Ship energy consumption calculation method and device, computer equipment and storage medium

Abstract

The present application relates to the technical field of ships, and discloses a ship energy consumption calculation method and device, computer equipment and a storage medium. The present application obtains ship operation data and multi-source sensor data collected by target sensors of a target ship. The multi-source sensor data is dynamically filtered based on the change characteristics of the ship operation data and the multi-source sensor data to obtain first target multi-source sensor data. The first target multi-source sensor data is dynamically filtered based on the ship operation data to obtain second target multi-source sensor data. The second target multi-source sensor data is dynamically compensated based on the ship operation data to obtain corrected multi-source sensor data. The energy consumption of a sub-ship is calculated based on the corrected multi-source sensor data and the sensor type of the corresponding target sensor. The energy consumption of each sub-ship is fused based on the ship operation data to obtain ship energy consumption data.

Description

Technical Field

[0001] This invention relates to the field of marine technology, specifically to methods, apparatus, computer equipment, and storage media for calculating marine energy consumption. Background Technology

[0002] In the shipping industry, the energy efficiency and environmental performance of ships are receiving increasing attention. Regulations such as the International Maritime Organization's Energy Efficiency Design Index, Ship Energy Efficiency Management Plan, and Carbon Intensity Index require ships to quantify energy consumption and emissions. Based on this, accurate calculation of energy consumption data is the foundation for compliance.

[0003] However, current ship energy consumption calculation methods typically rely on sensors such as flow meters and level gauges to collect liquid level or flow parameters, and then calculate energy consumption based on a single parameter. However, this method has significant drawbacks: First, sensors installed on ships operating in rivers and oceans are severely affected by the aquatic environment; ship trimming or rolling can cause distortion in liquid level measurements, with errors reaching up to 15% in extreme cases. Second, the zero-drift error of ship flow meters (e.g., typical value ±0.5%) and the nonlinear error of level sensors (up to 3% in the bilge section) lead to large discrepancies between sensor-collected data and actual data. Furthermore, fuel refueling typically relies on manual recording, with an error rate of approximately 2% to 5%. Due to these factors, traditional single-source calculation methods generally have errors exceeding 5% in real-world ship applications, making it difficult to meet the accuracy requirements for ship energy consumption calculations.

[0004] To address the error problem of single-source sensors, another energy consumption calculation method collects data from multiple sensors on the ship to obtain various energy consumption-related parameters as multi-source data, and then further fuses the multi-source data to calculate energy consumption. However, this method faces core challenges in multi-source data fusion. First, multi-source data is heterogeneous due to factors such as sampling frequency and sensor type, making fusion difficult when calculating energy consumption data based on the fused multi-source data. Second, each sensor in the multi-source data may have acquisition and calculation errors, similar to those in single-source energy consumption calculation methods. When finally obtaining energy consumption data from the multi-source data, the errors of each sensor make it difficult to meet the accuracy requirements for ship energy consumption calculation.

[0005] Therefore, the ship energy consumption calculation methods in related technologies have technical problems such as inaccurate energy consumption calculations, which cannot meet the accuracy requirements of ship energy consumption calculation data. Summary of the Invention

[0006] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for calculating ship energy consumption, in order to solve the problem of inaccurate energy consumption calculation in related technologies.

[0007] In a first aspect, the present invention provides a method for calculating ship energy consumption, the method comprising: acquiring ship operation data and multi-source sensor data collected by target sensors of a target ship; wherein the target sensors include flow meters, level gauges, and AIS systems; dynamically filtering the multi-source sensor data based on the variation characteristics of the ship operation data and the multi-source sensor data to obtain first target multi-source sensor data; wherein the variation characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data; dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain second target multi-source sensor data; wherein the ship operation data corresponds to the time sequence of the multi-source sensor data; dynamically compensating the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data; wherein the ship operation data corresponds to the time sequence of the second target multi-source sensor data; calculating the energy consumption of sub-ships based on the corrected multi-source sensor data and the corresponding sensor types; and fusing the energy consumption of each sub-ship based on the ship operation data to obtain ship energy consumption data.

[0008] As an exemplary embodiment, the step of dynamically filtering the multi-source sensor data based on the change characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data includes: dynamically filtering the multi-source sensor data based on the ship operation data to obtain the first multi-source sensor data within a preset value range; wherein, the ship operation data and the multi-source sensor data are time-series corresponding, and the preset value range is determined based on the time-series corresponding ship operation data and the numerical characteristics of the ship operation data; and dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain the first target multi-source sensor data.

[0009] As an exemplary embodiment, the step of dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain the first target multi-source sensor data includes:

[0010] Calculate a first rate of change for a predetermined number of time-series continuous multi-source sensor data; determine a first rate of change threshold based on the sensor type of the target sensor corresponding to the first rate of change; filter the multi-source sensor data based on the first rate of change threshold and the first rate of change to obtain multiple second multi-source sensor data exceeding the first rate of change threshold; acquire a first trend feature of third multi-source sensor data whose time sequence is later than the second multi-source sensor data; if the first trend feature satisfies a preset trend feature, remove the second multi-source sensor data.

[0011] As an exemplary embodiment, before removing the second multi-source sensor data, the ship energy consumption calculation method further includes: obtaining a second trend feature of the ship operation data based on the sensor type; if the second trend feature meets a preset trend feature, removing the second multi-source sensor data.

[0012] As an exemplary embodiment, the step of dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain first target multi-source sensor data includes: calculating the rate of change of a preset number of time-series continuous multi-source sensor data; determining a rate of change threshold based on the sensor type corresponding to the rate of change; filtering the multi-source sensor data based on the rate of change threshold and the rate of change to obtain multiple second multi-source sensor data exceeding the rate of change threshold; acquiring the change trend characteristics of second target multi-source sensor data whose time sequence is later than the second multi-source sensor data; and removing the second multi-source sensor data if the change trend characteristics meet preset change characteristics.

[0013] As an exemplary embodiment, the step of dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data includes: determining the operating state corresponding to each of the multi-source sensor data based on the ship operation data; determining a first filtering parameter and a second filtering parameter based on the operating state; and filtering the first target multi-source sensor data based on the first filtering parameter and the second filtering parameter to obtain the second target multi-source sensor data.

