Ship sewage disposal strategy generation technology based on operation parameters

Abstract

The invention discloses a ship decontamination strategy generation technology based on operation parameters. The technology comprises the steps of obtaining operation parameter data; assigning scores to continuous berthing and non-continuous berthing of the ship at different seawater temperatures; constructing a host theoretical fuel consumption model to calculate a theoretical fuel consumption standard, obtaining actual fuel consumption of a host every day, comparing the actual fuel consumption with the standard, obtaining a standard ratio, and assigning a score; acquiring fuel consumption data of constant-speed sailing, comparing actual fuel consumption of a host every day with the standard and assigning a score; acquiring a historical fuel consumption data mean value, and comparing the actual fuel consumption of the host every day with the mean value and assigning a score; accumulating assigned scores to obtain the state of the sewage bottom, and confirming a final sewage disposal port; when the method is applied, the dirty bottom state of the ship is comprehensively evaluated from multiple angles through multi-dimensional data during ship operation, the comprehensiveness of evaluation is improved, the influence of the temperature on marine organisms, dynamic oil consumption and other situations are further excavated, the potential influence of the dirty bottom can be reflected more accurately, and then the accuracy of a judgment result is improved. Therefore, the method is high in accuracy.

Description

Technical Field

[0001] The invention relates to a pollution cleaning strategy, belonging to the technical field of ship energy conservation and environmental protection, and in particular to a ship pollution cleaning strategy generation technology based on operating parameters. Background Art

[0002] Since the ship is in the seawater for a long time, many marine organisms will inevitably attach to the underwater part of the ship, causing the ship to be fouled. The fouling of the ship will increase the roughness of the hull surface, thereby increasing the friction resistance between the ship and the water, thus affecting the ship's propulsion performance, causing excessive energy consumption and rising fuel costs. Since the bottom of the ship is underwater, it is difficult for the crew to directly observe the state of the bottom. Whether the bottom of the ship is fouled depends only on the existing ship management experience. However, personal ship management experience has problems such as untimely discovery and cleaning, lack of accuracy, and low efficiency, which will miss the best time for cleaning, making the prevention and treatment of bottom fouling complicated and challenging.

[0003] At present, there are mainly the following means to monitor the bottom of ships: the first is to take photos of the bottom of the ship by divers, but this method requires a lot of manpower and material resources, and the safety of divers cannot be guaranteed; the second is to take photos of the bottom of the ship by fully submerged underwater robots or shore-based underwater high-definition cameras, but this method is not only expensive, but also complicated to operate remotely and inefficient; the third is to use the operational data of the ship's navigation for evaluation. This method is mainly for ships with navigation data collection. By calculating the fuel consumption data of the ship under the conditions of wind resistance and wave resistance, it is deduced whether the bottom of the ship is fouled. This method is more accurate for calculations such as wind resistance, but for the calculation of wave resistance, which is extremely nonlinear, its estimation accuracy is far from meeting the requirements, and most ships do not have the ability to collect high-precision data such as wind resistance and wave resistance data in real time, resulting in a narrow scope of application. Therefore, there is an urgent need for a ship bottom fouling cleaning strategy with high accuracy and wide application range to solve the above-mentioned defects in the existing technology. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects and problems existing in the prior art and to provide a ship pollution cleaning strategy generation technology based on operating parameters with high accuracy and wide application range.

[0005] To achieve the above objectives, the technical solution of the present invention is: a ship pollution cleaning strategy generation technology based on operating parameters, including:

[0006] S1. Obtaining the operating parameter data of the ship; the operating parameter data includes berthing data, navigation data, data on suitable growth of marine organisms, fuel consumption data, ship parameters, and weather data;

[0007] S2. acquiring continuous mooring data from the mooring data, and assigning points to the continuous mooring of the ship at different seawater temperatures based on the suitable growth data of marine organisms, to obtain continuous mooring points;

[0008] S3, obtaining total berthing time data and non-continuous berthing data from the berthing data, and obtaining total sailing time from the sailing data, and then calculating and scoring the non-continuous berthing ratio to obtain the non-continuous berthing scoring value;

[0009] S4. Construct a theoretical fuel consumption model for the main engine and calculate the theoretical fuel consumption standard. Then, obtain the actual daily fuel consumption of the main engine of the ship from the fuel consumption data. Compare the actual daily fuel consumption of the main engine with the theoretical fuel consumption standard to obtain the deviation ratio and assign a score to obtain the fuel consumption model scoring value.

[0010] S5. Obtaining the fuel consumption data for constant speed sailing from the navigation data and the fuel consumption data, and comparing and scoring the actual daily fuel consumption of the main engine in the fuel consumption data for constant speed sailing with the theoretical fuel consumption standard to obtain a fuel consumption scoring value for constant speed sailing;

[0011] S6. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data and calculate the average value, then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average value and manually assign points to obtain a manual marking score value;

[0012] S7, accumulating the scoring values ​​obtained in steps S2-S6 to obtain a final ship fouling score, and judging the fouling status of the ship based on the final ship fouling score; the judgment result includes any one of no fouling or no impact of fouling, suspected fouling, and serious fouling, and when the judgment result is serious fouling, proceed to step S8;

[0013] S8. Based on the current position of the ship, obtain the data of all ports that can be cleaned along the route, and confirm the final port of cleanup with the goal of arriving at the destination port on time and at the lowest cost.

