Intelligent management system for energy efficiency optimization of dredger based on fuel consumption prediction model

Abstract

The present invention discloses an intelligent management system for optimizing energy efficiency of dredgers based on a fuel consumption prediction model, and belongs to the technical field of ship engineering technology. In order to solve the problems of low accuracy of fuel consumption prediction and inconvenient control of operating costs, the system collects and analyzes the operating status, operating environment and static information of the dredger in real time, and calculates the force balance, dynamic state of the rake head and production curve at different ground speeds based on the calculation of the production model framework, and uses iterative calculations as inputs of the energy efficiency optimization suggestion module to accurately reflect the working status of the dredger, thereby providing a reliable data basis for fuel consumption prediction, thereby improving the accuracy of fuel consumption prediction. The fuel consumption prediction model can receive new working condition data in real time, and make real-time predictions based on these data, so that the system can monitor the fuel consumption of the dredger in real time, provide timely data support for operators, effectively reduce the fuel consumption of the dredger, improve energy efficiency, and reduce operating costs.

Description

Technical Field

[0001] The present invention relates to the technical field of ship engineering technology, and in particular to an intelligent management system for optimizing energy efficiency of dredgers based on a fuel consumption prediction model. Background Art

[0002] A dredger is an engineering vessel specially used for dredging underwater sediments such as mud, gravel, etc. It plays an important role in channel dredging, port construction, water conservancy projects and marine engineering. There are many types of dredgers, such as trailing suction dredgers, cutter suction dredgers, chain bucket dredgers, etc. Each type is suitable for different working environments according to its working principle and characteristics. Dredgers not only have efficient dredging capabilities and can adapt to dredging operations in various waters and working conditions, but also have good environmental performance and can avoid causing excessive disturbance and pollution to the waters. With the development of technology, modern dredgers also use advanced automated control systems and intelligent sensors and other technologies to realize the automation and intelligence of the excavation process, and improve work efficiency and safety. When using a dredger, its energy consumption often needs to be considered.

[0003] However, there are still the following problems in actual operation:

[0004] Traditional methods often predict fuel consumption based on experience or simple mathematical models, which have limited accuracy. They also rely on manual experience and regular maintenance, lack real-time and targetedness, resulting in high fuel consumption for dredgers and difficulty in effectively controlling operating costs. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent management system for optimizing energy efficiency of dredgers based on a fuel consumption prediction model, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent management system for optimizing energy efficiency of dredgers based on a fuel consumption prediction model, comprising:

[0007] Data acquisition module for:

[0008] Collect the real-time operation status data, working environment data and static information of the dredger;

[0009] Data processing module for:

[0010] Preprocess the collected raw data;

[0011] Fuel consumption prediction model module, used for:

[0012] Based on a machine learning algorithm, a fuel consumption prediction model is trained using historical data and real-time data. The fuel consumption prediction model is used to predict future fuel consumption based on the current ship status and operating environment;

[0013] Energy efficiency optimization suggestion module for:

[0014] According to the output results of the fuel consumption prediction model and the actual operation requirements of the ship, energy efficiency optimization suggestions are provided for the dredger, including adjusting the main engine speed, optimizing the navigation route, and improving the dredging process;

[0015] User interaction module, used to:

[0016] Provides a user interface through which users can view real-time data, energy efficiency optimization suggestions, and system operating status. At the same time, users can set and configure system parameters through the user interaction module.

[0017] Furthermore, the data acquisition module includes:

[0018] Real-time operation status data is collected, and the real-time operation status data includes real-time working condition data and a rake suction pipe process parameter group, wherein the rake suction pipe process parameter group is obtained in real time through the automatic control system and instrument monitoring equipment of the dredger.

[0019] Furthermore, the data acquisition module further includes:

[0020] Obtain static information of the ship, wherein the static information of the ship includes a fixed parameter group of a rake suction pipe, a fixed parameter group of a rake head, and a fixed parameter group of a rake head flushing, wherein the fixed parameter group of the rake suction pipe, the fixed parameter group of the rake head, and the fixed parameter group of a rake head flushing are all fixedly obtained from the technical specification of the dredger;

[0021] The working environment data is obtained, and the working environment data includes soil parameters, wherein the soil parameters include soil type, density, water content, and hardness, and the soil parameters are obtained through geological survey of the construction area.

[0022] Furthermore, the data acquisition module further includes:

[0023] A time interval real-time monitoring module is used to monitor the real-time working condition data and the collection time intervals corresponding to all types of data included in the rake suction pipe process parameter group;

[0024] An initial data transmission period setting module, used for setting an initial data transmission period for transmitting data to the data processing module according to the collection time intervals corresponding to the working condition data and all types of data included in the rake suction pipe process parameter group;

[0025] Real-time monitoring module, used to monitor in real time the actual length of time it takes to complete a single data collection including all types of data;

[0026] A comparison module, used to compare the actual length of time taken to complete a single data collection including all types of data with the initial data transmission period;

[0027] A data collection time interval change rate acquisition module is used to extract the data collection time interval change rate of each data type when the actual time length experienced by completing a single data collection including all types of data exceeds the initial data transmission period;

[0028] An initial data transmission cycle adjustment module, used for adjusting the initial data transmission cycle in real time according to the change rate of the data collection time interval of each data type, wherein the adjusted initial data transmission cycle;

[0029] The adjusted initial data transmission period is obtained by the following formula:

[0030]

[0031] Among them, H t Indicates the adjusted initial data transmission period; H c Indicates the initial data transmission cycle; H s It represents the actual length of time it takes to complete a single data collection including all types of data; p represents the period adjustment coefficient, and the period adjustment coefficient is obtained by the following formula:

[0032]

[0033] Among them, p represents the period adjustment coefficient; m represents the number of data types with delayed collection time; P i represents the data delay ratio of the i-th data type; P z It represents the average offset ratio corresponding to the data collection time offset of all types of data, and the data collection time offset includes the delayed offset of the collection time and the advanced offset of the collection time. When the collection time is delayed, the corresponding offset ratio is a positive value, and when the collection time is advanced, the corresponding offset ratio is a negative value.

