An intelligent working condition recommendation method and device for ship energy saving based on cleaning synergist

Abstract

The present invention relates to the field of ship energy conservation technology, and in particular to an intelligent working condition recommendation method and device based on ship energy conservation of detergent synergists, collecting original data of ship navigation conditions and original data of engine conditions, pre-processing to obtain ship navigation condition training data and engine condition training data; constructing a detergent synergist fuel saving rate model to obtain the correlation between engine conditions and fuel saving rate; constructing a fuel consumption rate model based on ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between ship navigation conditions, engine conditions and fuel consumption; cyclically judging to obtain the optimal combination of engine conditions and ship navigation conditions that achieve the best fuel saving effect under the maximum detergent synergist fuel saving rate and the best engine operating condition. The present invention forms intelligent working condition optimization recommendation by integrating fuel oil detergent synergist technology and intelligent data collection, energy saving and carbon reduction effect evaluation, and provides efficient and environmentally friendly solutions for the ship industry.

Description

Technical Field

[0001] The present invention relates to the technical field of ship energy conservation, and in particular to an intelligent working condition recommendation method and device for ship energy conservation based on a cleaning synergist. Background Art

[0002] As global attention to environmental protection and climate change increases, the shipping industry faces the urgent task of reducing greenhouse gas emissions. Marine fuel oil purifiers are chemical additives that can improve fuel combustion efficiency and reduce pollutant emissions, while intelligent operating condition recommendations use modern information technology, such as big data analysis, machine learning, and artificial intelligence, to monitor and optimize the operating status of ships in real time to achieve the dual goals of energy conservation and emission reduction. By integrating these two technologies, the present invention can not only further enhance the energy-saving effect of purifiers, but also intelligently plan and recommend the operating conditions of ships, thereby achieving significant energy-saving and emission reduction effects while ensuring the safety and economical operation of ships.

[0003] However, the energy-saving and emission-reduction effects of the actual application of marine fuel oil detergents and enhancers on board ships are affected by many factors, such as ship type, engine design, ship age, engine operating conditions, etc., so a systematic approach is needed to optimize its use. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent operating condition recommendation method and device for energy saving of ships based on cleaning enhancers, aiming to form intelligent operating condition optimization recommendations by integrating advanced fuel oil cleaning enhancer technology and intelligent data collection, energy saving and carbon reduction effect evaluation, and provide an efficient and environmentally friendly solution for the shipping industry.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] According to the first aspect of the present invention, the present invention claims protection for an intelligent working condition recommendation method for ship energy saving based on a detergent enhancer, comprising:

[0007] Collecting original data of ship navigation conditions and original data of engine conditions, preprocessing the original data of ship navigation conditions and original data of engine conditions to obtain ship navigation conditions training data and engine conditions training data;

[0008] Constructing a fuel saving rate model of a detergent enhancer according to the engine operating condition training data, and obtaining a correlation between the engine operating condition and the fuel saving rate through the detergent enhancer fuel saving rate model;

[0009] A fuel consumption rate model is constructed based on the ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between the ship navigation condition, the engine condition and the fuel consumption;

[0010] According to the correlation between the ship's navigation conditions, engine conditions and fuel consumption, the optimal combination of engine conditions and ship's navigation conditions that achieves the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is cyclically determined.

[0011] Furthermore, the collecting of the original data of the ship's navigation condition and the original data of the engine's condition also includes:

[0012] The original data of ship navigation conditions at least include:

[0013] Ship speed, ship draft, and sea condition level;

[0014] The engine operating condition raw data at least includes:

[0015] Speed, load, intake air temperature.

[0016] Further, the original ship navigation condition data and the original engine condition data are preprocessed to obtain ship navigation condition training data and engine condition training data, and further comprising:

[0017] Performing data cleaning operations on the original data of the ship's navigation condition and the original data of the engine condition to identify and remove abnormal values;

[0018] The original data of the ship's navigation condition and the original data of the engine's operating condition are subjected to data standardization processing, and the ship's navigation condition training data and the engine's operating condition training data are obtained by adopting a normalized method.

[0019] Furthermore, before constructing a detergent synergist fuel saving rate model based on the engine operating condition training data and obtaining the correlation between the engine operating condition and the fuel saving rate through the detergent synergist fuel saving rate model, the method further includes:

[0020] The navigation state of the ship is determined by clustering analysis of the navigation state of the ship according to the engine operating condition training data.

[0021] The engine operating condition training data under the same sailing state are obtained by respectively identifying the engine operating condition before and after the addition of the detergent enhancer and screening according to the difference range of the ship's sailing conditions.