[0014] As an exemplary embodiment, the step of dynamically compensating the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data includes:

[0015] Extract the pitch angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data corresponding to the time sequence of the multi-source sensor data of the second target from the ship operation data;

[0016] Based on the trim angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data, the following formula is used to perform liquid level compensation on the second target multi-source sensor data to obtain the corrected multi-source sensor data:

[0017]

[0018] θ = arctan(draft) aft -draft fore) / LBP

[0019]

[0020] In the formula, For the corrected multi-source sensor data, X is the second target multi-source sensor data, θ is the pitch angle data, and draft fore Based on previous draft data, draft aft The figures are: Aft draft, LBP (length), and Beam (breadth). This is the roll angle data.

[0021] As an exemplary embodiment, the step of fusing the energy consumption of each of the sub-ships based on the ship operation data to obtain ship energy consumption data includes: obtaining at least one of the speed change rate data, roll angle data, and wind speed data from the ship operation data; determining the energy consumption fusion weight corresponding to each of the sensors based on the speed change rate data, roll angle data, or wind speed data; and fusing the energy consumption of each of the sub-ships based on the energy consumption fusion weight to obtain the ship energy consumption data.

[0022] In a second aspect, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the ship energy consumption calculation method of the first aspect or any corresponding embodiment described above.

[0023] Thirdly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the ship energy consumption calculation method of the first aspect or any corresponding embodiment described above.

[0024] This invention provides a method, apparatus, computer equipment, and storage medium for calculating ship energy consumption. The method includes: acquiring ship operation data and multi-source sensor data collected by target sensors on the target ship; wherein the target sensors include flow meters, level gauges, and AIS systems; dynamically filtering the multi-source sensor data based on the changing characteristics of the ship operation data and the multi-source sensor data to obtain first target multi-source sensor data; wherein the changing characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data; dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain second target multi-source sensor data; wherein the ship operation data corresponds to the time sequence of the multi-source sensor data; and dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain second target multi-source sensor data. Dynamic compensation is performed on the multi-source sensor data of the two targets to obtain corrected multi-source sensor data; wherein, the ship operation data corresponds in time sequence with the second target multi-source sensor data; the energy consumption of the sub-ship is calculated based on the corrected multi-source sensor data and the corresponding sensor type; the energy consumption of each sub-ship is fused based on the ship operation data to obtain the ship energy consumption data; the above method can dynamically filter, dynamically screen and dynamically compensate the multi-source sensor data by considering the acquisition error of each sensor in the multi-source sensor data, the error caused by the ship being affected by the water environment, and the navigation status of the target ship, so as to obtain more accurate corrected multi-source sensor data; furthermore, the energy consumption of the sub-ship is calculated using the corrected multi-source sensor data, and the energy consumption of each sub-ship is fused by considering the ship operation data, so as to obtain more accurate ship energy consumption data. Attached Figure Description

[0025] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 This is a flowchart illustrating the ship energy consumption calculation method according to an embodiment of the present invention;

[0027] Figure 2 This is a structural block diagram of a ship energy consumption calculation device according to an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are also included.

[0030] According to an embodiment of the present invention, a method for calculating ship energy consumption is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for calculating ship energy consumption. Figure 1 This is a flowchart of a ship energy consumption calculation method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0032] Step S101: Obtain ship operation data and multi-source sensor data collected by the target sensors of the target ship; wherein, the target sensors include flow meters, level gauges, and AIS systems.

[0033] For example, the multi-source sensor data includes flow meter data, liquid level data, and AIS data, which can be acquired by the processor communicating with the target sensor, wherein the target sensor includes at least one of a flow meter, a liquid level gauge, and an Automatic Identification System (AIS).

[0034] For example, ship operation data includes ship main engine parameter data, pitch value, roll, main engine speed, etc., wherein the ship operation data can be collected by the processor communicating with the main engine.

[0035] Step S102: Dynamically filter the multi-source sensor data based on the change characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data; wherein, the change characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data.

[0036] To address the error problem of multi-source sensors, in this embodiment, the multi-source sensor data is dynamically filtered based on the changing characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data.

[0037] As a possible implementation, after obtaining multi-source sensor data, the data distribution range of the multi-source sensor data is extracted as a numerical feature. Then, each data is further filtered or verified according to the data feature. Data that conforms to the preset data distribution range is retained, and data that does not conform to the preset distribution range is removed to obtain the first target multi-source sensor data, so as to eliminate the acquisition error caused by various error factors of the sensor.

[0038] For example, when extracting numerical features from multi-source sensor data, in order to consider the data heterogeneity caused by the sensor acquisition frequency, sliding windows with different window sizes and sliding step lengths can be provided for each type of sensor data based on the sensor type. This results in sub-flowmeter data, sub-level data, and sub-AIS speed data with sliding window sizes and sliding step lengths according to the sensor type. The data distribution range of the sub-flowmeter data, sub-level data, and sub-AIS speed data is extracted as a numerical feature. Furthermore, each data is filtered or verified according to the numerical feature, retaining data that conforms to the preset data distribution range and removing data that does not conform to the preset distribution range. Finally, the sub-flowmeter data and sub-level data after removing outliers are merged according to the time sequence to obtain the first target multi-source sensor data, thereby eliminating acquisition errors caused by various sensor error factors.

[0039] In one embodiment, to correct sensor data based on the ship's operating status and address the error problem caused by inaccurate sensor acquisition due to the ship's operating status, the multi-source sensor data can be dynamically filtered based on the ship's operating data to obtain first target multi-source sensor data. Obtaining the first target multi-source sensor data is one possible implementation. After obtaining the multi-source sensor data, the data distribution range of the multi-source sensor data is extracted as a numerical feature. The ship's operating status is determined based on the ship's operating data corresponding to the time sequence of each multi-source sensor data. The data distribution range is further corrected based on the ship's operating status. Finally, each data is filtered or verified based on the corrected data distribution range. Data that conforms to the preset data distribution range is retained, and data that does not conform to the preset distribution range is removed to obtain the first target multi-source sensor data, thereby eliminating acquisition errors caused by various sensor error factors.