[0014] The step S2 specifically includes:

[0015] When the seawater temperature is 5℃-15℃, the scoring expression for continuous mooring at this temperature is as follows:

[0016]

[0017] Where: n is the continuous berthing time of n days, a i is the i-th day of the continuous parking time, t 1 is the score assignment, D 连 The number of days the ship has been moored continuously when the marine organisms begin to grow and attach, m 1 is the suspension factor;

[0018] When the seawater temperature is 15℃-25℃, the scoring expression for continuous mooring at this temperature is as follows:

[0019]

[0020] Where: b j is the jth day of the continuous parking time, t 2 is the score, m 2 is the suspension factor;

[0021] When the seawater temperature of the ship is 25℃-35℃, the scoring expression for continuous mooring at this temperature is as follows:

[0022]

[0023] Where: c e is the e-th day of the continuous parking time, t 3 is the score, m 3 is the suspension factor;

[0024] The continuous mooring score x1 is calculated by integrating the continuous mooring score of the ship at different seawater temperatures; the expression of the continuous mooring score is as follows:

[0025]

[0026] The stop coefficient m 1 、m 2 、m 3 It is used to reflect the growth rate of marine organisms at the bottom of the ship, and its expression is as follows:

[0027] m 1 , m 2 , m 3 =Q+W*R+Y*M+F*V+G*O;

[0028] Among them: Q is a constant term, representing the basic suspension value; W is the coefficient of the offshore distance R; Y is the coefficient of the marine organism density M; F is the coefficient of the water flow velocity V; G is the coefficient of the season O.

[0029] The step S3 specifically includes:

[0030] The non-continuous mooring data refers to data that is less than the number of days that the mooring has been continuous when the marine organisms begin to grow and attach;

[0031] The expression of the non-continuous parking ratio is as follows:

[0032] P=(D 非 / S)*100%;

[0033] Where: P is the proportion of non-continuous parking, D非 is the duration of non-continuous berthing, S is the sum of total berthing time and total sailing time;

[0034] Calculate the non-continuous parking score based on the non-continuous parking percentage;

[0035] If P < 30%, the non-continuous parking score is zero; if P > 30%, the non-continuous parking score is calculated according to the following expression:

[0036] x2=100*(P-30%).

[0037] The step S4 specifically includes:

[0038] S41, constructing a theoretical fuel consumption model of the main engine; the theoretical fuel consumption model of the main engine includes: an empirical value theoretical standard model, a big data theoretical standard model, and a unit consumption calculation theoretical standard model;

[0039] The empirical value theoretical standard model: by obtaining the fuel consumption standards of the sister ship group under no-load and full-load conditions, and combining the historical fuel consumption data of the sister ship group, a theoretical fuel consumption standard H based on the empirical value is obtained;

[0040] The big data theoretical standard model: by obtaining the fuel consumption data of the sister ship group when the main engine speed is the same and the empty and full load, and performing big data analysis based on the navigation data of the ship in unit time, a theoretical fuel consumption standard D based on big data is obtained;

[0041] The unit consumption calculation theoretical standard model: by obtaining the fuel consumption data of the sister ship group, and calculating the fuel consumption per nautical mile and the average value, the unit consumption calculation theoretical standard S is obtained;

[0042] S42. Obtain the actual daily fuel consumption E of the main engine of the ship from the fuel consumption data, and compare the actual daily fuel consumption E of the main engine with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation to obtain the deviation ratios A, B, and C; the details are as follows:

[0043] The deviation ratio A of the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard H based on the empirical value is as follows:

[0044] A=(EH) / H*100%;

[0045] The deviation ratio B between the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard D based on big data is as follows:

[0046] B = (ED) / H * 100%;

[0047] The deviation ratio C of the actual daily main engine fuel consumption E and the theoretical standard S for unit consumption calculation is as follows:

[0048] C = ((E*1000) / dS) / S*100%;

[0049] Where: d is the daily ship sailing distance;

[0050] S43, based on the deviation ratios A, B, and C, obtaining a fuel consumption model scoring value; the fuel consumption model scoring value includes any one or any combination of the following:

[0051] The first type: If the deviation ratio of any two of A, B, and C is ≥5%, the fuel consumption model score is: x3 = 1*T 好 ;

[0052] The second type: If the deviation ratio of any two of A, B, and C is less than 0%, the fuel consumption model score is: x4 = -1*T 好 ;

[0053] Where: T 好 It is the number of days with good weather during the ship's voyage.

[0054] The step S5 specifically includes:

[0055] S51. Obtaining constant speed sailing fuel consumption data from the navigation data and the fuel consumption data; the constant speed sailing fuel consumption data refers to data that meets the above conditions for three consecutive days or more: navigation time ≥ 18 hours, voyage distance > 120 nautical miles, main engine speed > 25 rpm;

[0056] S52, comparing the actual daily fuel consumption of the main engine in the fuel consumption data of constant speed navigation with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation, respectively, to obtain a fuel consumption score for constant speed navigation; the comparison result includes any one or any combination of the following:

[0057] The first type: If any deviation ratio among A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows:

[0058] x5=t 4 *T;

[0059] The second type: If the deviation ratio of any two of A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows:

[0060] x6=t 5 *T;

[0061] The third type: If the deviation ratio of any two of A, B, and C is less than 0%, the fuel consumption score for constant speed cruising is as follows:

[0062] x7=t 6 *T;

[0063] Where: t 4 ,t5 ,t 6 All are assigned points, and T is the number of days of constant speed sailing.

[0064] The step S6 specifically includes:

[0065] S61. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data, calculate the daily historical fuel consumption average, and then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average; the comparison result includes any one or any combination of the following:

[0066] The first type: If the actual daily fuel consumption data of the main engine is less than the daily historical fuel consumption average, there will be no warning;

[0067] The second type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 10%, it will be marked as a suspected bottom fouling warning;

[0068] The third type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 20%, it will be marked as a serious bottom fouling warning;

[0069] S62: Based on the suspected bottom contamination warning and the serious bottom contamination warning, assign a manual mark scoring value; the manual mark scoring value is as follows:

[0070] x8=t 7 *n+t 8 *m;

[0071] Among them: n, m are the number of times marked, t 7 is the score assigned for severe fouling warning, t 8 Assign a score to the suspected contaminated bottom warning.