[0022] Furthermore, a detergent synergist fuel saving rate model is constructed based on the engine operating condition training data, and a correlation between the engine operating condition and the fuel saving rate is obtained through the detergent synergist fuel saving rate model, which also includes:

[0023] Determining the input layer, output layer and hidden layer structure of the detergent synergist fuel saving rate model according to the engine operating condition training data;

[0024] Dividing the engine operating condition training data into a training set and a test set, defining a loss function, and using the training set to train the detergent synergist fuel saving rate model through a back propagation algorithm;

[0025] The test set is used to evaluate the fuel saving rate model of the detergent enhancer, optimize the fuel saving rate model of the detergent enhancer, and adjust the model structure and parameters.

[0026] Furthermore, a fuel consumption rate model is constructed based on the ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between the ship navigation condition, the engine condition and the fuel consumption, and further includes:

[0027] The output of the detergent synergist fuel saving rate model is introduced as a correction factor and embedded into the ship navigation condition training data;

[0028] The objective function is constructed and the relationship between the original data of ship navigation conditions, engine conditions and fuel consumption is analyzed.

[0029] Furthermore, according to the correlation between the ship's navigation conditions, engine conditions and fuel consumption, the optimal combination of engine conditions and ship's navigation conditions that achieves the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is determined cyclically, and further includes:

[0030] Genetic algorithm is used to optimize the working condition and determine the working condition constraints;

[0031] Determine the coding method and the first chromosome structure of the combination of the ship's navigation condition and the engine condition according to the real number coding;

[0032] Setting a population size, randomly generating an initial population of a combination of ship sailing conditions and engine conditions, and calculating the fuel consumption of the initial population;

[0033] Define a fitness function, calculate the fitness value of the chromosome structure, determine the selection probability of the first chromosome structure according to the fitness value and select a priority chromosome;

[0034] Determine the crossover probability of the priority chromosome, perform a crossover operation according to the crossover probability, randomly select a crossover point to exchange gene segments, and obtain a second chromosome;

[0035] Determine the mutation probability of the second chromosome, perform a mutation operation according to the mutation probability, randomly select mutation points for value replacement, and obtain a third chromosome;

[0036] The maximum number of iterations is set as the termination condition, and after it is determined that the termination condition is met, the operating condition combination represented by the chromosome with the highest fitness value in the current population is used as the optimal engine operating condition and ship navigation operating condition combination obtained by optimization.

[0037] According to the second aspect of the present invention, the present invention claims protection for an intelligent operating condition recommendation device for ship energy saving based on a cleaning synergist, comprising:

[0038] one or more processors;

[0039] A memory having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent operating condition recommendation method for ship energy saving based on detergent enhancers.

[0040] The present invention relates to the field of ship energy conservation technology, and in particular to an intelligent working condition recommendation method and device based on ship energy conservation of detergent synergists, collecting original data of ship navigation conditions and original data of engine conditions, pre-processing to obtain ship navigation condition training data and engine condition training data; constructing a detergent synergist fuel saving rate model to obtain the correlation between engine conditions and fuel saving rate; constructing a fuel consumption rate model based on ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between ship navigation conditions, engine conditions and fuel consumption; cyclically judging to obtain the optimal combination of engine conditions and ship navigation conditions that achieve the best fuel saving effect under the maximum detergent synergist fuel saving rate and the best engine operating condition. The present invention forms intelligent working condition optimization recommendation by integrating fuel oil detergent synergist technology and intelligent data collection, energy saving and carbon reduction effect evaluation, and provides efficient and environmentally friendly solutions for the ship industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A workflow diagram of an intelligent operating condition recommendation method for energy saving of ships based on a cleaning synergist as claimed in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0044] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0045] According to the first embodiment of the present invention, the present invention claims a method for intelligent working condition recommendation based on cleaning synergist for ship energy saving, referring to Figure 1 ,include:

[0046] Collecting original data of ship navigation conditions and original data of engine conditions, preprocessing the original data of ship navigation conditions and original data of engine conditions, and obtaining ship navigation conditions training data and engine conditions training data;

[0047] A fuel saving rate model of detergent enhancer is constructed based on the engine operating condition training data, and the correlation between the engine operating condition and the fuel saving rate is obtained through the detergent enhancer fuel saving rate model;

[0048] A fuel consumption rate model was constructed based on the ship's navigation condition training data and the detergent enhancer fuel saving rate model, and the correlation between the ship's navigation condition, engine condition and fuel consumption was obtained;

[0049] According to the correlation between ship navigation conditions, engine conditions and fuel consumption, the optimal combination of engine conditions and ship navigation conditions that can achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is obtained through cyclic judgment.

[0050] Furthermore, collecting the original data of the ship's navigation condition and the original data of the engine's condition also includes:

[0051] The original data of ship navigation conditions shall include at least:

[0052] Ship speed, ship draft, sea condition level (0~9);

[0053] The sea condition level is divided into 10 levels from 0 to 9 according to the classification of sea conditions by the meteorological department;

[0054] The original data of engine operating conditions shall include at least:

[0055] Speed, load, intake air temperature.