[0040] In one embodiment, the multi-source sensor data can be dynamically filtered based solely on the variation characteristics of the multi-source sensor data to obtain the first target multi-source sensor data. As a possible implementation, after obtaining the multi-source sensor data, the variation characteristics of the multi-source sensor data are extracted, and each data is further filtered or verified according to the variation characteristics. Data that meets the preset variation characteristics is retained, and data that does not meet the preset variation characteristics is removed to obtain the first target multi-source sensor data, so as to eliminate the acquisition error caused by various error factors of the sensor.

[0041] For example, after obtaining multi-source sensor data, the rate of change of the most recent N consecutive sampling points is calculated as the instantaneous rate of change. The instantaneous rate of change is used as the change characteristic of the multi-source sensor data to further filter or verify each data. Data that meets the preset change characteristics is retained, and data that does not meet the preset change characteristics are removed to obtain the first target multi-source sensor data, so as to eliminate the acquisition error caused by various error factors of the sensor; where N is a positive integer greater than or equal to 2.

[0042] For example, after obtaining multi-source sensor data, the rate of change of the most recent N consecutive sampling points is calculated as the instantaneous rate of change. The instantaneous rate of change is used as the change feature of the multi-source sensor data to further filter or verify each data. For data whose instantaneous rate of change does not meet the preset change feature, the rate of change of other data that are temporally adjacent and later than the data is obtained. When the signs of the rate of change are inconsistent, the data whose instantaneous rate of change does not meet the preset change feature is removed. In the first target multi-source sensor data, N is a positive integer greater than or equal to 2.

[0043] For example, N is 3.

[0044] For example, in order to correct the sensor data to take into account the data heterogeneity caused by the sensor type of the target sensor, when filtering or verifying each data point by using the instantaneous rate of change and / or the long-term rate of change as the change characteristics of multi-source sensor data, different judgment thresholds can be assigned to the change characteristics according to the sensor type of the target sensor.

[0045] Specifically, for the instantaneous rate of change of flow corresponding to the flow meter, a judgment threshold of [-3% / s, +5% / s] can be assigned to it, retaining data whose instantaneous rate of change is within the range of [-3% / s, +5% / s], and removing data whose instantaneous rate of change is not within the range of [-3% / s, +5% / s].

[0046] Specifically, for the instantaneous change rate of liquid level height corresponding to the liquid level gauge, a judgment threshold of [-2cm / s, +1.5cm / s] can be assigned to it; data with instantaneous change rate of liquid level height within the range of [-2cm / s, +1.5cm / s] are retained, while data with instantaneous change rate outside the range of [-2cm / s, +1.5cm / s] are removed.

[0047] Specifically, the instantaneous rate of change of AIS airspeed corresponding to AIS data can be assigned a value of [-0.3m / s]. 2 +0.25m / s 2 The threshold for determining [] is set; the instantaneous rate of change of AIS airspeed is retained within [-0.3m / s]. 2 +0.25m / s 2 The data, excluding those with AIS instantaneous speed change rates not below -0.3 m / s, were removed. 2 +0.25m / s 2 [Data].

[0048] In one embodiment, to consider the ship's operating status and the data heterogeneity caused by the sensor type of the target sensor, and to correct the sensor data to solve the error problem of multi-source sensors caused by inaccurate sensor acquisition due to the ship's operating status, the multi-source sensor data can be jointly filtered based on the ship's operating data and change characteristics to obtain the first target multi-source sensor data. Specifically, after obtaining the multi-source sensor data, the rate of change of the most recent N consecutive sampling points is calculated as the instantaneous rate of change, and the rate of change of consecutive sampling points within a preset time period is calculated as the long-term rate of change. Further, the ship's operating data corresponding to the time sequence of each rate of change is obtained, and the condition corresponding to the ship's operating data and the preset condition is used to determine whether the preset condition is triggered. When the preset condition is triggered, the preset change characteristics are corrected.

[0049] Specifically, for the instantaneous rate of change of the flow meter, the corresponding ship operation data can be the main engine power; when the main engine power is >90%, the preset condition is confirmed to be triggered, and a judgment threshold of +8% / s can be assigned to the preset change characteristic to correct the preset change characteristic, thereby retaining the data whose instantaneous rate of change is in the range of [-3% / s, +8% / s] and removing the data whose instantaneous rate of change is not in the range of [-3% / s, +8% / s].

[0050] Specifically, for the instantaneous rate of change of liquid level height, the corresponding ship operation data can be the ship's refueling status. When the refueling status is in progress, if the preset condition is confirmed to be triggered, a judgment threshold of +5cm / s can be assigned to the preset change feature to correct the preset change feature, thereby retaining the data whose instantaneous rate of change is within the range of [-2cm / s, +5cm / s] and removing the data whose instantaneous rate of change is not within the range of [-2cm / s, +5cm / s].

[0051] Specifically, for the instantaneous rate of change of AIS speed, the corresponding ship operation data can be the ship's berthing status; when the berthing status is "in berthing," a preset condition is confirmed to be triggered, and a preset change characteristic is assigned ±0.05 m / s. 2 The judgment threshold is used to correct the preset change characteristics, thereby retaining the instantaneous change rate within ±0.05m / s. 2 The data, excluding those with instantaneous rates of change not within ±0.05 m / s, were processed. 2 The data.

[0052] In one embodiment, to consider the ship's operating status and the data heterogeneity caused by the sensor type of the target sensor, and to correct the sensor data to solve the error problem of multi-source sensors caused by the inaccurate sensor acquisition due to the ship's operating status, the multi-source sensor data can be jointly filtered based on the ship's operating data and change characteristics to obtain the first target multi-source sensor data. Specifically, when filtering each data according to the change characteristics of the multi-source sensor data, for data that does not meet the preset change characteristics, the change characteristics of the ship's operating data corresponding to its time sequence are obtained. When the change characteristics of the ship's operating data do not match the change characteristics, the corresponding multi-source sensor data is removed to obtain the first target multi-source sensor data.

