the following formula: Where G represents the outlier evaluation parameter; G 01 G represents the coefficient of the outlier index; 02 This represents the coefficient of the weighting index for outlier data.

7. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: The correlation analysis algorithm introduced in S3 is used to analyze the correlation of various factors in the energy efficiency data of dredgers, specifically as follows: Let X1, X2, ..., X p and Y1, Y2, ..., Y q These are two types of parameters that need to be assessed for correlation, with X and Y corresponding to two sets of random variables. In the formula: p is the total number of vectors in group X, and q is the total number of vectors in group Y; Two sets of vectors to be evaluated: X = (X1, X2, ..., X...) p ) T Y = (Y1, Y2, ..., Y) q ) T (p≤q), merge the two sets of parameters into a single vector (X). T Y T ) = (X1, X2, ..., X p Y1, Y2, ..., Y q ) T The covariance matrix of the merged parameter variables is: Among them: Σ 11 =Cov(X, X),Σ 22 =Cov(Y,Y), Find two random variables X = (X1, X2, ..., X...) as parameters. p ) T Y = (Y1, Y2, ..., Y) q ) T The linear combination of (p≤q) is: And maximize the correlation coefficient ρ(U1, V1) of the linear combination U1 and V1 that vary from X and Y; The coefficients of each linear combination expression are:

8. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: S4 describes an energy efficiency evaluation model for trailing suction hopper dredgers, encompassing dredging, dumping, dredging-and-filling, and navigation cycles. Using a single dredging cycle as the basis, the time and fuel consumption for dredging, dumping, dredging-and-filling, and navigation are statistically analyzed. The formula for calculating cycle fuel consumption is as follows: In the formula: M is the fuel consumption of the trailing suction hopper, T is the fuel consumption time of the trailing suction hopper; i represents the amount of mud dredged when the trailing suction hopper is dredging, the amount of mud dumped when the trailing suction hopper is dumping mud, the amount of mud filled when the trailing suction hopper is filling, and the mileage when the trailing suction hopper is sailing, respectively.

9. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: In S4, an energy efficiency evaluation model is constructed for the single vehicle travel cycle and the anchor displacement vessel cycle of the cutter suction dredger. The working conditions are used as a distinction to calculate the time and fuel consumption of the single vehicle travel, the anchor displacement vessel, and the pile replacement process. The formula for calculating cycle fuel consumption is: In the formula: M is the fuel consumption of the cutter suction dredger, T is the fuel consumption time of the cutter suction dredger; i represents the single vehicle travel distance of the cutter suction dredger, the anchor displacement distance of the cutter suction dredger, and the voyage distance of the cutter suction dredger.

10. The method for calculating the energy efficiency of a dredger based on an energy efficiency analysis and evaluation model according to claim 1, characterized in that: The method for establishing the ship energy consumption assessment level in S5 is as follows: by calculating the historical CO2 emissions per unit volume of earthwork carried by the dredger, the calculation formula is as follows: In the formula: C Fj CO2 emission factor; FC j Total ship fuel consumption, in tons (t); M D The volume of earthwork is expressed in tons (t); j represents the type of fuel. After obtaining the historical CO2 index range in S5, a total of 5 levels are established for ship energy consumption assessment based on the historical data range, namely: Low energy consumption: Level 1-2, marked with a green label; Medium energy consumption: Level 3-4, marked with a yellow-brown label; High energy consumption: Level 5, marked with a red label.

Images