[0056] In this embodiment, the ship speed (v, knots), the ship draft (d, meters), the sea conditions (s, which can be divided into different levels from 0 to 9), the fuel consumption rate (F CR , g / kW·hour or kg / hour).

[0057] During the ship's voyage, the ship's comprehensive data collection system is used to continuously record the engine's various operating parameters and fuel consumption data. For the engine operating conditions, in addition to the three main parameters of speed, load, and intake temperature, auxiliary parameters such as exhaust temperature, fuel injection pressure, and intake pressure can also be recorded to more comprehensively describe the engine operating conditions. The data in Table 1 below are obtained.

[0058] Table 1 Example of data obtained

[0059]

[0060] Before adding detergent, collect data at fixed time intervals (e.g. every 10 seconds) and mark these data as "before addition". The data record should include an accurate time stamp to facilitate subsequent data matching.

[0061] Determine the addition ratio of the detergent enhancer. In the construction of this model, the addition ratio of the detergent enhancer is fixed, for example, it is added at 1‰ (one thousandth) of the fuel mass.

[0062] After the detergent booster is added, continue to collect data at the same time intervals and mark these data as "after addition" data.

[0063] Further, the original data of ship sailing condition and the original data of engine condition are preprocessed to obtain ship sailing condition training data and engine condition training data, and further includes:

[0064] Perform data cleaning operations on the original data of ship navigation conditions and engine operating conditions to identify and remove abnormal values;

[0065] The original data of the ship's sailing condition and the original data of the engine's condition are subjected to data standardization, and the ship's sailing condition training data and the engine's condition training data are obtained by normalization. In this embodiment, for example, if the engine speed obviously exceeds its normal working range (determined according to the technical specifications of the engine), such as the rated speed of a low-speed ship engine is 60-120 rpm, if a value of 1000 rpm appears, it is determined as an abnormal value and removed.

[0066] For fuel consumption data, if there is a sudden maximum or minimum value (the difference is too large compared with the previous and subsequent data), it will also be treated as an outlier and processed.

[0067] Furthermore, before constructing a detergent synergist fuel saving rate model based on the engine operating condition training data and obtaining the correlation between the engine operating condition and the fuel saving rate through the detergent synergist fuel saving rate model, the method further includes:

[0068] The navigation status of the ship is determined by clustering analysis based on the engine operating condition training data.

[0069] The engine operating condition training data under the same sailing state are obtained by respectively identifying the engine operating condition before and after the addition of the detergent enhancer and screening according to the difference range of the ship's sailing conditions.

[0070] In this embodiment, the navigation state of the ship is divided into different categories, such as the acceleration stage of sailing, the constant speed cruising stage, the deceleration stage of docking, etc. The navigation state is determined according to the speed, rudder angle and other parameters of the ship.

[0071] Before and after dosing, find the data in the same navigation state (cruise, acceleration, deceleration). For example, in the acceleration stage of sailing, the load and speed of the engine change in a certain pattern. In the data of the acceleration stage of sailing before dosing and the acceleration stage of sailing after dosing, screen according to the difference range of the main operating parameters (speed, load, intake temperature) to determine the engine operating data that is consistent before and after dosing. The present invention proposes to match the operating conditions of cruising, acceleration, and deceleration stages respectively. Due to space limitations, the present invention takes the cruising state as an example for explanation.

[0072] For example, the acceleration of the ship is calculated based on Formula 2, and it is determined whether it is in the cruising state. i The absolute value is less than 0.15m / s 2 For cruising; i Greater than or equal to 0.15m / s 2 To accelerate; a iLess than or equal to -0.15m / s 2 To slow down.

[0073] (Formula 2)

[0074] in:

[0075] a i , acceleration of the ship, m / s 2 ;

[0076] v i , ship speed, knots.

[0077] i represents the current time, i+1 represents the next 10 seconds, and i-1 represents the previous 10 seconds, that is, it represents the previous and next two collected data.

[0078] Based on formula 2, the working condition judgment of the ship cruising (or acceleration, deceleration) is obtained.

[0079] Furthermore, a detergent synergist fuel saving rate model is constructed based on the engine operating condition training data, and the correlation between the engine operating condition and the fuel saving rate is obtained through the detergent synergist fuel saving rate model, which also includes:

[0080] Determine the input layer, output layer and hidden layer structure of the detergent enhancer fuel saving rate model based on the engine operating condition training data;

[0081] The engine operating condition training data is divided into a training set and a test set, a loss function is defined, and the training set is used to train the detergent enhancer fuel saving rate model through the back propagation algorithm;

[0082] The test set is used to evaluate the detergent enhancer fuel saving rate model, optimize the detergent enhancer fuel saving rate model, and adjust the model structure and parameters.