[0053] For example, since the flow meter is usually positively correlated with the main engine power and main engine speed, for data that does not conform to the preset change characteristics, the sensor type of the target sensor corresponding to the change characteristics is obtained; when the sensor type of the target sensor is the flow meter, the main engine power and / or main engine speed data corresponding to the time sequence of each change characteristic in the ship operation data are obtained, and the main engine power and / or main engine speed data are calculated as the operation data change rate. When the operation data change rate does not match the change characteristics, the corresponding multi-source sensor data is removed to obtain the first target multi-source sensor data.

[0054] For example, the similarity value between the rate of change of the running data and the change characteristics can be calculated. When the similarity value is less than or equal to a preset similarity judgment threshold, it is confirmed that the rate of change of the running data and the change characteristics do not match.

[0055] For example, since the level gauge is usually related to the ship's roll and pitch values, for data that does not conform to the preset change characteristics, the sensor type of the target sensor corresponding to the change characteristics is obtained; when the sensor type of the target sensor is the level gauge, the ship's roll and / or pitch values ​​corresponding to the time sequence of each change characteristic in the ship's operating data are obtained, and the main ship's roll and / or pitch values ​​are calculated as the rate of change of the operating data. When the rate of change of the operating data does not match the change characteristics, the corresponding multi-source sensor data is removed to obtain the first target multi-source sensor data.

[0056] In one embodiment, the multi-source sensor data is simultaneously filtered based on the ship operation data, the numerical characteristics of the multi-source sensor data, and the variation characteristics of the multi-source sensor data to obtain first target multi-source sensor data. Specifically, for the acquired multi-source sensor data, the multi-source sensor data is first filtered based on the numerical characteristics of the multi-source sensor data and the ship operation data, and then filtered based on the variation characteristics of the multi-source sensor data and the ship operation data to obtain first target multi-source sensor data; or, for the acquired multi-source sensor data, the multi-source sensor data is first filtered based on the variation characteristics of the multi-source sensor data and the ship operation data, and then filtered based on the numerical characteristics of the multi-source sensor data and the ship operation data to obtain first target multi-source sensor data.

[0057] Step S103: Dynamically filter the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data; wherein the ship operation data and the multi-source sensor data correspond in time sequence.

[0058] Regarding the filtering of multi-source sensor data, on the one hand, since the multi-source sensor data is collected by sensors with different sampling frequencies, and the noise variance of liquid level data changes by up to 10 times due to ocean waves, and finally, the rate of change of fuel flow during rapid acceleration of the main engine is far greater than the normal value, the error of Kalman filtering with fixed parameters increases by 4-8 times when the roll is greater than 5°. Furthermore, a single model that does not consider the ship's operating state during filtering cannot simultaneously adapt to the filtering of collected data under both stable navigation and maneuvering conditions.

[0059] Therefore, in this embodiment, the first target multi-source sensor data is dynamically filtered based on the ship operation data to obtain the second target multi-source sensor data.

[0060] For example, when dynamically filtering the multi-source sensor data of the first target, the ship's navigation state can be determined first based on the ship's operation data, and different filtering parameters that determine the filtering intensity can be assigned based on different navigation states. For the filtering parameters that determine the filtering intensity, a first filtering parameter can be assigned to a relatively severe navigation state, and a second filtering parameter can be assigned to a relatively stable navigation state. The first filtering intensity when filtering with the first filtering parameter is stronger than the second filtering intensity of the second filtering parameter.

[0061] One possible implementation is to use Kalman filtering to filter the multi-source sensor data of the first target to obtain the multi-source sensor data of the second target.

[0062] Specifically, Kalman filtering is an algorithm that uses the state equation of a linear system to make an optimal estimate of the system state through the system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimation can also be regarded as a filtering process. In this invention, the process noise parameters and observation noise parameters can be predetermined when performing Kalman filtering. The process noise parameters and observation noise parameters are then used to filter the multi-source sensor data of the first target to obtain the multi-source sensor data of the second target.

[0063] Step S104: Dynamically compensate the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data; wherein the ship operation data and the second target multi-source sensor data correspond in time sequence.

[0064] Sensors installed on ships operating in rivers and oceans are severely affected by the aquatic environment. The ship's pitching or rolling can cause distortion in liquid level measurement, with measurement errors reaching up to 15% in extreme cases. In this embodiment, the multi-source sensor data of the second target is dynamically compensated based on the ship's operating data to obtain corrected multi-source sensor data.

[0065] For example, pitch and roll data corresponding to the liquid level data in the second target multi-source sensor data can be obtained from the ship operation data. Further, the difference between the measured liquid level and the actual liquid level when pitch and roll cause liquid level distortion can be calculated based on the pitch and roll data. Finally, the difference is compensated to the measured liquid level to perform liquid level compensation on the second target multi-source sensor data to obtain the corrected multi-source sensor data.

[0066] Step S105: Calculate the sub-ship energy consumption based on the corrected multi-source sensor data and the corresponding sensor type of the target sensor.

[0067] In this embodiment, a pre-calibrated segmented linear tank capacity conversion model is first used to convert the liquid level data for unified metering processing. Specifically, the correspondence between the liquid level height and the corresponding volume of the ship under different tank capacities can be tested in advance, and a segmented linear tank capacity conversion model can be further established. Finally, the tank liquid level data is converted into volume data according to the tank capacity conversion model.

[0068] Specifically, Table 1 is an illustrative table of raw cabin capacity data according to an embodiment of the present invention:

[0069] Table 1. Original Cabin Capacity Data

[0070]

[0071] In Table 1, h represents the liquid level height in cm, and V represents the corresponding volume in m³. 3 .

[0072] Furthermore, the piecewise linear tank capacity conversion model based on equation (1) can be used:

[0073] V(h)=V k-1 +(V k -V k-1 ) / (h k -h k-1 )*(hh k-1 ),h k-1 ≤h<h k (1)

[0074] In equation (1), V(h) represents the volume when the liquid level is h. k-1 The liquid level height is indicated by h. k-1 The volume, V k The liquid level height is indicated by h. k The volume, h k h is the minimum liquid level height greater than h in the original tank capacity data table. k-1 The maximum liquid level height that is less than h in the original data table of the tank capacity.