[0072] The step S7 specifically includes:

[0073] The final ship fouling score is expressed as follows:

[0074] X=x1+x2+x3+x4+x5+x6+x7+x8;

[0075] The final ship fouling score is compared with the preset threshold range for judgment; the judgment result includes any one or any combination of the following:

[0076] The first type: If the final ship fouling score is X≤T low , it is judged that there is no pollution or the pollution has no effect;

[0077] The second type: If the final ship fouling score is T high >X>T low , it is judged as suspected contaminated bottom;

[0078] The third type: If the final ship fouling score is X ≥ T high , it is judged as serious bottom pollution;

[0079] Where: T low is the lower limit of the threshold range, T high is the upper limit of the threshold range.

[0080] The method for obtaining the preset threshold range specifically includes:

[0081] S71. Collect ship fuel consumption related data and perform pre-processing;

[0082] S72, collecting characteristics related to the degree of fouling of the ship, and quantifying and converting the characteristics related to the degree of fouling into a fouling score;

[0083] S73. Establish a correlation analysis model to predict the relationship between the ship fuel consumption related data and the fouling score, and calculate the average value and standard deviation of the fouling score; the expressions of the average value and standard deviation are as follows:

[0084]

[0085]

[0086] Where: μ is the mean, σ is the standard deviation, n is the number of bottom fouling scores, x i is the i-th contamination score;

[0087] S74, determining a threshold range based on the normal distribution, mean value μ and standard deviation σ of the bottom contamination score; the threshold range satisfies μ±σ;

[0088] The expression of the threshold range is as follows:

[0089] T low =μ-k·σ;

[0090] T high =μ+k·σ;

[0091] Where: k is a constant.

[0092] The step S8 specifically includes:

[0093] S81. Obtain the data of the current position of the ship and all ports within the voyage that can be cleaned;

[0094] S82. Calculate the time T from the current position of the ship to each port where pollution can be cleaned i , which is expressed as follows:

[0095]

[0096] Where: Di is the distance from the current position of the ship to the port i where pollution can be cleaned, and V is the average speed of the ship;

[0097] S83, based on time T i 、W the waiting time for pollution cleaning at each port where pollution can be cleaned i , the time required for cleaning pollution in each cleanable port C i , Time from the port where pollution can be cleaned to the destination port T j , respectively judge whether the ship can arrive at each port where pollution can be cleaned and complete pollution cleaning before the arrival time of the destination port; the judgment formula is as follows:

[0098] T i +W i +C i +T j <T max ;

[0099] Where: T max is a constant;

[0100] If the above judgment formula is met, the port that can be cleaned will be used as an alternative port for cleaning;

[0101] If the above judgment formula is not met, the port that can be cleaned will be excluded;

[0102] S84. If there are more than two alternative ports for pollution cleaning, the cost F of each alternative port for pollution cleaning is calculated based on i , which is expressed as follows:

[0103] F i =f i *T i +f j *T j +C n ;

[0104] Where: f i is the fuel cost per unit time before pollution cleaning, f j Fuel cost per unit time after cleaning, C n is the pollution cleaning cost of the alternative pollution cleaning port n;

[0105] S85. Compare the costs of alternative pollution cleaning ports F i , with the goal of minimizing costs, and confirming the final pollution cleanup port.

[0106] Compared with the prior art, the present invention has the following beneficial effects:

[0107] 1. In a ship pollution cleaning strategy generation technology based on operating parameters of the present invention, the operating parameter data of the ship is first obtained, and then the continuous berthing and discontinuous berthing of the ship at different seawater temperatures are scored, and then the main engine theoretical fuel consumption model is constructed to calculate the theoretical fuel consumption standard, the daily main engine actual fuel consumption is obtained and compared with the deviation, the deviation ratio is obtained and scored, and then the constant speed navigation fuel consumption data is obtained, and the daily main engine actual fuel consumption is compared with the standard and scored, and then the historical fuel consumption data is obtained and the average is calculated, and the daily main engine actual fuel consumption is compared with the daily historical fuel consumption average and the scores are accumulated to obtain the final ship fouling score, the ship's fouling status is judged, and finally based on the judgment result, the final pollution cleaning port is confirmed; in the application of this design, the ship's bottom fouling status is comprehensively evaluated from multiple angles through multi-dimensional data such as the temperature when the ship is berthed, the growth characteristics of marine organisms, and the fuel consumption characteristics, which not only improves the comprehensiveness of the bottom fouling evaluation, but also further explores the influence of seawater temperature on marine organisms and dynamic fuel consumption, so that it can more accurately reflect the potential impact of the bottom fouling, thereby improving the accuracy of the judgment result. Therefore, the accuracy of the present invention is higher.

[0108] 2. In the ship pollution cleaning strategy generation technology based on operating parameters of the present invention, by obtaining multi-dimensional data when the ship is running, and these data are relatively common routine data during the operation of the ship, the scheme does not rely on the need to obtain specific data, so that it can be applied to target ships of different ship types, greatly improving the promotion ability and scope of application. Therefore, the scope of application of the present invention is relatively wide.

[0109] 3. In the ship pollution cleaning strategy generation technology based on operation parameters of the present invention, after the fouling judgment is completed, the current position of the ship and the data of the port that can be cleaned are used to intelligently judge the best port for pollution cleaning with the shortest arrival time or the lowest cost as the goal, thus realizing the pollution cleaning strategy closed loop from the judgment of the fouling to the treatment of the fouling, and reducing the influence of human subjective factors, improving the objectivity of the pollution cleaning strategy, and helping to reduce the cost in the pollution cleaning link. Therefore, the cost of the present invention is relatively low. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] Figure 1 It is a flow chart of the method steps of the present invention.

[0111] Figure 2 This is one of the schematic diagrams of the dirty bottom judgment process of the present invention.