[0034] Furthermore, the initial data transmission period setting module further includes:

[0035] A reference data transmission period acquisition module is used to set a reference data transmission period for data transmission to the data processing module according to the collection time intervals corresponding to all types of data included in the working condition data and the rake suction pipe process parameter group, wherein the reference data transmission period is the minimum time period length that can include all types of data to complete a single data collection;

[0036] The maximum interval acquisition module is used to extract the maximum time interval between the corresponding moments of single data collection corresponding to all types of data;

[0037] A maximum deviation value acquisition module, used for extracting the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection are collected;

[0038] The cycle time compensation value acquisition module is used to obtain the cycle time compensation value by using the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum time interval between the corresponding moments of the single data collection are used for data collection; wherein the cycle time compensation value is obtained by the following formula:

[0039]

[0040] Among them, H x Indicates the compensation amount of the cycle length; H max Indicates the maximum time interval between the corresponding moments of a single data collection corresponding to all types of data; P 01 Indicates the maximum deviation value of the data collection time corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P 02 Indicates the maximum deviation value of the data collection time corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P z01 Indicates the data collection time interval corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection; P z02 Indicates the data collection time interval corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection;

[0041] The initial data transmission cycle acquisition execution module is used to obtain the initial data transmission cycle by using the cycle duration compensation amount combined with the reference data transmission cycle; wherein the initial data transmission cycle is obtained by the following formula:

[0042]

[0043] Among them, H c represents the initial data transmission cycle; H0 represents the reference data transmission cycle; H x Indicates the period duration compensation amount.

[0044] Furthermore, the data processing module includes:

[0045] The collected real-time operation status data is cleaned, filtered and standardized to remove noise and interference in key parameters, and the processed real-time operation status data is converted into a unified format.

[0046] Furthermore, the fuel consumption prediction model module includes:

[0047] Parameter processing unit, used to:

[0048] Construct a production model framework, and generate production curves, cutting depth curves, main force curves of the rake head and rake pipe, and moment balance data of the rake head movable cover based on real-time operation status data, operating environment data, and static information of the ship;

[0049] Fuel consumption prediction unit, used for:

[0050] Based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and the moment balance data of the rake head movable cover, the key features are extracted, and the fuel consumption prediction model is constructed and trained. The predicted fuel consumption value is obtained based on the fuel consumption prediction model.

[0051] Furthermore, the parameter processing unit is also used for:

[0052] Input the fixed parameter group of the trailing suction pipe, the process parameter group of the trailing suction pipe and the soil parameters, wherein the fixed parameter group of the trailing suction pipe includes the trailing suction pipe length and weight parameters inherent in the trailing suction pipe vessel, and the process parameter group of the trailing suction pipe includes the trailing pipe angle, wave compensation force and movable cover angle parameters that can be adjusted by the operator according to the operation requirements, and perform parameterized modeling on the three-point suspended trailing suction pipe system;

[0053] The calculation steps include setting an initial ground speed, calculating the force balance of the rake head and the rake tube and the relative state of the rake head and the mud surface through the iterative method of dynamic cutting depth, and ending the calculation when the horizontal force acting on the rake tube system is greater than the thrust that the propeller can provide;

[0054] It is determined whether the pressure of the movable cover cylinder is greater than the set pressure at this time. If it is greater than the set pressure, the movable cover is retracted by one angle, and the calculation step is returned to perform iterative calculation;

[0055] If it is not greater than the set pressure, calculate the in-situ cutting volume at the ground speed;

[0056] Determine whether the current ground speed reaches the set maximum speed, if so, end the calculation;

[0057] Otherwise, increase the ground speed and return to the calculation step to continue the calculation;

[0058] Finally, a production curve is calculated with the ground speed as the horizontal coordinate and the in-situ cutting amount as the vertical coordinate.

[0059] Furthermore, the parameter processing unit is also used for:

[0060] Input the fixed parameter group of the rake suction pipe, and perform parameterized modeling on the three-point suspended rake suction pipe system based on the fixed parameter group of the rake suction pipe;

[0061] The fixed parameter group of the rake head is input, and the single-row rake tooth active rake head is parameterized modeled based on the fixed parameter group of the rake head;

[0062] Input the fixed parameter group of rake head flushing, and perform parameterized modeling on the wear block flushing, rake tooth flushing and movable cover flushing on the rake head based on the fixed parameter group of rake head flushing;

[0063] Input high-pressure flushing pump curve parameters and high-pressure flushing water pipeline characteristics, and calculate the high-pressure flushing water pump working point and the injection pressure speed at the nozzle based on the high-pressure flushing water pump curve parameters and high-pressure flushing water pipeline characteristics;

[0064] Build the scouring model at the wear-resistant block of clay and saturated sand, and calculate the scouring depth and width based on the scouring model at the wear-resistant block;

[0065] Build cutting models with different cutting angles for clay and saturated sand. The saturated sand cutting model also includes a model for the effect of rake flushing on cutting force.