[0083] Among them, in this embodiment, since we are mainly concerned with the influence of the speed, load and intake temperature of the ship engine on the fuel saving rate of the detergent enhancer, the number of input layer nodes is 3, corresponding to the three operating parameters of the engine speed, load and intake temperature.

[0084] The number of nodes in the output layer is 1, corresponding to the target variable of fuel saving rate.

[0085] We chose to set up 2 hidden layers. The first hidden layer has 5 nodes, and the second hidden layer has 3 nodes. This structure was chosen based on experience and experiments, and is designed to better capture the complex nonlinear relationship between input variables and output variables.

[0086] Before dividing the engine operating condition training data into training set and test set, data standardization is also included;

[0087] Specifically, since the data of engine speed, load, and intake temperature are of different magnitudes, they need to be standardized and converted to the same magnitude so that the neural network can be better trained.

[0088] Using normalization method, for example, for the speed r (Assuming the value range is [r min , r max ], the normalized formula is Equation 1, for load L (value range is [0%, 100%]) and intake air temperature T (assuming the value range is [T min , T max ]) is also processed using a similar normalization formula.

[0089] (Formula 1)

[0090] in:

[0091] r’ i , normalized speed, dimensionless;

[0092] r i , actual engine speed, rpm;

[0093] r min , the actual minimum speed of the engine, rpm;

[0094] r max , the actual maximum operating speed of the engine, rpm.

[0095] The preprocessed data is divided into a training set and a test set in a ratio of 80% and 20%. For example, if there are 1,000 sets of data in total, 800 sets are used as training sets and 200 sets are used as test sets.

[0096] The mean square error (MSE) is used as the loss function, and the calculation formula is shown in Equation 2.

[0097] (Formula 2)

[0098] in:

[0099] n , the number of data points in the training set;

[0100] j i , the fuel saving rate of the ith data point predicted by the neural network;

[0101] , the actual fuel saving rate of the ith data point.

[0102] The training set data is input into the neural network, and the back-propagation algorithm is used to adjust the weights of the neural network.

[0103] In each iteration, the MSE loss between the predicted fuel saving rate and the actual fuel saving rate is calculated.

[0104] According to the loss value, the connection weights between nodes in each layer are adjusted from the output layer to the input layer through the back propagation algorithm, so that the value of the loss function gradually decreases. For example, in the initial training, the weights are randomly initialized, and as the training progresses, the weights are continuously updated to better fit the relationship between the input data and the output data.

[0105] Input the test set data into the trained neural network model to obtain the fuel saving rate predicted by the model.

[0106] Calculate the root mean square error (RMSE), the calculation formula is shown in formula 3. The smaller the RMSE value, the higher the prediction accuracy of the model.

[0107] (Formula 3)

[0108] in:

[0109] m , the number of test set data points;

[0110] j i , the fuel saving rate of the ith data point predicted by the neural network;

[0111] , the actual fuel saving rate of the ith data point.

[0112] If the evaluation indicators of the model are not ideal, such as a large RMSE, you can consider adjusting the structure of the neural network.

[0113] Increase the number of nodes in the hidden layer, such as increasing the number of nodes in the first hidden layer from 5 to 7, and increasing the number of nodes in the second hidden layer from 3 to 5.

[0114] Or increase the number of hidden layers, such as increasing it to 3 hidden layers.

[0115] Adjust training parameters, such as the learning rate. If the learning rate is too large, the model may not converge; if the learning rate is too small, the training speed will be very slow. You can try different learning rate values, such as starting from 0.001, and observe the training effect of the model.

[0116] Adjust the number of iterations, increase or decrease it, and find the number of iterations that gives the best model performance.

[0117] Specific implementation cases:

[0118] 1) Model construction

[0119] A multi-layer neural network was constructed, including an input layer (3 neurons, corresponding to the three input features of speed, load and intake temperature), two hidden layers (64 and 32 neurons respectively, with ReLU activation function) and an output layer (1 neuron, corresponding to fuel saving rate). A linear relationship model was initially obtained.

[0120] (Formula 3)

[0121] in:

[0122] bθ is the intercept, b1, b2 and b3 are the coefficients corresponding to speed, load and intake temperature respectively

[0123] 2) Training and Evaluation

[0124] The model was trained for 100 epochs (epochs = 100) using the training set with a batch size of 32 (batch_size = 32).

[0125] The mean square error (MSE) is calculated on the test set. The value of the mean square error represents the average square difference between the predicted value and the true value. The smaller the value of MSE, the better the prediction effect of the model on the test set. For example, if the value of MSE is 0.1, it means that on average, the square difference between the predicted fuel saving rate and the true fuel saving rate is 0.1.