[0112] Figure 3 This is the second schematic diagram of the dirty bottom judgment process of the present invention. DETAILED DESCRIPTION

[0113] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0114] Embodiment 1:

[0115] See also Figure 1 , a ship pollution cleaning strategy generation technology based on operating parameters, including:

[0116] S1. Obtaining the operating parameter data of the ship; the operating parameter data includes berthing data, navigation data, data on suitable growth of marine organisms, fuel consumption data, ship parameters, and weather data;

[0117] Furthermore, the mooring data includes continuous mooring data, discontinuous mooring data, and total mooring time data; the navigation data includes total navigation time, constant speed navigation time, water speed, ground speed, bow draft, and stern draft; the suitable growth data for marine organisms include seawater temperature, marine organism type, and degree of attachment when marine organisms grow; the ship parameters include main engine speed, deadweight, ship type, and anti-fouling material of the bottom of the ship. In actual situations, the performance and thickness of the hull paint may also be considered; the weather data includes seawater temperature, wind speed, wind direction, flow direction, wind direction angle, seawater flow rate, wave height, wave grade, wave average period, significant wave height, and main wave direction angle; in addition, the operating parameter data also includes power share, contract speed, speed deviation, ground range, water range, ground slip, water slip, auxiliary engine fuel consumption, boiler fuel consumption, and other data.

[0118] S2. acquiring continuous mooring data from the mooring data, and assigning points to the continuous mooring of the ship at different seawater temperatures based on the suitable growth data of marine organisms, to obtain continuous mooring points;

[0119] In this embodiment, since the attachment of marine organisms to ships in seawater areas is relatively serious and is correlated with the ship's distance from the shore, the seawater area is mainly considered when considering the continuous mooring of the ship. If it is in a freshwater area, the continuous mooring points for the freshwater area do not need to be added, and this scheme can also be applied to freshwater areas.

[0120] In this embodiment, through the ship model test and the actual pollution removal data, it is known that after the ship is repaired and cleaned, basically no fouling that can affect the ship will occur within three months; and it is found in the study that if ordinary antifouling paint is used for factory repair or within three months of leaving the factory, basically no fouling will occur. If high-efficiency antifouling paint such as silicone is used, the number of days will be accumulated according to the instructions of the antifouling paint. According to the different quality and antifouling effect of the antifouling paint, the period without fouling will be extended.

[0121] At the same time, it was found through experiments that after the non-fouling period, marine organisms began to attach to the bottom of the ship after the ship was moored for 5 days, and as the number of mooring days increased, the marine organisms continued to grow, and the marine organisms also showed different attachment conditions under seawater of different temperatures; therefore, in this embodiment, the number of consecutive mooring days when the marine organisms began to grow and attach was preset to 5 days, recorded as D 连 (D>5), and the temperature range of seawater is preset to the water range of 5℃-35℃ where ships normally operate.

[0122] Furthermore, the step S2 specifically includes:

[0123] When the seawater temperature is 5℃-15℃, the scoring expression for continuous mooring at this temperature is as follows:

[0124]

[0125] Where: n is the continuous berthing time of n days, a i is the i-th day of the continuous parking time, t 1 is the score assignment, D 连 The number of days the ship has been moored continuously when the marine organisms begin to grow and attach, m 1 is the drift coefficient;

[0126] When the seawater temperature is 15℃-25℃, the scoring expression for continuous mooring at this temperature is as follows:

[0127]

[0128] Where: b j is the jth day of the continuous parking time, t 2 is the score, m 2 is the drift coefficient;

[0129] When the seawater temperature of the ship is 25℃-35℃, the scoring expression for continuous mooring at this temperature is as follows:

[0130]

[0131] Where: c e is the e-th day of the continuous parking time, t 3 is the score, m 3 is the drift coefficient;

[0132] The continuous mooring score x1 is calculated by integrating the continuous mooring score of the ship at different seawater temperatures; the expression of the continuous mooring score is as follows:

[0133]

[0134] Furthermore, the stop coefficient can reflect the growth rate of marine organisms on the bottom of the ship when the ship is moored at different positions; a higher stop coefficient means that the marine organisms on the hull grow faster, and the corresponding bottom fouling rate is faster; while a lower stop coefficient means that the marine organisms on the hull grow slower, and the corresponding bottom fouling rate is slower.

[0135] The factors that affect the suspension coefficient are mainly the following:

[0136] Distance from shore: Sea areas closer to the shore may be more affected by human activities, have shallower water depths, and have a higher concentration of marine life in the surface waters; conversely, the oceans farther from the shore have a lower concentration of marine life.

[0137] Density of marine organisms: The density of marine organisms in different sea areas is different, which directly affects the speed of bottom fouling.

[0138] Water flow speed: Marine organisms are not easy to attach to waters with fast water flow, but are easy to attach to waters with slow water flow.

[0139] Seasonal changes: The activity levels of marine organisms vary in different seasons, which will also affect the speed of bottom fouling.

[0140] The stop coefficient m 1 、m 2 、m 3 The expression is as follows:

[0141] m 1 , m 2 , m 3 =Q+W*R+Y*M+F*V+G*O;

[0142] Among them: Q is a constant term, representing the basic suspension value; W is the coefficient of the offshore distance R; Y is the coefficient of the marine organism density M; F is the coefficient of the water flow velocity V; G is the coefficient of the season O.

[0143] S3, obtaining total berthing time data and non-continuous berthing data from the berthing data, and obtaining total sailing time from the sailing data, and then calculating and scoring the non-continuous berthing ratio to obtain the non-continuous berthing scoring value;

[0144] Furthermore, the step S3 specifically includes:

[0145] The non-continuous mooring data refers to data that is less than the number of days that the mooring has been continuous when the marine organisms begin to grow and attach;

[0146] The expression of the non-continuous parking ratio is as follows:

[0147] P=(D 非 / S)*100%;

[0148] Where: P is the proportion of non-continuous parking, D 非 is the duration of non-continuous berthing, S is the sum of total berthing time and total sailing time;

[0149] Calculate the non-continuous parking score based on the non-continuous parking percentage;

[0150] If P < 30%, the non-continuous parking score is zero; if P > 30%, the non-continuous parking score is calculated according to the following expression:

[0151] x2=100*(P-30%).