[0066] Input process parameters, and generate the real-time visualization status of the current rake tube and rake head based on the process parameters calculation;

[0067] Based on the production model framework, the force balance and the dynamic state of the drag head at ground speed are iteratively calculated;

[0068] After the iterative calculation is completed, the production curve, cutting depth curve, main force curve of the rake head and rake pipe, and the moment balance data of the rake head movable cover are output.

[0069] Furthermore, the fuel consumption prediction unit is also used for:

[0070] Extract key features based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and moment balance data of the rake head and rake cover, wherein the key features include average production, maximum cutting depth, peak force of the rake head and rake tube, and range of moment of the active cover;

[0071] Establish a fuel consumption prediction model between fuel consumption and key characteristics based on linear regression fitting data;

[0072] Bring historical data into the fuel consumption prediction model, perform verification training on the fuel consumption prediction model, and adjust the model parameters based on the verification results;

[0073] When there is new working condition data, the working condition data is input into the model to obtain a predicted fuel consumption value, wherein the working condition data includes new production, cutting depth, and stress conditions.

[0074] Compared with the prior art, the present invention has the following beneficial effects:

[0075] 1. The system of the present invention can accurately predict fuel consumption by collecting and analyzing the operating status, operating environment and static information of the dredger in real time, and provide energy efficiency optimization suggestions based on the prediction results. These suggestions include adjusting the main engine speed, optimizing the navigation route, improving the dredging process, etc., thereby effectively reducing the fuel consumption of the dredger, improving energy efficiency, and reducing operating costs. The intelligent management system can automatically process a large amount of data, reduce manual intervention and misjudgment, and improve management efficiency. At the same time, through real-time feedback and energy efficiency optimization suggestions, the system can help operators better understand the status of the ship and improve operating efficiency.

[0076] 2. The present invention is based on the calculation of the production model framework. The system can iteratively calculate the force balance under different ground speeds, the dynamic state of the dredger head, the production curve and other information. This information can provide detailed operation guidance for operators, help them to formulate more reasonable operation plans, and optimize operation decisions. The output results of the fuel consumption prediction model module can be used as the input of the energy efficiency optimization suggestion module to generate more specific energy efficiency optimization suggestions, which will help to improve the energy efficiency management level of the dredger and reduce operating costs.

[0077] 3. The present invention extracts key features from the production curve, cutting depth curve, main force curve of the rake head and rake pipe, and the torque balance data of the rake head and movable cover, such as average production, maximum cutting depth, peak force of the rake head and rake pipe, and range of change of the movable cover torque. These key features can accurately reflect the working state of the dredger, and further provide a reliable data basis for fuel consumption prediction, thereby improving the accuracy of fuel consumption prediction. The fuel consumption prediction model can receive new working condition data in real time, including new production, cutting depth, force conditions, etc., and make real-time predictions based on these data, so that the system can monitor the fuel consumption of the dredger in real time, provide timely data support for operators, and help them optimize energy consumption during operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 This is a module schematic diagram of the dredger energy efficiency optimization intelligent management system of the present invention. DETAILED DESCRIPTION

[0079] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0080] In order to solve the technical problems that traditional methods are often based on experience or simple mathematical models to predict fuel consumption, with limited accuracy, and rely on manual experience and regular maintenance, lack of real-time and pertinence, resulting in high fuel consumption of dredgers and difficulty in effectively controlling operating costs, please refer to Figure 1 , the present invention provides the following technical solutions:

[0081] The intelligent management system for dredger energy efficiency optimization based on the fuel consumption prediction model includes:

[0082] Data acquisition module for:

[0083] Collect the real-time operation status data, working environment data and static information of the dredger;

[0084] Data processing module for:

[0085] Preprocess the collected raw data, clean, filter and standardize the collected real-time operation status data, remove noise and interference in key parameters, and convert the processed real-time operation status data into a unified format;

[0086] Fuel consumption prediction model module, used for:

[0087] Based on a machine learning algorithm, a fuel consumption prediction model is trained using historical data and real-time data. The fuel consumption prediction model is used to predict future fuel consumption based on the current ship status and operating environment;

[0088] Energy efficiency optimization suggestion module for:

[0089] According to the output results of the fuel consumption prediction model and the actual operation requirements of the ship, energy efficiency optimization suggestions are provided for the dredger, including adjusting the main engine speed, optimizing the navigation route, and improving the dredging process;

[0090] User interaction module, used to:

[0091] Provides a user interface through which users can view real-time data, energy efficiency optimization suggestions, and system operating status. At the same time, users can set and configure system parameters through the user interaction module.

[0092] In the above embodiment, the system can accurately predict fuel consumption by collecting and analyzing the operating status, operating environment and static information of the dredger in real time, and provide energy efficiency optimization suggestions based on the prediction results. These suggestions include adjusting the main engine speed, optimizing the navigation route, improving the dredging process, etc., thereby effectively reducing the fuel consumption of the dredger, improving energy efficiency, and reducing operating costs. The intelligent management system can automatically process large amounts of data, reduce manual intervention and misjudgment, and improve management efficiency. At the same time, through real-time feedback and energy efficiency optimization suggestions, the system can help operators better understand the status of the ship and improve operating efficiency.