[0126] 3) Prediction

[0127] Use the trained model to predict the test set. j _pred, in practical applications, the relationship between the predicted value and the true value can be further analyzed, such as calculating the error distribution between the predicted value and the true value, drawing a scatter plot, etc., to more comprehensively evaluate the performance of the model. In practical applications, real ship engine data needs to be used, and more adjustments and optimizations may be required to the model structure and hyperparameters.

[0128] Furthermore, a fuel consumption rate model is constructed based on the ship navigation condition training data and the detergent enhancer fuel saving rate model to obtain the correlation between the ship navigation condition, engine condition and fuel consumption, and also includes:

[0129] The output of the detergent-enhancing agent fuel saving rate model is introduced as a correction factor and embedded into the ship's navigation condition training data;

[0130] The objective function is constructed and the relationship between the original data of ship navigation conditions, engine conditions and fuel consumption is analyzed.

[0131] In this embodiment, it is assumed that the original engine operating condition, ship sailing condition and fuel consumption rate model are F CR = f(r, L, T, v, d, s) , the nested model becomes F’ CR’ = f(r, L, T, v, d, s) × (1 - J) , where J is the ship engine operating condition and the detergent enhancement fuel saving rate model according to the engine operating condition (r, L, T) Predicted fuel saving rate.

[0132] In order to achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions, the objective function is established.

[0133] Fuel consumption F C =F’ CR × P × t, in P is the engine power (with r and L related, P = f(n, L) ), t = D / v (D is the flight distance). So the objective function is F Cmin = f(r, L, T, v, d, s) × (1 - J) × f(n, L) × D / v

[0134] Furthermore, according to the correlation between the ship's navigation conditions, engine conditions and fuel consumption, the optimal combination of the engine conditions and the ship's navigation conditions that achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is cyclically determined, and also includes:

[0135] Genetic algorithm is used to optimize the working condition and determine the working condition constraints;

[0136] Determine the coding method and the first chromosome structure of the combination of the ship's navigation condition and the engine condition according to the real number coding;

[0137] Set the population size, randomly generate the initial population of the ship's navigation conditions and engine conditions, and calculate the fuel consumption of the initial population;

[0138] Define a fitness function, calculate the fitness value of the chromosome structure, determine the selection probability of the first chromosome structure according to the fitness value and select the priority chromosome;

[0139] Determine the crossover probability of the priority chromosome, perform a crossover operation based on the crossover probability, randomly select a crossover point to exchange gene fragments, and obtain the second chromosome;

[0140] Determine the mutation probability of the second chromosome, perform mutation operation according to the mutation probability, randomly select mutation points for value replacement, and obtain the third chromosome;

[0141] The maximum number of iterations is set as the termination condition. After the termination condition is determined to be met, the operating condition combination represented by the chromosome with the highest fitness value in the current population is used as the optimal engine operating condition and ship navigation operating condition combination obtained by optimization.

[0142] In this embodiment, the operating condition constraint is determined for the engine operating condition constraint:

[0143] 1) Engine operating condition constraints

[0144] The engine speed range is r min =30 rpm to r max =120 rpm.

[0145] Load range is L min =30% to L max =80%.

[0146] The intake air temperature range is T min =0℃ to T max =40℃.

[0147] 2) Ship navigation condition constraints

[0148] Speed ​​constraint: According to the ship design and route regulations, the minimum speed v min =5 knots, maximum speed v max =16 sections.

[0149] Draft depth constraint: Due to the port water depth and ship load, the draft depth range is d min =5m to d max =10 meters.

[0150] Sea conditions: The main sea conditions faced by this route are level 1-3, and restrictions are imposed during the optimization process based on the safety requirements for navigation under different sea conditions.

[0151] When determining the encoding method, real number encoding is used for continuous variables in engine operating conditions (speed r, load L, intake temperature T) and ship navigation conditions (speed V, draft d, sea state s).

[0152] A chromosome represents a combination of an engine operating condition and a ship sailing condition. Assume that the chromosome structure is [n, L, T, v, d, s], where each element is a real number represented by the above encoding method.

[0153] Set the population size to N, for example N = 100.

[0154] N chromosomes are randomly generated within the value range of each variable, that is, N groups of combinations of engine operating conditions and ship sailing conditions are randomly generated.

[0155] According to the nested fuel consumption model F Cmin = f(r, L, T, v, d, s) × (1 - J) × f(r, L) × D / v , for each chromosome in the population (i.e. each set of operating conditions), calculate its corresponding fuel consumption F C .