[0152] S4. Construct a theoretical fuel consumption model for the main engine and calculate the theoretical fuel consumption standard. Then, obtain the actual daily fuel consumption of the main engine of the ship from the fuel consumption data. Compare the actual daily fuel consumption of the main engine with the theoretical fuel consumption standard to obtain the deviation ratio and assign a score to obtain the fuel consumption model scoring value.

[0153] Furthermore, the step S4 specifically includes:

[0154] S41, constructing a theoretical fuel consumption model of the main engine; the theoretical fuel consumption model of the main engine includes: an empirical value theoretical standard model, a big data theoretical standard model, and a unit consumption calculation theoretical standard model;

[0155] The empirical value theoretical standard model: by obtaining the fuel consumption standards of the sister ship group under no-load and full-load conditions, and combining the historical fuel consumption data of the sister ship group, a theoretical fuel consumption standard H based on the empirical value is obtained;

[0156] The big data theoretical standard model: by obtaining the fuel consumption data of the sister ship group when the main engine speed is the same and the empty and full load, and performing big data analysis based on the navigation data of the ship in unit time, a theoretical fuel consumption standard D based on big data is obtained;

[0157] The unit consumption calculation theoretical standard model: by obtaining the fuel consumption data of the sister ship group, and calculating the fuel consumption per nautical mile and the average value, the unit consumption calculation theoretical standard S is obtained;

[0158] S42. Obtain the actual daily fuel consumption E of the main engine of the ship from the fuel consumption data, and compare the actual daily fuel consumption E of the main engine with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation to obtain the deviation ratios A, B, and C; the details are as follows:

[0159] The deviation ratio A of the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard H based on the empirical value is as follows:

[0160] A=(EH) / H*100%;

[0161] The deviation ratio B between the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard D based on big data is as follows:

[0162] B = (ED) / H * 100%;

[0163] The deviation ratio C of the actual daily main engine fuel consumption E and the theoretical standard S for unit consumption calculation is as follows:

[0164] C = ((E*1000) / dS) / S*100%;

[0165] Where: d is the daily ship sailing distance;

[0166] S43, based on the deviation ratios A, B, and C, obtaining a fuel consumption model scoring value; the fuel consumption model scoring value includes any one or any combination of the following:

[0167] The first type: If the deviation ratio of any two of A, B, and C is ≥5%, the fuel consumption model score is: x3 = 1*T 好 ;

[0168] The second type: If the deviation ratio of any two of A, B, and C is less than 0%, the fuel consumption model score is: x4 = -1*T 好 ;

[0169] Where: T 好 It is the number of days with good weather during the voyage of the ship. Good weather refers to the weather with wind force 4 or below and wave level of light waves or below.

[0170] S5. Obtaining the fuel consumption data for constant speed sailing from the navigation data and the fuel consumption data, and comparing and scoring the actual daily fuel consumption of the main engine in the fuel consumption data for constant speed sailing with the theoretical fuel consumption standard to obtain a fuel consumption scoring value for constant speed sailing;

[0171] Furthermore, the step S5 specifically includes:

[0172] S51. Obtaining constant speed sailing fuel consumption data from the navigation data and the fuel consumption data; the constant speed sailing fuel consumption data refers to data that meets the above conditions for three consecutive days or more: navigation time ≥ 18 hours, voyage distance > 120 nautical miles, main engine speed > 25 rpm;

[0173] S52, comparing the actual daily fuel consumption of the main engine in the fuel consumption data of constant speed navigation with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation, respectively, to obtain a fuel consumption score for constant speed navigation; the comparison result includes any one or any combination of the following:

[0174] The first type: If any deviation ratio among A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows:

[0175] x5=t 4 *T;

[0176] The second type: If the deviation ratio of any two of A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows:

[0177] x6=t 5 *T;

[0178] The third type: If the deviation ratio of any two of A, B, and C is less than 0%, the fuel consumption score for constant speed cruising is as follows:

[0179] x7=t 6 *T;

[0180] Where: t 4 ,t 5 ,t 6 are all assigned scores (preferably 5, 10, -10 respectively), and T is the number of days of constant speed sailing.

[0181] S6. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data and calculate the average value, then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average value and manually assign points to obtain a manual marking score value;

[0182] Furthermore, the step S6 specifically includes:

[0183] S61. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data, calculate the daily historical fuel consumption average, and then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average; the comparison result includes any one or any combination of the following:

[0184] The first type: If the actual daily fuel consumption data of the main engine is less than the daily historical fuel consumption average, there will be no warning;

[0185] The second type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 10%, it will be marked as a suspected bottom fouling warning;

[0186] The third type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 20%, it will be marked as a serious bottom fouling warning;

[0187] S62: Based on the suspected bottom contamination warning and the serious bottom contamination warning, assign a manual mark scoring value; the manual mark scoring value is as follows:

[0188] x8=t 7 *n+t 8 *m;

[0189] Among them: n, m are the number of times marked, t 7is the score assigned to the severe fouling warning (preferably 10), t 8 The score assigned to the suspected contamination warning (preferably 5).

[0190] Furthermore, in order to prevent the marking personnel from making wrong judgments, a corresponding marking and deduction method has also been established. After being marked as a serious bottom fouling warning once, if there is no serious bottom fouling warning within 15 days, the corresponding score will be deducted.

[0191] After being marked as a suspected contaminated bottom warning once, if there is no suspected contaminated bottom warning within 7 days, the corresponding score will be deducted.

[0192] S7, accumulating the scoring values ​​obtained in steps S2-S6 to obtain a final ship fouling score, and judging the fouling status of the ship based on the final ship fouling score; the judgment result includes any one of no fouling, suspected fouling, and serious fouling, and when the judgment result is serious fouling, proceed to step S8.