[0093] In the above embodiment, by reducing fuel consumption, the system helps to reduce exhaust emissions generated by dredgers during operation, reduce pollution to the environment, and conform to the current green, low-carbon, and environmentally friendly development concept. The fuel consumption prediction model based on machine learning algorithms can accurately predict future fuel consumption based on historical data and real-time data, providing a scientific basis for decision-making. At the same time, energy efficiency optimization suggestions are also generated based on model output and actual ship operation needs, with higher accuracy and practicality.

[0094] Data acquisition module, including:

[0095] Real-time operation status data is collected, and the real-time operation status data includes real-time working condition data and a rake suction pipe process parameter group, wherein the rake suction pipe process parameter group is obtained in real time through the automatic control system and instrument monitoring equipment of the dredger.

[0096] Obtain static information of the ship, wherein the static information of the ship includes a fixed parameter group of a rake suction pipe, a fixed parameter group of a rake head, and a fixed parameter group of a rake head flushing, wherein the fixed parameter group of the rake suction pipe, the fixed parameter group of the rake head, and the fixed parameter group of a rake head flushing are all fixedly obtained from the technical specification of the dredger;

[0097] The working environment data is obtained, and the working environment data includes soil parameters, wherein the soil parameters include soil type, density, water content, and hardness, and the soil parameters are obtained through geological survey of the construction area.

[0098] In the above embodiment, the real-time collected dredger operation status data, such as real-time working condition data and rake suction pipe process parameter group, can accurately reflect the current working status of the dredger. These data are crucial to the fuel consumption prediction model because they directly affect the fuel consumption. Therefore, by collecting these data in real time, the accuracy of the fuel consumption prediction model can be improved. The static information of the ship, such as the rake suction pipe fixed parameter group, the rake head fixed parameter group, and the rake head flushing fixed parameter group, provides the basic physical and performance characteristics of the dredger. Although these fixed parameters do not change over time, they are crucial for understanding and optimizing the working performance of the dredger. Incorporating this information into the system can enhance the adaptability and flexibility of the system, enabling it to be optimized for different types of dredgers. The operating environment data, especially the soil parameters, have a significant impact on the energy consumption and performance of the dredger. By obtaining these parameters through geological surveys of the construction area, the system can take into account the impact of different soils on the energy consumption of the dredger, thereby providing more accurate fuel consumption predictions and more reasonable energy efficiency optimization suggestions.

[0099] In the above embodiment, by integrating real-time operation status data, ship static information and operating environment data, the system can comprehensively analyze the working conditions of the dredger and provide more comprehensive energy efficiency optimization suggestions. These suggestions are not limited to adjusting the main engine speed or optimizing the navigation route, but can also include dredging process optimization for specific soil or working conditions, thereby further improving the energy efficiency of the dredger.

[0100] At the same time, the data acquisition module also includes:

[0101] A time interval real-time monitoring module is used to monitor the real-time working condition data and the collection time intervals corresponding to all types of data included in the rake suction pipe process parameter group;

[0102] An initial data transmission period setting module, used for setting an initial data transmission period for transmitting data to the data processing module according to the collection time intervals corresponding to the working condition data and all types of data included in the rake suction pipe process parameter group;

[0103] Real-time monitoring module, used to monitor in real time the actual length of time it takes to complete a single data collection including all types of data;

[0104] A comparison module, used to compare the actual length of time taken to complete a single data collection including all types of data with the initial data transmission period;

[0105] A data collection time interval change rate acquisition module is used to extract the data collection time interval change rate of each data type when the actual time length experienced by completing a single data collection including all types of data exceeds the initial data transmission period;

[0106] An initial data transmission cycle adjustment module, used for adjusting the initial data transmission cycle in real time according to the change rate of the data collection time interval of each data type, wherein the adjusted initial data transmission cycle;

[0107] The adjusted initial data transmission period is obtained by the following formula:

[0108]

[0109] Among them, H t Indicates the adjusted initial data transmission period; H c Indicates the initial data transmission cycle; H s It represents the actual length of time it takes to complete a single data collection including all types of data; p represents the period adjustment coefficient, and the period adjustment coefficient is obtained by the following formula:

[0110]

[0111] Among them, p represents the period adjustment coefficient; m represents the number of data types with delayed collection time; P i represents the data delay ratio of the i-th data type; P z It represents the average offset ratio corresponding to the data collection time offset of all types of data, and the data collection time offset includes the delayed offset of the collection time and the advanced offset of the collection time. When the collection time is delayed, the corresponding offset ratio is a positive value, and when the collection time is advanced, the corresponding offset ratio is a negative value.

[0112] The technical effect of the above technical solution is: through the time interval real-time monitoring module, the system can track and monitor the collection time intervals of various data types (including real-time working condition data and rake suction pipe process parameters) in real time to ensure the timeliness of data collection. At the same time, this also helps to timely identify possible delays or anomalies in data collection, so as to take measures to make adjustments.

[0113] The initial data transmission cycle setting module sets the initial cycle of data transmission to the data processing module according to the data collection time interval, which is a reasonable starting point. However, through the real-time monitoring module and the comparison module, the system can further dynamically adjust the data transmission cycle according to the comparison result between the actual length of time required for a single data collection and the initial data transmission cycle. This adaptive adjustment mechanism can ensure the timeliness and efficiency of data transmission and avoid delays or waste of data transmission.

