Polar region ship risk analysis and decision-making system

Abstract

The invention provides a polar region ship risk analysis and decision-making system, and belongs to the technical field of ship safety, the system comprises a user interaction layer, a data processing layer and a data storage layer, and further comprises a current condition risk assessment module, a loss calculation module and a system data updating module; the user interaction layer provides an interface for interacting with a crew for the three modules; the data processing layer provides support for Bayesian network model construction, analysis and calculation of the current situation risk assessment module, also provides data processing capability for calculation of all expenses in the loss calculation module, and realizes data conversion and storage in the system data updating module; and the data storage layer provides data storage and reading services for the three modules to ensure that the modules can obtain required data. According to the method, ice trapping and ice damage risks possibly encountered by the ship can be evaluated, decision making and loss calculation are assisted, effective support and navigation suggestions are provided for sailors, and support is provided for actual polar region ship risk management.

Description

Technical Field

[0001] The present invention belongs to the technical field of ship safety, and in particular, relates to a polar region ship risk analysis and decision-making system. Background Art

[0002] As global temperatures continue to rise and polar glaciers continue to melt, the commercial, normalized, and project-based operation of ships in the Arctic will become a reality. However, the harsh natural environment, special geographical location, and complex navigation conditions of the Arctic pose great threats and challenges to the safety of ship navigation. Ice entrapment and ice damage are considered to be the most serious risks. Once they occur, they may cause damage to the ship, property loss, environmental damage, and even casualties. At present, most of the research on risk assessment of ships in Arctic ice areas is theoretical. Although it can guide actual production operations, it still cannot be directly applied to the navigation process of ships. Therefore, it is necessary to design and implement a risk assessment and decision-making system for ships in Arctic ice areas. Using the Python programming language, the Bayesian network model is compiled to form a graphical interface that interacts with the user, and the three system functions of risk assessment, decision support, and loss calculation are realized. While assessing the risks of ships in the current environment, effective support and suggestions are provided for crew operations and navigation decisions. Summary of the invention

[0003] Aiming at the two risk factors of ice entrapment and ice damage faced by polar ships, the present invention designs and establishes a polar ship risk analysis and decision-making system by using Python language.

[0004] The present invention is implemented through the following technical solutions: A polar region ship risk analysis and decision-making system:

[0005] The system includes a user interaction layer, a data processing layer and a data storage layer;

[0006] The user interaction layer is used to select the current risk node status, display reasoning results and auxiliary decision-making suggestions, and display economic loss results;

[0007] The data processing layer performs parameter learning and data reasoning through a Bayesian network model;

[0008] The data storage layer is used to store accident samples, recommended measures and parameters.

[0009] Furthermore, the human-computer interface display content of the user interaction layer includes current situation risk assessment, loss calculation, system data update and system exit.

[0010] Furthermore, the parameter transfer path of the data processing layer is as follows: the human-computer interface transforms the ice area and ship accident data into the computer engine, and through Python software, the input computer data is converted into Python type, and then the Bayesian network model is constructed using the pgmpy library and analyzed and calculated;

[0011] The Bayesian network returns the inference data to the Python engine, which converts the data into the original type of data of the computer engine and transmits it back to the computer engine, displays the results on the human-computer interface, and realizes the functions of providing risk analysis and auxiliary decision-making.

[0012] Further, the system includes a current situation risk assessment module, a loss calculation module and a system data update module;

[0013] The user interaction layer provides an interface for the three modules to interact with the crew, and the crew operates each module through this layer;

[0014] The data processing layer provides support for the construction, analysis and calculation of the Bayesian network model of the current situation risk assessment module, and also provides data processing capabilities for the calculation of various expenses in the loss calculation module, while realizing data conversion and storage in the system data update module;

[0015] The data storage layer provides data storage and reading services for the three modules, ensuring that the modules can obtain the required data.

[0016] Furthermore, the current situation risk assessment module displays content including risk factor selection, Bayesian network reasoning results and recommended measures, and has risk assessment and decision-making support functions;

[0017] The loss calculation module briefly calculates the economic losses of the ship after an ice-trapped or ice-damaged accident. The parameters include whether the ship is docked after the accident, whether it returns empty-handed, the section where the accident occurred, the remaining mileage of the section, and the thrust loss after the accident.