[0193] Furthermore, the step S7 specifically includes:

[0194] The final ship fouling score is expressed as follows:

[0195] X=x1+x2+x3+x4+x5+x6+x7+x8;

[0196] The final ship fouling score is compared with the preset threshold range for judgment; the judgment result includes any one or any combination of the following:

[0197] The first type: If the final ship fouling score is X≤T low , it is judged that there is no pollution or the pollution has no effect;

[0198] The second type: If the final ship fouling score is T high >X>T low , it is judged as suspected contaminated bottom;

[0199] The third type: If the final ship fouling score is X ≥ T high , it is judged as serious bottom pollution;

[0200] Where: T low is the lower limit of the threshold range, T high is the upper limit of the threshold range.

[0201] Furthermore, the method for obtaining the preset threshold range specifically includes:

[0202] S71. Collect ship fuel consumption related data and perform preprocessing to ensure that the data covers various operating conditions; the ship fuel consumption related data includes fuel consumption, speed, and ship performance; the preprocessing includes cleaning data, removing outliers and missing values, and interpolation or prediction methods can be used to fill missing values;

[0203] S72. Collecting relevant characteristics of the ship's bottom fouling degree, such as the increase in fuel consumption and the decrease in speed; quantifying and converting the relevant characteristics of the bottom fouling degree into a bottom fouling score, for example, converting the bottom fouling degree into a bottom fouling score from 0 to 100, where 0 indicates no bottom fouling and 100 indicates severe bottom fouling that makes normal navigation impossible;

[0204] S73. Establish a correlation analysis model, calculate the correlation coefficient between the characteristics such as the increase in fuel consumption and the decrease in speed and the fouling score, and identify the key influencing factors; predict the relationship between the ship's fuel consumption related data and the fouling score, and calculate the mean and standard deviation of the fouling score, preferably a linear regression model.

[0205] The expressions of the mean value and standard deviation are as follows:

[0206]

[0207]

[0208] Where: μ is the mean, σ is the standard deviation, n is the number of bottom fouling scores, x i is the i-th contamination score;

[0209] S74, determining a threshold range based on the normal distribution, mean value μ and standard deviation σ of the bottom contamination score; the threshold range satisfies μ±σ;

[0210] The expression of the threshold range is as follows:

[0211] T low =μ-k·σ;

[0212] T high =μ+k·σ;

[0213] Where: k is a constant.

[0214] In this embodiment, it is assumed that the threshold range of "suspected contaminated bottom" and "serious contaminated bottom" is determined; if the contaminated bottom score roughly conforms to the normal distribution, μ±σ covers 68% of the data, the mean μ=70, the standard deviation σ=10, and k=1;

[0215] The lower limit of the threshold range is T low =70-1*10=60; then the upper limit of the threshold range is T high=70+1*10=80; therefore, the interval of 60 to 80 points can be used as a reasonable threshold range for "suspected contamination" to "serious contamination".

[0216] S8. Based on the current position of the ship, obtain the data of all ports that can be cleaned along the route, and confirm the final port of cleanup with the goal of arriving at the destination port on time and at the lowest cost.

[0217] S81. Obtain data on the current position of the ship and all ports within the voyage range where pollution can be cleaned. In this embodiment, the distance between the current position of the ship and the nearest port where pollution can be cleaned can be determined by the GPS system, and data from various sources, such as AIS data, weather forecasts, etc., can be integrated to form a comprehensive view to improve the reliability and accuracy of the data.

[0218] S82. Calculate the time T from the current position of the ship to each port where pollution can be cleaned i , which is expressed as follows:

[0219]

[0220] Where: Di is the distance from the current position of the ship to the port i where pollution can be cleaned, V is the average speed of the ship (the average speed of sister ships under historical meteorological conditions can be referred to);

[0221] In this embodiment, by using smart routes and setting a certain radius, all ports along the route that can clean up pollution are found, and each port that can clean up pollution will publicize various pollution cleaning service information on a public platform, such as the waiting time for pollution cleaning and the time required for pollution cleaning.

[0222] S83, based on time T i , the waiting time for pollution cleaning at each port where pollution can be cleaned W i , the time required for cleaning pollution in each cleanable port C i , Time from the port where pollution can be cleaned to the destination port T j , respectively judge whether the ship can arrive at each port where pollution can be cleaned and complete pollution cleaning before the arrival time of the destination port (this time is usually the agreed time in the contract); the judgment formula is as follows:

[0223] T i +W i +C i +T j <T max ;

[0224] Where: T max is a constant;

[0225] If the above judgment formula is met, the port that can be cleaned will be used as an alternative port for cleaning;

[0226] If the above judgment formula is not met, the port that can be cleaned will be excluded;

[0227] S84. If there are more than two alternative ports for pollution cleaning, the cost F of each alternative port for pollution cleaning is calculated based on i , which is expressed as follows:

[0228] F i =f i *T i +f j *T j +C n ;

[0229] Where: f i is the fuel cost per unit time before pollution cleaning, f j Fuel cost per unit time after cleaning, C n is the pollution cleaning cost of the alternative pollution cleaning port n;

[0230] S85. Compare the costs of alternative pollution cleaning ports F i , with the goal of minimizing costs, and confirming the final pollution cleanup port.

[0231] Whether the ship can arrive at each port where pollution can be cleaned and complete pollution cleaning before the arrival time of the destination port refers to:

[0232] If the ship needs to clean up the pollution before going to the destination port, it is necessary to judge whether the distance and cleaning time of the ship to the pollution cleaning port will occupy the original time to arrive at the destination port, resulting in failure to arrive at the destination port on time.

[0233] For example, ship A needs to arrive at the destination port at 12:00 in 20 days, and at 12:00 on the same day, a serious fouling warning appears and the bottom cleaning is required; assuming that the journey from the current location of ship A to the cleanable port and the time required for cleaning are 3 days, and the time from the cleanable port to the destination port is 16.5 days, then 16.5 days plus 3 days is 19.5 days, which meets the requirement of arriving at the destination port in 20 days. In this case, this cleanable port can be used as an alternative cleaning port, and vice versa.