[0114] When the time required for a single data collection exceeds the initially set transmission cycle, the data collection time interval change rate acquisition module can identify and extract the time interval change rate of each data type. This function is particularly important for dealing with complex and changing working conditions, and can ensure that the system can still maintain efficient and stable data transmission when facing changes in data collection speed.

[0115] The initial data transmission cycle adjustment module adjusts the initial data transmission cycle in real time based on the rate of change of the data collection time interval and the cycle adjustment coefficient. This adjustment strategy not only takes into account the actual change in the time required for a single data collection, but also introduces a cycle adjustment coefficient, which comprehensively considers multiple factors (such as data type delay, data collection time offset, etc.), thereby achieving more accurate and intelligent adjustment.

[0116] The entire technical solution improves the stability and reliability of data collection and transmission through real-time monitoring, dynamic adjustment and data optimization. This is particularly important for industrial application scenarios that require high reliability and real-time performance, and can ensure that the system can still maintain efficient operation in the face of various complex working conditions.

[0117] In summary, this technical solution effectively improves the real-time, accuracy and stability of data collection and transmission through a series of intelligent and adaptive mechanisms and strategies, providing strong technical support for industrial applications.

[0118] Specifically, the initial data transmission period setting module further includes:

[0119] A reference data transmission period acquisition module is used to set a reference data transmission period for data transmission to the data processing module according to the collection time intervals corresponding to all types of data included in the working condition data and the rake suction pipe process parameter group, wherein the reference data transmission period is the minimum time period length that can include all types of data to complete a single data collection;

[0120] The maximum interval acquisition module is used to extract the maximum time interval between the corresponding moments of single data collection corresponding to all types of data;

[0121] A maximum deviation value acquisition module, used for extracting the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection are collected;

[0122] The cycle time compensation value acquisition module is used to obtain the cycle time compensation value by using the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum time interval between the corresponding moments of the single data collection are used for data collection; wherein the cycle time compensation value is obtained by the following formula:

[0123]

[0124] Among them, H x Indicates the compensation amount of the cycle length; H max Indicates the maximum time interval between the corresponding moments of a single data collection corresponding to all types of data; P 01 Indicates the maximum deviation value of the data collection time corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P 02 Indicates the maximum deviation value of the data collection time corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P z01 Indicates the data collection time interval corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection; P z02 Indicates the data collection time interval corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection;

[0125] The initial data transmission cycle acquisition execution module is used to obtain the initial data transmission cycle by using the cycle duration compensation amount combined with the reference data transmission cycle; wherein the initial data transmission cycle is obtained by the following formula:

[0126]

[0127] Among them, H c represents the initial data transmission cycle; H0 represents the reference data transmission cycle; H x Indicates the period duration compensation amount.

[0128] The technical effect of the above technical solution is: through the reference data transmission cycle acquisition module, the system can set a reasonable reference data transmission cycle based on the collection time interval of all types of data, that is, the minimum time cycle length that can include all types of data to complete a single data collection. This ensures that the data transmission cycle will not be too short, thereby avoiding resource waste or processing pressure caused by too frequent data transmission.

[0129] The maximum interval acquisition module and the maximum deviation acquisition module further analyze the maximum time interval between all types of data at the corresponding time of a single data collection, and extract the maximum deviation value allowed for the two data types corresponding to these time intervals at the data collection time. This analysis takes into account the differences in collection time between different data types and provides more refined data support for the adjustment of the data transmission cycle.

[0130] The cycle time compensation acquisition module uses the above-mentioned maximum time interval and maximum deviation value to calculate the cycle time compensation through a specific formula. This compensation takes into account the deviation of the acquisition time between data types, ensuring that the data transmission cycle can accommodate the slight difference in the acquisition time between data types while including all data types, thereby improving the flexibility and accuracy of data transmission.

[0131] The initial data transmission cycle acquisition execution module combines the cycle length compensation amount with the benchmark data transmission cycle, and calculates the final initial data transmission cycle through a formula. This combination not only ensures the rationality of the data transmission cycle (based on the benchmark cycle), but also takes into account the acquisition time difference between data types (adjusted by the compensation amount). Therefore, the setting of the initial data transmission cycle is more scientific and accurate, and can meet the needs of practical applications.

[0132] The entire technical solution optimizes the setting of the data transmission cycle through refined data analysis and calculation. This helps to reduce the redundancy and delay of data transmission and improve the efficiency and real-time performance of data transmission. At the same time, by considering the acquisition time difference and the maximum allowable deviation value between data types, the system can more flexibly cope with complex and changing working conditions, improving overall performance and stability.

[0133] In summary, this technical solution significantly improves the accuracy and flexibility of the data transmission cycle by introducing concepts such as benchmark data transmission cycle, maximum interval value, maximum deviation value and cycle duration compensation, and combines specific formulas for calculation and optimization, providing a more efficient and reliable data transmission solution for industrial applications.