[0075] Furthermore, for flow meter data, the flow meter type is determined based on the data unit output by the flow meter and a pre-established flow meter type identification matrix, thereby obtaining the volume; wherein, the flow meter may include volumetric flow meters and mass flow meters, and the data unit of the volumetric flow meter may include m³ / h, m 3 The units for mass flow meters can include kg / h and kg.

[0076] Furthermore, based on the corrected multi-source sensor data and the sensor type of the corresponding target sensor, the energy consumption of the sub-ship corresponding to each sensor is calculated.

[0077] Specifically, for flow meter consumption data statistics, if the target sensor is a volumetric flow meter, it is necessary to combine the density value and convert it into mass units. The density value can be obtained through the flow meter's real-time density, manually entered density, or a standard density table. After conversion to mass units, energy consumption is further calculated.

[0078] Specifically, for instantaneous flow meters, the energy consumption is calculated using equation (2):

[0079] consume t0～t1 =∫v(t)dt,t∈(t0,t1) (2)

[0080] In equation (2), consume t0～t1 This represents the energy consumption data calculated by the instantaneous flow meter during the time periods t0 and t1.

[0081] Specifically, for the cumulative flow meter, the energy consumption is calculated using equation (3):

[0082] consume t0～t1 =x t1 -x t0 (3)

[0083] In equation (3), consume t0～t1 This represents the energy consumption data calculated by the cumulative flow meter during the time periods t0 and t1, x. t1 x represents the value of the cumulative flow meter at time t1. t0 This represents the value of the cumulative flow meter at time t0.

[0084] Specifically, for the statistics of liquid level gauge consumption data, the liquid level data is converted into the chamber inventory data through the liquid level segmented linear chamber capacity conversion model using formula (4), and the consumption is calculated by combining the manually filled-in addition data.

[0085] consumer t0～t1 =(M t1 -M t0 )ρ+add (4)

[0086] In formula (4), M t0 M represents the stock at time t0. t1 Let ρ be the stock at time t1, ρ be the density, and add be the manually entered addition data.

[0087] Step S106: Based on the ship operation data, fuse the energy consumption of each of the sub-ships to obtain ship energy consumption data.

[0088] As mentioned above, since the level gauge is greatly affected by the ship's trim and roll, the ship's operating data can be considered to determine the ship's operating status, and then different fusion weights can be assigned to the energy consumption of each sub-ship based on the ship's operating status.

[0089] In one embodiment, the energy consumption of each of the sub-ships is fused based on the ship operation data using a dynamic weight matrix method; specifically, after obtaining the ship operation data, at least one of the following is extracted from the ship operation data: rate of change of speed, roll angle, and wind speed.

[0090] For example, when the rate of change of speed is less than 0.2 kn / min, the energy consumption of the sub-ship corresponding to the flow meter is assigned a fusion weight of 0.4, and the energy consumption of the sub-ship corresponding to the level gauge is assigned a fusion weight of 0.6.

[0091] For example, when the roll angle is greater than 5°, a fusion weight of 0.7 is assigned to the energy consumption of the sub-ship corresponding to the flow meter, and a fusion weight of 0.3 is assigned to the energy consumption of the sub-ship corresponding to the level gauge.

[0092] For example, when the wind speed is greater than level 7, the energy consumption of the sub-ship corresponding to the flow meter is assigned a fusion weight of 0.65, and the energy consumption of the sub-ship corresponding to the level gauge is assigned a fusion weight of 0.35.

[0093] Furthermore, by fusing the energy consumption of each of the sub-ships using equation (5), the ship energy consumption data is obtained:

[0094] consume = consume flow *w flow +consume liquid *w liquid (5)

[0095] In equation (5), consume flow This represents the energy consumption of the sub-ship calculated by the flow meter, w flow This indicates the fusion weight of the energy consumption of the sub-ship corresponding to the flow meter, consume liquid This represents the energy consumption of the sub-ship calculated by the level gauge, w liquid This indicates the fusion weight of the energy consumption of the sub-ship corresponding to the level gauge.

[0096] This embodiment provides a method for calculating ship energy consumption. The method includes: acquiring ship operation data and multi-source sensor data collected by target sensors of the target ship. ；The target sensors include flow meters, level gauges, and AIS systems. Based on the changing characteristics of the ship operation data and the multi-source sensor data, the multi-source sensor data is dynamically filtered to obtain first target multi-source sensor data. The changing characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data. Based on the ship operation data, the first target multi-source sensor data is dynamically filtered to obtain second target multi-source sensor data. The ship operation data corresponds to the time sequence of the multi-source sensor data. Based on the ship operation data, the second target multi-source sensor data is dynamically compensated to obtain corrected multi-source sensor data. The data corresponds to the time sequence of the second target multi-source sensor data; the energy consumption of the sub-ship is calculated based on the corrected multi-source sensor data and the corresponding sensor type; the energy consumption of each sub-ship is fused based on the ship operation data to obtain the ship energy consumption data; the above method can dynamically filter, dynamically screen, and dynamically compensate the multi-source sensor data by considering the acquisition errors of each sensor in the multi-source sensor data, the errors caused by the ship's interference from the water environment, and the navigation status of the target ship, so as to obtain more accurate corrected multi-source sensor data; furthermore, the energy consumption of the sub-ship is calculated using the corrected multi-source sensor data, and the energy consumption of each sub-ship is fused based on the ship operation data, so as to obtain more accurate ship energy consumption data.

[0097] As an exemplary embodiment, the step of dynamically filtering the multi-source sensor data based on the change characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data includes: dynamically filtering the multi-source sensor data based on the ship operation data to obtain the first multi-source sensor data within a preset value range; wherein, the ship operation data and the multi-source sensor data are time-series corresponding, and the preset value range is determined based on the time-series corresponding ship operation data and the numerical characteristics of the ship operation data; and dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain the first target multi-source sensor data.

[0098] In this embodiment, the multi-source sensor data is dynamically filtered based on the ship operation data to obtain the first multi-source sensor data within a preset value range. This is to give the ship dynamic filtering conditions by considering the ship's operating status when filtering the multi-source sensor data. The ship operation data and the multi-source sensor data are time-series corresponding, and the preset value range is determined based on the time-series corresponding ship operation data and the numerical characteristics of the ship operation data.