[0234] In this embodiment, intelligent AI can be combined with the system to intelligently recommend the best port and time for pollution removal, and convert the optimal solution into easy-to-understand suggestions and reports, which are sent to the ship supervisor for review, and necessary adjustments are made based on the feedback from the ship supervisor.

[0235] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A ship pollution cleaning strategy generation technology based on operating parameters, characterized in that: include: S1. Obtaining the operating parameter data of the ship; the operating parameter data includes berthing data, navigation data, data on suitable growth of marine organisms, fuel consumption data, ship parameters, and weather data; S2. acquiring continuous mooring data from the mooring data, and assigning points to the continuous mooring of the ship at different seawater temperatures based on the suitable growth data of marine organisms, to obtain continuous mooring points; S3, obtaining total berthing time data and non-continuous berthing data from the berthing data, and obtaining total sailing time from the sailing data, and then calculating and scoring the non-continuous berthing ratio to obtain the non-continuous berthing scoring value; S4. Construct a theoretical fuel consumption model for the main engine and calculate the theoretical fuel consumption standard. Then, obtain the actual daily fuel consumption of the main engine of the ship from the fuel consumption data. Compare the actual daily fuel consumption of the main engine with the theoretical fuel consumption standard to obtain the deviation ratio and assign a score to obtain the fuel consumption model scoring value. S5. Obtaining the fuel consumption data for constant speed sailing from the navigation data and the fuel consumption data, and comparing and scoring the actual daily fuel consumption of the main engine in the fuel consumption data for constant speed sailing with the theoretical fuel consumption standard to obtain a fuel consumption scoring value for constant speed sailing; S6. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data and calculate the average value, then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average value and manually assign points to obtain a manual marking score value; S7, accumulating the scoring values ​​obtained in steps S2-S6 to obtain a final ship fouling score, and judging the fouling status of the ship based on the final ship fouling score; the judgment result includes any one of no fouling or no impact of fouling, suspected fouling, and serious fouling, and when the judgment result is serious fouling, proceed to step S8; S8. Based on the current position of the ship, obtain the data of all ports that can be cleaned along the route, and confirm the final port of cleanup with the goal of arriving at the destination port on time and at the lowest cost.

2. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 1 is characterized by: The step S2 specifically includes: When the seawater temperature is 5℃-15℃, the scoring expression for continuous mooring at this temperature is as follows: Where: n is the continuous berthing time of n days, a i is the i-th day of the continuous parking time, t1 is the assigned score, D 连 is the number of consecutive days the ship has been anchored when marine organisms begin to grow and attach, and m1 is the suspension coefficient; When the seawater temperature is 15℃-25℃, the scoring expression for continuous mooring at this temperature is as follows: Where: b j is the jth day of the continuous anchorage time, t2 is the assigned score, and m2 is the stop coefficient; When the seawater temperature of the ship is 25℃-35℃, the scoring expression for continuous mooring at this temperature is as follows: Where: c e is the e-th day of the continuous anchorage time, t3 is the assigned score, and m3 is the stop coefficient; The continuous mooring score x1 is calculated by integrating the continuous mooring score of the ship at different seawater temperatures; the expression of the continuous mooring score is as follows:

3. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 2 is characterized by: The stop coefficients m1, m2, and m3 are used to reflect the growth rate of marine organisms at the bottom of the ship, and their expressions are as follows: m1, m2, m3=Q+W*R+Y*M+F*V+G*O; Among them: Q is a constant term, representing the basic suspension value; W is the coefficient of the offshore distance R; Y is the coefficient of the marine organism density M; F is the coefficient of the water flow velocity V; G is the coefficient of the season O.

4. A ship pollution cleaning strategy generation technology based on operating parameters according to claim 2 or 3, characterized in that: The step S3 specifically includes: The non-continuous mooring data refers to data that is less than the number of days that the mooring has been continuous when the marine organisms begin to grow and attach; The expression of the non-continuous parking ratio is as follows: P=(D 非 / S)*100%; Where: P is the proportion of non-continuous parking, D 非 is the duration of non-continuous berthing, S is the sum of total berthing time and total sailing time; Calculate the non-continuous parking score based on the non-continuous parking percentage; If P < 30%, the non-continuous parking score is zero; if P > 30%, the non-continuous parking score is calculated according to the following expression: x2=100*(P-30%).

5. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 4 is characterized by: The step S4 specifically includes: S41, constructing a theoretical fuel consumption model of the main engine; the theoretical fuel consumption model of the main engine includes: an empirical value theoretical standard model, a big data theoretical standard model, and a unit consumption calculation theoretical standard model; The empirical value theoretical standard model: by obtaining the fuel consumption standards of the sister ship group under no-load and full-load conditions, and combining the historical fuel consumption data of the sister ship group, a theoretical fuel consumption standard H based on the empirical value is obtained; The big data theoretical standard model: by obtaining the fuel consumption data of the sister ship group when the main engine speed is the same and the empty and full load, and performing big data analysis based on the navigation data of the ship in unit time, a theoretical fuel consumption standard D based on big data is obtained; The unit consumption calculation theoretical standard model: by obtaining the fuel consumption data of the sister ship group, and calculating the fuel consumption per nautical mile and the average value, the unit consumption calculation theoretical standard S is obtained; S42. Obtain the actual daily fuel consumption E of the main engine of the ship from the fuel consumption data, and compare the actual daily fuel consumption E of the main engine with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation to obtain the deviation ratios A, B, and C; the details are as follows: The deviation ratio A of the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard H based on the empirical value is as follows: A=(EH) / H*100%; The deviation ratio B between the actual daily fuel consumption E of the main engine and the theoretical fuel consumption standard D based on big data is as follows: B = (ED) / H * 100%; The deviation ratio C of the actual daily main engine fuel consumption E and the theoretical standard S for unit consumption calculation is as follows: C = ((E*1000) / dS) / S*100%; Where: d is the daily ship sailing distance; S43, based on the deviation ratios A, B, and C, obtaining a fuel consumption model scoring value; the fuel consumption model scoring value includes any one or any combination of the following: The first type: If the deviation ratio of any two of A, B, and C is ≥5%, the fuel consumption model score is: x3 = 1*T 好 ; The second type: If the deviation ratio of any two of A and B is less than 0%, the fuel consumption model score is: x4 = -1*T 好 ; Where: T 好 It is the number of days with good weather during the ship's voyage.

6. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 5 is characterized by: The step S5 specifically includes: S51. Obtaining constant speed sailing fuel consumption data from the navigation data and the fuel consumption data; the constant speed sailing fuel consumption data refers to data that meets the above conditions for three consecutive days or more: navigation time ≥ 18 hours, voyage distance > 120 nautical miles, main engine speed > 25 rpm; S52, comparing the actual daily fuel consumption of the main engine in the fuel consumption data of constant speed navigation with the theoretical fuel consumption standard H based on experience value, the theoretical fuel consumption standard D based on big data, and the theoretical standard S for unit consumption calculation, respectively, to obtain a fuel consumption score for constant speed navigation; the comparison result includes any one or any combination of the following: The first type: If any deviation ratio among A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows: x5 = t4*T; The second type: If the deviation ratio of any two of A, B, and C is greater than 5%, the fuel consumption score for constant speed cruising is as follows: x6 = t5 * T; The third type: If the deviation ratio of any two of A, B, and C is less than 0%, the fuel consumption score for constant speed cruising is as follows: x7 = t6 * T; Among them: t4, t5, t6 are all assigned points, and T is the number of days of constant speed navigation.

7. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 6 is characterized by: The step S6 specifically includes: S61. Obtain the historical fuel consumption data of the sister ship group from the fuel consumption data, calculate the daily historical fuel consumption average, and then compare the actual daily main engine fuel consumption data of the ship in good weather with the daily historical fuel consumption average; the comparison result includes any one or any combination of the following: The first type: If the actual daily fuel consumption data of the main engine is less than the daily historical fuel consumption average, there will be no warning; The second type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 10%, it will be marked as a suspected bottom fouling warning; The third type: If the actual daily fuel consumption data of the main engine is greater than the daily historical fuel consumption average and exceeds 20%, it will be marked as a serious bottom fouling warning; S62: Based on the suspected bottom contamination warning and the serious bottom contamination warning, assign a manual mark scoring value; the manual mark scoring value is as follows: x8=t7*n+t8*m; Where: n, m are the number of markings, t7 is the score assigned to the severe bottom fouling warning, and t8 is the score assigned to the suspected bottom fouling warning.

8. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 7 is characterized by: The step S7 specifically includes: The final ship fouling score is expressed as follows: X=x1+x2+x3+x4+x5+x6+x7+x8; The final ship fouling score is compared with the preset threshold range for judgment; the judgment result includes any one or any combination of the following: The first type: If the final ship fouling score is X≤T low , it is judged that there is no bottom pollution or the bottom pollution has no effect; The second type: If the final ship fouling score is T high >X>T low , it is judged as suspected contaminated bottom; The third type: If the final ship fouling score is X ≥ T high , it is judged as serious bottom pollution; Where: T low is the lower limit of the threshold range, T high is the upper limit of the threshold range.

9. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 8 is characterized by: The method for obtaining the preset threshold range specifically includes: S71. Collect ship fuel consumption related data and perform pre-processing; S72, collecting characteristics related to the degree of fouling of the ship, and quantifying and converting the characteristics related to the degree of fouling into a fouling score; S73. Establish a correlation analysis model to predict the relationship between the ship fuel consumption related data and the fouling score, and calculate the average value and standard deviation of the fouling score; the expressions of the average value and standard deviation are as follows: Where: μ is the mean, σ is the standard deviation, n is the number of bottom fouling scores, x i is the i-th contamination score; S74, determining a threshold range based on the normal distribution, mean value μ and standard deviation σ of the bottom contamination score; the threshold range satisfies μ±σ; The expression of the threshold range is as follows: T low =μ-k·σ; T high =μ+k·σ; Where: k is a constant.

10. The ship pollution cleaning strategy generation technology based on operating parameters according to claim 1 is characterized by: The step S8 specifically includes: S81. Obtain the data of the current position of the ship and all ports within the voyage that can be cleaned; S82. Calculate the time T from the current position of the ship to each port where pollution can be cleaned i , which is expressed as follows: Where: Di is the distance from the current position of the ship to the port i where pollution can be cleaned, and V is the average speed of the ship; S83, based on time T i 、W the waiting time for pollution cleaning at each port where pollution can be cleaned i , the time required for cleaning pollution in each cleanable port C i , Time from the port where pollution can be cleaned to the destination port T j , respectively judge whether the ship can arrive at each port where pollution can be cleaned and complete pollution cleaning before the arrival time of the destination port; the judgment formula is as follows: T i +W i +C i +T j <T max ; Where: T max is a constant; If the above judgment formula is met, the port that can be cleaned will be used as an alternative port for cleaning; If the above judgment formula is not met, the port that can be cleaned will be excluded; S84. If there are more than two alternative ports for pollution cleaning, the cost F of each alternative port for pollution cleaning is calculated based on i , which is expressed as follows: F i =f i *T i +f j *T j +C n ; Where: f i is the fuel cost per unit time before pollution control, f i Fuel cost per unit time after cleaning, C n is the pollution cleanup cost of the alternative pollution cleanup port n; S85. Compare the costs of alternative pollution cleaning ports F i , with the goal of minimizing costs, and confirming the final pollution cleanup port.

Images