[0134] Fuel consumption prediction model module, including:

[0135] Parameter processing unit, used to:

[0136] Construct a production model framework, and generate production curves, cutting depth curves, main force curves of the rake head and rake pipe, and moment balance data of the rake head movable cover based on real-time operation status data, operating environment data, and static information of the ship;

[0137] The parameter processing unit is also used to:

[0138] Input the fixed parameter group of the trailing suction pipe, the process parameter group of the trailing suction pipe and the soil parameters, wherein the fixed parameter group of the trailing suction pipe includes the trailing suction pipe length and weight parameters inherent in the trailing suction pipe vessel, and the process parameter group of the trailing suction pipe includes the trailing pipe angle, wave compensation force and movable cover angle parameters that can be adjusted by the operator according to the operation requirements, and perform parameterized modeling on the three-point suspended trailing suction pipe system;

[0139] The calculation steps include setting an initial ground speed, calculating the force balance of the rake head and the rake tube and the relative state of the rake head and the mud surface through the iterative method of dynamic cutting depth, and ending the calculation when the horizontal force acting on the rake tube system is greater than the thrust that the propeller can provide;

[0140] It is determined whether the pressure of the movable cover cylinder is greater than the set pressure at this time. If it is greater than the set pressure, the movable cover is retracted by one angle, and the calculation step is returned to perform iterative calculation;

[0141] If it is not greater than the set pressure, calculate the in-situ cutting volume at the ground speed;

[0142] Determine whether the current ground speed reaches the set maximum speed, if so, end the calculation;

[0143] Otherwise, increase the ground speed and return to the calculation step to continue the calculation;

[0144] Finally, a production curve is calculated with the ground speed as the horizontal coordinate and the in-situ cutting amount as the vertical coordinate.

[0145] The parameter processing unit is also used to:

[0146] Input the fixed parameter group of the rake suction pipe, and perform parameterized modeling on the three-point suspended rake suction pipe system based on the fixed parameter group of the rake suction pipe;

[0147] The fixed parameter group of the rake head is input, and the single-row rake tooth active rake head is parameterized modeled based on the fixed parameter group of the rake head;

[0148] Input the fixed parameter group of rake head flushing, and perform parameterized modeling on the wear block flushing, rake tooth flushing and movable cover flushing on the rake head based on the fixed parameter group of rake head flushing;

[0149] Input high-pressure flushing pump curve parameters and high-pressure flushing water pipeline characteristics, and calculate the high-pressure flushing water pump working point and the injection pressure speed at the nozzle based on the high-pressure flushing water pump curve parameters and high-pressure flushing water pipeline characteristics;

[0150] Build the scouring model at the wear-resistant block of clay and saturated sand, and calculate the scouring depth and width based on the scouring model at the wear-resistant block;

[0151] Build cutting models with different cutting angles for clay and saturated sand. The saturated sand cutting model also includes a model for the effect of rake flushing on cutting force.

[0152] Input process parameters, and generate the real-time visualization status of the current rake tube and rake head based on the process parameters calculation;

[0153] Based on the production model framework, the force balance and the dynamic state of the drag head at ground speed are iteratively calculated;

[0154] After the iterative calculation is completed, the production curve, cutting depth curve, main force curve of the rake head and rake pipe, and the moment balance data of the rake head movable cover are output.

[0155] In the above embodiment, through detailed parameterized modeling, including modeling of the rake suction pipe system, rake head, flushing system, etc., and considering the scouring and cutting models under different soil conditions, the fuel consumption prediction model can more accurately simulate the state of the dredger in actual operation, thereby improving the accuracy of fuel consumption prediction. The fuel consumption prediction model not only considers the static parameters of the dredger, but also combines real-time operating parameters (such as rake pipe angle, wave compensation force, etc.) and operating environment parameters (such as soil parameters), so that the system can adapt to different operating conditions and ship types, and provide prediction results that are more in line with the actual situation.

[0156] In the above embodiment, based on the calculation of the yield model framework, the system can iteratively calculate information such as force balance, dynamic state of the drag head and yield curve at different ground speeds. This information can provide detailed operation guidance for operators, help them formulate more reasonable operation plans and optimize operation decisions. The output results of the fuel consumption prediction model module (such as yield curve, cutting depth curve, etc.) can be used as input to the energy efficiency optimization suggestion module to generate more specific energy efficiency optimization suggestions, which will help improve the energy efficiency management level of the dredger and reduce operating costs.

[0157] In the above embodiment, through real-time visual status display, the operator can intuitively understand the working status and operation effect of the dredger. This not only helps to find and solve problems in a timely manner, but also improves the safety and efficiency of the operation. The fuel consumption prediction model module is an iterative optimization system. With the accumulation of data and the continuous improvement of the model, the prediction accuracy and adaptability of the system will be further improved. At the same time, by collecting and analyzing actual operation data, the system can also provide valuable feedback for the design and improvement of the dredger.

[0158] Fuel consumption prediction unit, used for:

[0159] Based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and the moment balance data of the rake head movable cover, the key features are extracted, and the fuel consumption prediction model is constructed and trained. The predicted fuel consumption value is obtained based on the fuel consumption prediction model.

[0160] Extract key features based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and moment balance data of the rake head and rake cover, wherein the key features include average production, maximum cutting depth, peak force of the rake head and rake tube, and range of moment of the active cover;

[0161] Establish a fuel consumption prediction model between fuel consumption and key characteristics based on linear regression fitting data;

[0162] Bring historical data into the fuel consumption prediction model, perform verification training on the fuel consumption prediction model, and adjust the model parameters based on the verification results;

[0163] When there is new working condition data, the working condition data is input into the model to obtain a predicted fuel consumption value, wherein the working condition data includes new production, cutting depth, and stress conditions.