[0156] in, f(r, L, T, v, d, s) It is the relationship function between engine operating conditions, ship sailing conditions and fuel consumption rate. J It is the fuel saving rate predicted by the fuel saving rate model of the ship engine and the detergent enhancer according to the current engine operating conditions (r, L, T). f(r, L) It is a function of the relationship between engine power, speed and load. D is the voyage distance (assumed to be 1000 nautical miles), and v is the speed.

[0157] The fitness function Fitness is defined as the fuel consumption F C The reciprocal of Fitness = 1 / Fc The purpose is to make the chromosome with smaller fuel consumption have higher fitness.

[0158] According to the fitness value of each chromosome, the probability of its being selected is calculated.

[0159] Using roulette wheel selection, chromosome i The probability of selection

[0160] in, Fitness i is the fitness value of the i-th chromosome; Represents the sum of the fitness values ​​of all individuals in the population. This formula shows that the larger the individual fitness value, the greater the probability of being selected.

[0161] According to the calculated selection probability, N chromosomes are selected from the population to form a new population. During the selection process, chromosomes with high fitness have a greater probability of being selected.

[0162] Set the crossover probability to P c ,For example P c = 0.8.

[0163] For each pair of chromosomes in the new population (randomly paired), the crossover probability P c Determines whether to perform crossover operation.

[0164] If a crossover operation is performed, a crossover point is randomly selected and two chromosomes are exchanged at the crossover point to obtain two new chromosomes. 1 , L 1 , T 1 , v 1 , d 1 ,s 1 ] and [r 2 , L 2 , T 2 , v 2 , d 2 ,s 2 ], assuming that the crossover point is after the load L, after the crossover, we get [r 1 , L 1 , T 2 , v 2 , d 2 ,s 2 ] and [r 2 , L 2 , T 1 , v 1 , d 1 ,s 1 ].

[0165] Set the mutation probability to P m ,For example P m = 0.1.

[0166] For each chromosome in the new population, the mutation probability P m Decide whether to perform a mutation operation.

[0167] If a mutation operation is performed, a mutation point (i.e., a working condition variable) is randomly selected, and a new value is randomly generated within the value range of the variable to replace the original value. For example, for chromosome [r, L, T, v, d, s], if the engine speed is selected r To mutate, in [r min , r max ] A new speed value is randomly generated to replace the original r value.

[0168] You can set the maximum number of iterations Max Iter As a termination condition, such as Max Iter = 500.

[0169] Alternatively, the iteration can be stopped when the average fitness of the population has not improved significantly in several consecutive generations.

[0170] If the termination condition is met, the iteration stops, and the operating condition combination represented by the chromosome with the highest fitness in the current population is the optimal engine operating condition and ship navigation operating condition combination obtained by optimization.

[0171] If the termination condition is not met, return to step 4 (select operation) to continue the next round of iteration.

[0172] After multiple iterations, it is assumed that the optimal chromosome obtained is [r=102, L=50%, T=30℃, v=12 knots, d=8 meters, s=2]. This is the optimal combination of engine operating conditions (speed of 102 rpm, load of 50%, intake air temperature of 30°C) and ship sailing conditions (speed of 12 knots, draft of 8 meters, sea condition of level 2) to achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best operating conditions of the engine. Shipping companies can effectively reduce fuel consumption by sailing ships according to this combination of operating conditions. If certain external conditions change, the parameters can be fixed and the optimal solution of other controllable parameters can be calculated using the same method.

[0173] Based on the above method, what is finally obtained is the optimal combination of engine operating conditions (including engine speed, load, intake temperature, etc.) and ship navigation conditions (including speed, draft depth, sea conditions, etc.) that achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions.

[0174] According to the second embodiment of the present invention, the present invention claims protection for an intelligent operating condition recommendation device for ship energy saving based on a cleaning synergist, comprising:

[0175] one or more processors;

[0176] A memory having one or more programs stored thereon, when the one or more programs are executed by one or more processors, enables the one or more processors to implement an intelligent working condition recommendation method for ship energy saving based on a detergent enhancer.

[0177] Among them, in this embodiment, a universal data interface is developed to connect various existing subsystems of the ship, such as the ship's voyage data recorder (VDR), the ship's navigation system, the power system (including fuel flow monitoring), draft sensors, cargo management systems, and existing environmental monitoring equipment. These interfaces are compatible with different types of communication protocols and data formats to ensure smooth data acquisition. For example, for navigation equipment using the NMEA 0183 protocol and power system equipment using the CAN bus protocol, the data interface unit can perform protocol conversion to achieve data interaction;

[0178] Collect relevant data from each subsystem and integrate them. For example, obtain the ship's position (longitude, latitude), speed and heading from the navigation system; obtain engine speed, torque, fuel consumption rate and other information from the power system; obtain draft data from the ship's draft sensor; obtain cargo weight and cargo distribution (such as front and back, left and right weight distribution ratio) from the cargo management system; obtain meteorological data such as wind speed, wind direction, and temperature from existing meteorological equipment, and obtain water depth data from ship-borne depth sounding equipment. Organize these data in a unified format for subsequent processing;