[0099] In this embodiment, the first multi-source sensor data is dynamically filtered based on the ship operation data and the change characteristics, so as to give the ship dynamic filtering conditions by considering the ship's operating status when filtering the multi-source sensor data; thus obtaining the first target multi-source sensor data.

[0100] Specifically, as an exemplary embodiment, the step of dynamically filtering the multi-source sensor data based on the ship operation data to obtain the first multi-source sensor data within a preset numerical range includes: determining the target sliding window length based on the acquisition frequency of the target sensor; performing sliding window truncation on the sensor data corresponding to each target sensor in the multi-source sensor data based on the target sliding window length to obtain multiple sliding window intervals; determining the quartiles of each sliding window interval based on the numerical characteristics of each sliding window interval; acquiring roll angle data corresponding to the time sequence of each sliding window interval in the ship operation data; determining the correction coefficient for each sliding window interval based on the roll angle data; wherein the roll angle is positively correlated with the correction coefficient; and filtering each sensor data based on the quartiles and the correction coefficient to obtain the first multi-source sensor data.

[0101] In this embodiment, dynamic interquartile range is used. The Range (IQR) algorithm is used to filter data based on the numerical characteristics of multi-source sensor data. The IQR algorithm is an outlier detection method based on statistical quartiles. It determines the core range of data distribution by calculating the difference between the 25th percentile (Q1) and the 75th percentile (Q3) of the dataset. Specifically, the target sliding window length is determined based on the acquisition frequency of the target sensor. Based on the target sliding window length, each sensor data is truncated into a sliding window to obtain multiple sliding window intervals. The quartiles of each sliding window interval are determined based on the numerical characteristics of each sliding window interval. Further, [Q1-k*IQR, Q3+k*IQR] is used as the numerical characteristics. Each data is further filtered or verified based on the numerical characteristics. Data that falls within the [Q1-k*IQR, Q3+k*IQR interval and conforms to the preset data distribution range is retained, and data that does not fall within the [Q1-k*IQR, Q3+k*IQR interval and does not conform to the preset distribution range is removed. Finally, the first target multi-source sensor data is obtained. In this embodiment, K is 1.5.

[0102] Furthermore, to consider the time-varying nature of the statistical characteristics of multi-source sensor data under different navigation states and to adapt the filtering to the navigation state, this invention further considers dynamic numerical range filtering of ship operation data and dynamic correction of quartiles. Specifically, in the ship operation data, roll angle data corresponding to the time sequence of each sliding window interval is obtained; a correction coefficient for each sliding window interval is determined based on the roll angle data; wherein the roll angle is positively correlated with the correction coefficient; and the sensor data is filtered based on the quartiles and the correction coefficient to obtain the first target multi-source sensor data.

[0103] For example, after obtaining the roll angle data, for roll angles less than 3°, it is confirmed that the ship is in a calm state at this time, and a detection strategy that strictly detects weak anomalies is adopted, in which case the correction coefficient k is taken as 1.5.

[0104] For example, after obtaining the roll angle data, for roll angles greater than or equal to 3° and less than or equal to 8°, it is confirmed that the ship is in normal navigation state at this time, and a detection strategy with a moderately relaxed threshold is adopted, in which case the correction coefficient k is taken as 2.

[0105] For example, after obtaining the roll angle data, for roll angles greater than 8°, it is confirmed that the ship is in a severe sea state. A detection strategy to avoid misjudging motion and causing fluctuations is adopted, and the correction coefficient k is taken as 2.5.

[0106] As an exemplary embodiment, the step of dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain the first target multi-source sensor data includes: calculating a first rate of change of a preset number of time-series continuous multi-source sensor data; determining a first rate of change threshold based on the sensor type of the target sensor corresponding to the first rate of change; filtering the multi-source sensor data based on the first rate of change threshold and the first rate of change to obtain multiple second multi-source sensor data exceeding the first rate of change threshold; acquiring a first trend feature of third multi-source sensor data whose time sequence is later than the second multi-source sensor data; if the first trend feature satisfies a preset change feature, acquiring a second trend feature of the ship operation data corresponding to the time sequence of the second multi-source sensor data based on the sensor type of the second multi-source sensor data;

[0107] If the second trend feature meets the preset trend feature, the second multi-source sensor data is removed to obtain the first target multi-source sensor data.

[0108] In this embodiment, the multi-source sensor data is filtered based on the reasonableness check of the change rate of adjacent data points to obtain the first target multi-source sensor data.

[0109] Specifically, the process involves calculating a first rate of change for a predetermined number of sequentially continuous first multi-source sensor data; determining a first rate of change threshold based on the sensor type of the target sensor corresponding to the first rate of change; filtering the first multi-source sensor data based on the first rate of change threshold and the first rate of change to obtain multiple second multi-source sensor data exceeding the first rate of change threshold, and filtering multiple abnormally changing second multi-source sensor data as suspicious points; further, acquiring a first trend feature of third multi-source sensor data whose time sequence is later than the second multi-source sensor data; if the first trend feature satisfies a preset trend feature, acquiring a second trend feature of the ship operation data corresponding to the time sequence of the second multi-source sensor data based on the sensor type of the second multi-source sensor data; if the second trend feature satisfies the preset trend feature, removing the second multi-source sensor data to obtain the first target multi-source sensor data, thereby dynamically filtering the first multi-source sensor data by combining the first trend feature of the second multi-source sensor data with the second trend feature of the corresponding ship operation data to obtain the first target multi-source sensor data.

[0110] Regarding the filtering of multi-source sensor data, on the one hand, since the multi-source sensor data is collected by sensors with different sampling frequencies, and the noise variance of liquid level data changes by up to 10 times due to ocean waves, and finally, the rate of change of fuel flow during rapid acceleration of the main engine is far greater than the normal value, the error of Kalman filtering with fixed parameters increases by 4-8 times when the roll is greater than 5°. Furthermore, a single model that does not consider the ship's operating state during filtering cannot simultaneously adapt to the filtering of collected data under both stable navigation and maneuvering conditions.