[0164] In the above embodiment, by extracting key features from the production curve, cutting depth curve, main force curve of the rake head and rake pipe, and the torque balance data of the rake head and movable cover, such as average production, maximum cutting depth, peak force of the rake head and rake pipe, and range of torque variation of the movable cover, these key features can accurately reflect the working state of the dredger, and then provide a reliable data basis for fuel consumption prediction, thereby improving the accuracy of fuel consumption prediction. The fuel consumption prediction model can receive new working condition data in real time, including new production, cutting depth, force conditions, etc., and make real-time predictions based on these data. This enables the system to monitor the fuel consumption of the dredger in real time, provide timely data support to operators, and help them optimize energy consumption during operation.

[0165] In the above embodiment, based on accurate fuel consumption prediction, the system can better evaluate the energy efficiency level under different working conditions, thereby providing data support for energy efficiency optimization. By comparing the fuel consumption under different working conditions, the system can find out the working conditions with low energy efficiency and give corresponding optimization suggestions, such as adjusting the ground speed, optimizing the rake head angle, etc., so as to help the dredger achieve the optimization of energy efficiency. Through accurate fuel consumption prediction and energy efficiency optimization, the system can help the dredger reduce fuel consumption and reduce unnecessary energy consumption. This not only reduces the operating cost of the dredger, but also reduces the impact on the environment, achieving a dual improvement in economic and ecological benefits.

[0166] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent management system for dredger energy efficiency optimization based on a fuel consumption prediction model, characterized in that: include: Data acquisition module for: Collect the real-time operation status data, working environment data and static information of the dredger; Data processing module for: Preprocess the collected raw data; Fuel consumption prediction model module, used for: Based on a machine learning algorithm, a fuel consumption prediction model is trained using historical data and real-time data. The fuel consumption prediction model is used to predict future fuel consumption based on the current ship status and operating environment; Energy efficiency optimization suggestion module for: According to the output results of the fuel consumption prediction model and the actual operation requirements of the ship, energy efficiency optimization suggestions are provided for the dredger, including adjusting the main engine speed, optimizing the navigation route, and improving the dredging process; User interaction module, used to: Provide a user interface through which users can view real-time data, energy efficiency optimization suggestions, and system operation status. At the same time, users can set and configure system parameters through the user interaction module. Wherein, the data acquisition module includes: Collecting real-time operation status data, the real-time operation status data includes real-time working condition data and a rake suction pipe process parameter group, wherein the rake suction pipe process parameter group is obtained in real time through an automatic control system of the dredger and instrument monitoring equipment; A time interval real-time monitoring module is used to monitor the real-time working condition data and the collection time intervals corresponding to all types of data included in the rake suction pipe process parameter group; An initial data transmission period setting module, used for setting an initial data transmission period for transmitting data to the data processing module according to the collection time intervals corresponding to the working condition data and all types of data included in the rake suction pipe process parameter group; Real-time monitoring module, used to monitor in real time the actual length of time it takes to complete a single data collection including all types of data; A comparison module, used to compare the actual length of time taken to complete a single data collection including all types of data with the initial data transmission period; The data collection time interval change rate acquisition module is used to extract the data collection time interval change rate of each data type when the actual time length experienced by completing a single data collection including all types of data exceeds the initial data transmission period.

2. The dredger energy efficiency optimization intelligent management system based on the fuel consumption prediction model according to claim 1 is characterized in that: The data acquisition module further includes: An initial data transmission cycle adjustment module, used for adjusting the initial data transmission cycle in real time according to the change rate of the data collection time interval of each data type, wherein the adjusted initial data transmission cycle; The adjusted initial data transmission period is obtained by the following formula: ； Among them, H t Indicates the adjusted initial data transmission period; H c Indicates the initial data transmission cycle; H s It represents the actual length of time it takes to complete a single data collection including all types of data; p represents the period adjustment coefficient, and the period adjustment coefficient is obtained by the following formula: ； Among them, p represents the period adjustment coefficient; m represents the number of data types with delayed collection time; P i represents the data delay ratio of the i-th data type; P z It represents the average offset ratio corresponding to the data collection time offset of all types of data, and the data collection time offset includes the delayed offset of the collection time and the advanced offset of the collection time. When the collection time is delayed, the corresponding offset ratio is a positive value, and when the collection time is advanced, the corresponding offset ratio is a negative value.

3. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 2 is characterized in that: The initial data transmission cycle setting module also includes: A reference data transmission period acquisition module is used to set a reference data transmission period for data transmission to the data processing module according to the collection time intervals corresponding to all types of data included in the working condition data and the rake suction pipe process parameter group, wherein the reference data transmission period is the minimum time period length that can include all types of data to complete a single data collection; The maximum interval acquisition module is used to extract the maximum time interval between the corresponding moments of single data collection corresponding to all types of data; A maximum deviation value acquisition module, used for extracting the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection are collected; The cycle time compensation value acquisition module is used to obtain the cycle time compensation value by using the maximum deviation value of the data collection time allowed when two data types corresponding to the maximum time interval between the corresponding moments of the single data collection are used for data collection; wherein the cycle time compensation value is obtained by the following formula: ； Among them, H x Indicates the compensation amount of cycle duration; H max Indicates the maximum time interval between the corresponding moments of a single data collection corresponding to all types of data; P 01 Indicates the maximum deviation value of the data collection time corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P 02 Indicates the maximum deviation value of the data collection time corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding times of the single data collection; P z01 Indicates the data collection time interval corresponding to the data type with the earlier collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection; P z02 Indicates the data collection time interval corresponding to the data type with the later collection time among the two data types corresponding to the maximum value of the time interval between the corresponding moments of the single data collection; The initial data transmission cycle acquisition execution module is used to obtain the initial data transmission cycle by using the cycle duration compensation amount combined with the reference data transmission cycle; wherein the initial data transmission cycle is obtained by the following formula: ； Among them, H c represents the initial data transmission cycle; H0 represents the reference data transmission cycle; H x Indicates the period duration compensation amount.

4. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 3 is characterized in that: The data acquisition module further includes: Obtain static information of the ship, wherein the static information of the ship includes a fixed parameter group of a rake suction pipe, a fixed parameter group of a rake head, and a fixed parameter group of a rake head flushing, wherein the fixed parameter group of the rake suction pipe, the fixed parameter group of the rake head, and the fixed parameter group of a rake head flushing are all fixedly obtained from the technical specification of the dredger; The working environment data is obtained, and the working environment data includes soil parameters, wherein the soil parameters include soil type, density, water content, and hardness, and the soil parameters are obtained through geological survey of the construction area.

5. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 1, characterized in that: The data processing module comprises: The collected real-time operation status data is cleaned, filtered and standardized to remove noise and interference in key parameters, and the processed real-time operation status data is converted into a unified format.

6. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 1, characterized in that: The fuel consumption prediction model module includes: Parameter processing unit, used to: Construct a production model framework, and generate production curves, cutting depth curves, main force curves of the rake head and rake pipe, and moment balance data of the rake head movable cover based on real-time operation status data, operating environment data, and static information of the ship; Fuel consumption prediction unit, used for: Based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and the moment balance data of the rake head movable cover, the key features are extracted, and the fuel consumption prediction model is constructed and trained. The predicted fuel consumption value is obtained based on the fuel consumption prediction model.

7. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 6 is characterized in that: The parameter processing unit is further used for: Input the fixed parameter group of the trailing suction pipe, the process parameter group of the trailing suction pipe and the soil parameters, wherein the fixed parameter group of the trailing suction pipe includes the trailing suction pipe length and weight parameters inherent in the trailing suction pipe vessel, and the process parameter group of the trailing suction pipe includes the trailing pipe angle, wave compensation force and movable cover angle parameters that can be adjusted by the operator according to the operation requirements, and perform parameterized modeling on the three-point suspended trailing suction pipe system; The calculation steps include setting an initial ground speed, calculating the force balance of the rake head and the rake tube and the relative state of the rake head and the mud surface through the iterative method of dynamic cutting depth, and ending the calculation when the horizontal force acting on the rake tube system is greater than the thrust that the propeller can provide; It is determined whether the pressure of the movable cover cylinder is greater than the set pressure at this time. If it is greater than the set pressure, the movable cover is retracted by one angle, and the calculation step is returned to perform iterative calculation; If it is not greater than the set pressure, calculate the in-situ cutting volume at the ground speed; Determine whether the current ground speed reaches the set maximum speed, if so, end the calculation; Otherwise, increase the ground speed and return to the calculation step to continue the calculation; Finally, a production curve is calculated with the ground speed as the horizontal coordinate and the in-situ cutting amount as the vertical coordinate.

8. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 7 is characterized in that: The parameter processing unit is further used for: Input the fixed parameter group of the rake suction pipe, and perform parameterized modeling on the three-point suspended rake suction pipe system based on the fixed parameter group of the rake suction pipe; The fixed parameter group of the rake head is input, and the single-row rake tooth active rake head is parameterized modeled based on the fixed parameter group of the rake head; Input the fixed parameter group of rake head flushing, and perform parameterized modeling on the wear block flushing, rake tooth flushing and movable cover flushing on the rake head based on the fixed parameter group of rake head flushing; Input high-pressure flushing pump curve parameters and high-pressure flushing water pipeline characteristics, and calculate the high-pressure flushing water pump working point and the injection pressure speed at the nozzle based on the high-pressure flushing water pump curve parameters and high-pressure flushing water pipeline characteristics; Build the scouring model at the wear-resistant block of clay and saturated sand, and calculate the scouring depth and width based on the scouring model at the wear-resistant block; Build cutting models with different cutting angles for clay and saturated sand. The saturated sand cutting model also includes a model for the effect of rake flushing on cutting force. Input process parameters, and generate the real-time visualization status of the current rake tube and rake head based on the process parameters calculation; Based on the production model framework, the force balance and the dynamic state of the drag head at ground speed are iteratively calculated; After the iterative calculation is completed, the production curve, cutting depth curve, main force curve of the rake head and rake pipe, and the moment balance data of the rake head movable cover are output.

9. The intelligent management system for optimizing energy efficiency of dredgers based on the fuel consumption prediction model according to claim 6, characterized in that: The fuel consumption prediction unit is further used for: Extract key features based on the production curve, cutting depth curve, main force curve of the rake head and rake tube, and moment balance data of the rake head and rake cover, wherein the key features include average production, maximum cutting depth, peak force of the rake head and rake tube, and range of moment of the active cover; Establish a fuel consumption prediction model between fuel consumption and key characteristics based on linear regression fitting data; Bring historical data into the fuel consumption prediction model, perform verification training on the fuel consumption prediction model, and adjust the model parameters based on the verification results; When there is new working condition data, the working condition data is input into the model to obtain a predicted fuel consumption value, wherein the working condition data includes new production, cutting depth, and stress conditions.

Images