[0179] Receive various data from the data integration module and perform preliminary preprocessing on the data, such as data cleaning (removing outliers), data format standardization, etc. Set different collection frequencies according to the importance and frequency of data changes. For example, key navigation data such as ship position and speed are collected once per second; data with relatively slow changes such as cargo weight are collected every 10 seconds;

[0180] The central processing unit (CPU) performs in-depth comprehensive analysis and processing on the collected data. Based on the ship's real-time position, speed, heading, weather conditions, engine operating conditions, cargo conditions and other factors, the optimal operating condition recommendation is calculated based on the solution of the present invention;

[0181] Utilize the existing internal communication network of the ship, such as Ethernet or CAN bus, to achieve efficient data communication between various subsystems within the ship. Ensure smooth data interaction between the data integration module, data processing and control module, and other related equipment on the ship (such as the ship's automatic identification system (AIS), electronic chart display and information system (ECDIS), etc.);

[0182] Use the ship's original communication equipment, such as very high frequency (VHF) communication equipment for voice communication with nearby ships and shore base stations; satellite communication equipment for long-distance data transmission, such as sending the ship's navigation data, fault information, etc. to the headquarters of the ship management company or the maritime management department, and receiving navigation warnings, weather forecasts and other information from the outside world;

[0183] The existing display screen on the ship's bridge is used to display various navigation information of the ship in the form of intuitive graphics, charts and numbers, as well as the best navigation condition selection under the current status.

[0184] This embodiment achieves functional integrity and ensures that the system can fully realize the functions of ship navigation data collection, processing and working condition optimization. For example, data such as ship position and speed are collected and input into the algorithm model to output the optimal working condition recommendation result.

[0185] Provides a simple and unified external interface to facilitate external inquiries on ship status or acquisition of relevant data.

[0186] Data level: Determine the processing flow of data collected from various subsystems of the ship within the package, including from data integration to processing to algorithm model, and clarify the output data type.

[0187] Functional modules: clearly define the modules involved in encapsulation, such as data integration, processing and control, communication, display and interaction modules, and algorithm models.

[0188] Define a unified internal data structure, such as a structure to store ship navigation data (position, speed, engine condition, weather data, etc.). For example, in C language:

[0189] struct ShipData {

[0190] double longitude;

[0191] double latitude;

[0192] double speed;

[0193] double course;

[0194] double engine_rpm;

[0195] double engine_torque;

[0196] double fuel_consumption_rate;

[0197] double draft;

[0198] double cargo_weight;

[0199] double wind_speed;

[0200] double wind_direction;

[0201] double air_temperature;

[0202] };

[0203] ```

[0204] Convert and standardize the collected data, unify the units and quantify special data to meet the internal data structure requirements.

[0205] The intelligent working condition recommendation algorithm model is integrated into the data processing and control module, and interacts through function calls or message passing. For example, in object-oriented programming, the class in the data processing and control module contains the algorithm model class object and calls its method calculation.

[0206] Integrate the communication and display modules to ensure that the communication module transmits data correctly, and intuitively display the algorithm model results in the display and interaction module, such as displaying the optimal working conditions with a dashboard.

[0207] External interface definition:

[0208] Query interface: Provides a query interface to obtain ship information, such as the function in Python:

[0209] Python

[0210] def get_ship_status():

[0211] ship_status = {

[0212] "longitude": 120.0,

[0213] "latitude": 30.0,

[0214] "speed": 10.0,

[0215] "course": 90.0,

[0216] "optimal_condition": {

[0217] "engine_rpm": 1500,

[0218] "speed": 12.0

[0219] }

[0220] }

[0221] return ship_status

[0222] Control interface (if any): Define the control interface if the permissions allow, such as the example in Java:

[0223] java

[0224] public class ShipControl {

[0225] public boolean set_target_speed(double speed) {

[0226] if (speed >= 0 && speed <= 30) {

[0227] / / Actual control logic

[0228] return true;

[0229] }

[0230] return false;

[0231] }

[0232] }

[0233] Interface security and permission management:

[0234] Set up an authentication mechanism for the external interface, such as username and password or digital certificate authentication.

[0235] Different permissions are assigned to different users or systems, such as ship operators, management company headquarters, and maritime management departments each have corresponding permissions.