[0111] To address this issue, as an exemplary embodiment, the step of dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data includes: determining the operating state corresponding to each of the multi-source sensor data based on the ship operation data; determining a first filtering parameter and a second filtering parameter based on the operating state; and filtering the first target multi-source sensor data based on the first filtering parameter and the second filtering parameter to obtain the second target multi-source sensor data; wherein the first filtering parameter may be the Q matrix corresponding to process noise in Kalman filtering, and the second filtering parameter may be the R matrix corresponding to observation noise.

[0112] Specifically, in this embodiment, the operating status corresponding to the data from each of the multi-source sensors is determined based on the ship's operating data.

[0113] For example, Table 2 is a comparison table of ship operation data and operation status according to an embodiment of the present invention. See Table 2:

[0114] Table 2. Comparison of Ship Operation Data and Operation Status

[0115]

[0116] Furthermore, after determining the ship's operating status, the process noise and observation noise parameters of the Kalman filter are dynamically adjusted according to the ship's operating status.

[0117] For example, when the ship is in a steady-state operation, the process noise Q for the Kalman filter of the flow meter data is taken as diag(0.01,0.001), and the observation noise R is taken as 0.05; the process noise Q for the Kalman filter of the level gauge data is taken as diag(0.02,0.005), and the observation noise R is taken as 0.1; the process noise Q for the Kalman filter of the AIS data is taken as diag(0.1,0.03), and the observation noise R is taken as 0.3.

[0118] For example, when the ship is in maneuvering mode, the process noise Q of the Kalman filter applied to the flow meter data is taken as diag(0.05,0.01), and the observation noise R is taken as 0.1; the process noise Q of the Kalman filter applied to the level gauge data is taken as diag(0.1,0.02), and the observation noise R is taken as 0.3; the process noise Q of the Kalman filter applied to the AIS data is taken as diag(0.3,0.1), and the observation noise R is taken as 0.5.

[0119] For example, when the ship is operating in a severe sea state mode, the process noise Q of the Kalman filter for the flow meter data is taken as diag(0.2,0.05), and the observation noise R is taken as 0.3; the process noise Q of the Kalman filter for the level gauge data is taken as diag(0.5,0.1), and the observation noise R is taken as 1.2; the process noise Q of the Kalman filter for the AIS data is taken as diag(1.0,0.3), and the observation noise R is taken as 2.0.

[0120] For example, when the ship is in transition mode, the process noise of the flow meter data after Kalman filtering is linearly interpolated, and the observed noise R is taken as 1.5 times the maximum value of R; the process noise Q of the level gauge data after Kalman filtering is linearly interpolated, and the observed noise R is taken as 2 times the maximum value of R.

[0121] As an exemplary embodiment, the step of dynamically compensating the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data includes: extracting pitch angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data corresponding to the time sequence of the second target multi-source sensor data from the ship operation data; and performing liquid level compensation on the second target multi-source sensor data using formula (6) based on the pitch angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data to obtain the corrected multi-source sensor data.

[0122]

[0123] θ = arctan(draft) aft -draft fore ) / LBP

[0124]

[0125] In equation (6), For the corrected multi-source sensor data, X is the second target multi-source sensor data, θ is the pitch angle data, and draft fore Based on previous draft data, draft aft The figures are: Aft draft, LBP (length), and Beam (breadth). This is the roll angle data.

[0126] This embodiment provides a ship energy consumption calculation device, such as... Figure 2 As shown, it includes:

[0127] The acquisition module 501 is used to acquire ship operation data and multi-source sensor data collected by the target sensors of the target ship; wherein, the target sensors include flow meters, level gauges, and AIS systems;

[0128] The filtering module 502 is used to dynamically filter the multi-source sensor data based on the change characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data; wherein the change characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data;

[0129] The filtering module 503 is used to dynamically filter the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data; wherein the ship operation data and the multi-source sensor data correspond in time sequence.

[0130] The compensation module 504 is used to dynamically compensate the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data; wherein the ship operation data and the second target multi-source sensor data correspond in time sequence.

[0131] Calculation module 505 is used to calculate the energy consumption of the sub-ship based on the corrected multi-source sensor data and the corresponding sensor type;

[0132] Fusion module 506 is used to fuse the energy consumption of each of the sub-ships based on the ship operation data to obtain ship energy consumption data.

[0133] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments.

[0134] It should be noted that the above modules, as part of the device, can be implemented in software or hardware, with the hardware environment including the network environment.

[0135] This invention also provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs; and the processor is used to execute the methods described in any of the above embodiments by running the computer programs stored in the memory.

[0136] Figure 3 This is a structural block diagram of an optional computer device according to an embodiment of this application, such as... Figure 3 As shown, the system includes a processor 10, a communication interface 20, a memory 30, and a communication bus 40. The processor 10, communication interface 20, and memory 30 communicate with each other via the communication bus 40.

[0137] Memory 30 is used to store computer programs;

[0138] When the processor 10 executes the computer program stored in the memory 30, it implements the ship energy consumption calculation method as described in any of the above embodiments.

[0139] Optionally, in this embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0140] The communication interface is used for communication between the aforementioned computer equipment and other devices.

[0141] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0142] The processors mentioned above can be general-purpose processors, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; they can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0143] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0144] Those skilled in the art will understand that Figure 3 The structure shown is for illustrative purposes only. The device that implements any of the methods in the above embodiments can be a terminal device, such as a smartphone (e.g., an Android phone, an iOS phone), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 3 This does not limit the structure of the aforementioned electronic device. For example, the terminal device may also include components that are more... Figure 3 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 3 The different configurations shown.

[0145] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0146] As an exemplary embodiment, this application also provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the method steps of any one of the embodiments in this application at runtime.

[0147] Optionally, in this embodiment, the storage medium described above can be used to execute program code for the method steps of the embodiments of this application.

[0148] Optionally, in this embodiment, the storage medium may be located on at least one of the network devices in the network shown in the above embodiment.

[0149] Optionally, in this embodiment, the storage medium is configured to store methods for performing the above embodiments.

[0150] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated in this embodiment.

[0151] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0152] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0153] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods in the above embodiments.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0155] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the solution provided in this embodiment, depending on actual needs.