[0236] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0237] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0238] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. An intelligent working condition recommendation method for ship energy saving based on detergent synergist, characterized in that: include: Collecting original data of ship navigation conditions and original data of engine conditions, preprocessing the original data of ship navigation conditions and original data of engine conditions to obtain ship navigation conditions training data and engine conditions training data; Constructing a fuel saving rate model of a detergent enhancer according to the engine operating condition training data, and obtaining a correlation between the engine operating condition and the fuel saving rate through the detergent enhancer fuel saving rate model; A fuel consumption rate model is constructed based on the ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between the ship navigation condition, the engine condition and the fuel consumption; According to the correlation between the ship's navigation conditions, engine conditions and fuel consumption, the optimal combination of engine conditions and ship's navigation conditions that achieves the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is determined cyclically; The method of constructing a detergent synergist fuel saving rate model based on the engine operating condition training data, and obtaining a correlation between the engine operating condition and the fuel saving rate through the detergent synergist fuel saving rate model, further includes: Determining the input layer, output layer and hidden layer structure of the detergent synergist fuel saving rate model according to the engine operating condition training data; Dividing the engine operating condition training data into a training set and a test set, defining a loss function, and using the training set to train the detergent synergist fuel saving rate model through a back propagation algorithm; Using the test set to evaluate the fuel saving rate model of the detergent enhancer, optimizing the fuel saving rate model of the detergent enhancer, and adjusting the model structure and parameters; The method of constructing a fuel consumption rate model based on the ship navigation condition training data and the detergent synergist fuel saving rate model to obtain the correlation between the ship navigation condition, the engine condition and the fuel consumption also includes: The output of the detergent-boosting agent fuel saving rate model is introduced as a correction factor and embedded into the ship navigation condition training data; The objective function is constructed and the relationship between the original data of ship navigation conditions, engine conditions and fuel consumption is analyzed.

2. The intelligent working condition recommendation method for ship energy saving based on detergent synergist according to claim 1 is characterized in that: The collecting of the original data of the ship's navigation condition and the original data of the engine's condition also includes: The original data of ship navigation conditions at least include: Ship speed, ship draft, and sea condition level; The engine operating condition raw data at least includes: Speed, load, intake air temperature.

3. The intelligent working condition recommendation method for ship energy saving based on detergent synergist according to claim 1 is characterized in that: Preprocessing the original ship navigation condition data and the original engine condition data to obtain ship navigation condition training data and engine condition training data also includes: Performing data cleaning operations on the original data of the ship's navigation condition and the original data of the engine condition to identify and remove abnormal values; The original data of the ship's navigation condition and the original data of the engine's operating condition are subjected to data standardization processing, and the ship's navigation condition training data and the engine's operating condition training data are obtained by adopting a normalized method.

4. The intelligent working condition recommendation method for ship energy saving based on detergent synergist according to claim 1 is characterized in that: Before constructing a detergent synergist fuel saving rate model based on the engine operating condition training data and obtaining the correlation between the engine operating condition and the fuel saving rate through the detergent synergist fuel saving rate model, the method further includes: Performing cluster analysis on the navigation status of the ship according to the engine operating condition training data to determine the navigation status of the ship; The engine operating condition training data under the same sailing state are obtained by respectively identifying the engine operating condition before and after the addition of the detergent enhancer and screening according to the difference range of the ship's sailing conditions.

5. The intelligent working condition recommendation method for ship energy saving based on detergent synergist according to claim 1 is characterized in that: According to the correlation between the ship's navigation conditions, engine conditions and fuel consumption, the optimal combination of engine conditions and ship's navigation conditions that achieve the best fuel saving effect under the maximum fuel saving rate of the detergent enhancer and the best engine operating conditions is determined cyclically, and also includes: Genetic algorithm is used to optimize the working condition and determine the working condition constraints; Determine the coding method and the first chromosome structure of the combination of the ship's navigation condition and the engine condition according to the real number coding; Setting a population size, randomly generating an initial population of a combination of ship sailing conditions and engine conditions, and calculating the fuel consumption of the initial population; Define a fitness function, calculate the fitness value of the chromosome structure, determine the selection probability of the first chromosome structure according to the fitness value and select a priority chromosome; Determine the crossover probability of the priority chromosome, perform a crossover operation according to the crossover probability, randomly select a crossover point to exchange gene segments, and obtain a second chromosome; Determine the mutation probability of the second chromosome, perform a mutation operation according to the mutation probability, randomly select mutation points for value replacement, and obtain a third chromosome; The maximum number of iterations is set as the termination condition, and after it is determined that the termination condition is met, the operating condition combination represented by the chromosome with the highest fitness value in the current population is used as the optimal engine operating condition and ship navigation operating condition combination obtained by optimization.

6. An intelligent working condition recommendation device for ship energy saving based on cleaning synergist, characterized in that: include: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement an intelligent operating condition recommendation method for ship energy saving based on a detergent enhancer according to any one of claims 1 to 5.

Images