[0156] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0157] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0158] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for calculating ship energy consumption, characterized in that, The method for calculating ship energy consumption includes: Acquire ship operation data and multi-source sensor data collected by target sensors on the target ship; wherein, the target sensors include flow meters, level gauges, and AIS systems; Based on the changing characteristics of the ship operation data and the multi-source sensor data, the multi-source sensor data is dynamically filtered to obtain the first target multi-source sensor data; wherein, the changing characteristics of the ship operation data and the multi-source sensor data correspond to the time sequence of the multi-source sensor data; Based on the ship operation data, the first target multi-source sensor data is dynamically filtered to obtain the second target multi-source sensor data; wherein, the ship operation data and the multi-source sensor data correspond in time sequence. Based on the ship operation data, the multi-source sensor data of the second target is dynamically compensated to obtain corrected multi-source sensor data; wherein, the ship operation data and the multi-source sensor data of the second target correspond in time sequence. The energy consumption of the sub-ship is calculated based on the corrected multi-source sensor data and the corresponding sensor types. Based on the ship operation data, the energy consumption of each of the sub-ships is fused to obtain the ship energy consumption data.

2. The ship energy consumption calculation method as described in claim 1, characterized in that, The step of dynamically filtering the multi-source sensor data based on the changing characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data includes: Based on the ship operation data, the multi-source sensor data is dynamically filtered by numerical range to obtain the first multi-source sensor data within a preset numerical range; wherein, the ship operation data and the multi-source sensor data are time-series corresponding, and the preset numerical range is determined based on the time-series corresponding ship operation data and the numerical characteristics of the ship operation data; Based on the ship operation data and the change characteristics, the first multi-source sensor data is dynamically filtered to obtain the first target multi-source sensor data.

3. The ship energy consumption calculation method as described in claim 2, characterized in that, The step of dynamically filtering the multi-source sensor data based on the ship operation data to obtain the first multi-source sensor data within a preset value range includes: The length of the target sliding window is determined based on the acquisition frequency of the target sensor; Based on the target sliding window length, the sensor data corresponding to each target sensor in the multi-source sensor data are respectively truncated by sliding window to obtain multiple sliding window intervals; The quartiles of each sliding window interval are determined based on the numerical characteristics of each sliding window interval. From the ship operation data, obtain the roll angle data corresponding to the timing of each sliding window interval; The correction coefficient for each sliding window interval is determined based on the roll angle data; wherein the roll angle is positively correlated with the correction coefficient. The sensor data is filtered based on the quartiles and the correction coefficients to obtain the first multi-source sensor data.

4. The ship energy consumption calculation method as described in claim 2, characterized in that, The step of dynamically filtering the first multi-source sensor data based on the ship operation data and the change characteristics to obtain the first target multi-source sensor data includes: Calculate the first rate of change of a predetermined number of time-series continuous multi-source sensor data; A first rate of change threshold is determined based on the sensor type of the target sensor corresponding to the first rate of change; Based on the first rate of change threshold and the first rate of change, the multi-source sensor data is filtered to obtain multiple second multi-source sensor data that exceed the first rate of change threshold. Acquire the first trend feature of the third multi-source sensor data whose timing is later than that of the second multi-source sensor data; If the first trend feature satisfies the preset trend feature, the second trend feature of the ship operation data corresponding to the time sequence of the second multi-source sensor data is obtained based on the sensor type of the second multi-source sensor data. If the second trend feature meets the preset trend feature, the second multi-source sensor data is removed to obtain the first target multi-source sensor data.

5. The ship energy consumption calculation method as described in claim 1, characterized in that, The step of dynamically filtering the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data includes: The operating status corresponding to each of the multi-source sensor data is determined based on the ship's operating data; The first and second filter parameters are determined based on the operating status. The first target multi-source sensor data is filtered based on the first filtering parameter and the second filtering parameter to obtain the second target multi-source sensor data.

6. The ship energy consumption calculation method as described in claim 1, characterized in that, The step of dynamically compensating the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data includes: Extract the pitch angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data corresponding to the time sequence of the multi-source sensor data of the second target from the ship operation data; Based on the trim angle data, roll angle data, forward draft data, aft draft data, ship length data, and ship beam data, the following formula is used to perform liquid level compensation on the second target multi-source sensor data to obtain the corrected multi-source sensor data: θ=arctan(draft aft -draft fore ) / LBP In the formula, For the corrected multi-source sensor data, X is the second target multi-source sensor data, θ is the pitch angle data, and draft fore Based on previous draft data, draft aft The figures are: Aft draft, LBP (length), and Beam (breadth). This is the roll angle data.

7. The ship energy consumption calculation method as described in claim 1, characterized in that, The process of fusing the energy consumption of each of the sub-ships based on the ship operation data to obtain ship energy consumption data includes: Among the ship operation data, at least one of the following is obtained: rate of change of speed data, roll angle data, and wind speed data; Based on the speed change rate data, roll angle data, or wind speed data, the energy consumption fusion weights corresponding to each of the sensors are determined respectively. The energy consumption of each sub-ship is fused based on the energy consumption fusion weight to obtain the ship energy consumption data.

8. A ship energy consumption calculation device, characterized in that, The ship energy consumption calculation device includes: The acquisition module is used to acquire ship operation data and multi-source sensor data collected by target sensors of the target ship; wherein, the target sensors include flow meters, level gauges, and AIS systems; The filtering module is used to filter the multi-source sensor data based on the numerical and variation characteristics of the ship operation data and the multi-source sensor data to obtain the first target multi-source sensor data. The filtering module is used to filter the first target multi-source sensor data based on the ship operation data to obtain the second target multi-source sensor data. The liquid level compensation module is used to perform liquid level compensation on the second target multi-source sensor data based on the ship operation data to obtain corrected multi-source sensor data; The calculation module is used to calculate the energy consumption of the sub-ship based on the corrected multi-source sensor data and the corresponding sensor types; The fusion module is used to fuse the energy consumption of each of the sub-ships based on the ship operation data to obtain ship energy consumption data.

9. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the ship energy consumption calculation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the ship energy consumption calculation method according to any one of claims 1 to 7.

Images