[0018] Furthermore, the accident loss calculation takes into account the maintenance cost F1, which includes annual maintenance and single maintenance costs such as propellers, the increased fuel cost F2 caused by the thrust reduction due to propeller structural damage, the transit port cost F3 and the possible loss F4 caused by returning to the maintenance port empty, as shown in the following formula:

[0019] F l =F1+F2+F3+F4

[0020] The calculation of maintenance cost F1 is based on the annual maintenance rate of ice-resistant ships being 1.606%;

[0021] The additional fuel cost F2 depends on the fuel consumption rate (f), fuel price (bp) and single voyage time (time). The fuel cost is defined as:

[0022] F2=f×time×b p

[0023] Assuming the fuel price is 500USD / ton; according to the propeller law, the fuel consumption rate (f) can be calculated as follows:

[0024] f=SFOC×BHP

[0025]

[0026] Among them, SFOC stands for specific fuel consumption (unit: g / kW·h), with a fixed value of 185g / kW·h; BHP is the engine brake horsepower (unit: kW); m is the proportional factor, Vi is the speed of the container ship sailing in different sections, BHPmax is the maximum output power of the main engine; Vmax is the maximum ship speed;

[0027] The transit port fee F3 mainly includes (a) port fees, (b) container loading and unloading fees, (c) port pilotage fees and (d) icebreaking fees at specific ports; each fee is generally calculated based on the net tonnage or container volume of the ship and the relevant rate standards, as shown in the following formula:

[0028]

[0029] (b) Container handling charges = handling rate (unit: USD / TEU) × vessel container capacity (unit: TEU)

[0030] (c) Port pilotage fee = pilotage rate (unit: USD / ton) × net ton;

[0031] (d) Icebreaking fee for a specific port = Icebreaking rate (unit: USD / ton) × gross tonnage

[0032] Among them, the icebreaking rate is obtained from the Russian Northern Sea Route Administration;

[0033] The loss F4 caused by returning to the repair port empty is calculated based on the freight index, assuming that the container freight rate is 900USD / TEU.

[0034] Furthermore, the system data update module is divided into accident data update and accident loss parameter update parts. The system user discretizes the newly occurred ice entrapment and ice damage accident reports according to the divided risk factors, inputs them into the corresponding box of the accident data update part, and then updates and adds to the software accident database; in view of the different losses after ice entrapment and ice damage accidents of different ship types, the accident loss parameter update module modifies the corresponding parameters according to the specific type of ship where the system user is located to obtain a more accurate economic loss estimate.

[0035] Beneficial effects of the present invention

[0036] The present invention designs and develops a risk assessment and decision-making system that can be actually applied to ships sailing in polar ice areas. The system is simple, convenient and fast to operate, and can assess the ice trapping and ice damage risks that ships may encounter, assist in decision-making and calculate losses, provide effective support and navigation advice for crew members, and provide support for actual polar ship risk management. The present invention has broadened the practical application scope of risk assessment for ships in Arctic ice areas to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a design diagram of the risk assessment and decision-making system of the present invention.

[0038] Figure 2 It is the risk analysis and decision-making system interface of the present invention.

[0039] Figure 3 It is a schematic diagram of the processing layer parameter transmission path of the present invention.

[0040] Figure 4 It is the previous situation risk assessment module of the present invention.

[0041] Figure 5 It is the loss calculation module of the present invention.

[0042] Figure 6 It is the system data updating module of the present invention.

[0043] Figure 7 It is the accident data updating module of the present invention.

[0044] Figure 8 It is the loss parameter updating module of the present invention.

[0045] Fig. 9 The diagram is set when the "lookout negligence" and "sea ice thickness" nodes of the present invention occur.

[0046] Fig.10 These are the relevant suggestions for when the "poor ice conditions" node occurs in the present invention.

[0047] Fig.11This is a sample calculation of the present invention, where (a) is the loss setting and (b) is the calculation result. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The experimental methods used in the following examples are conventional methods unless otherwise specified. The materials, reagents, methods and instruments used are conventional materials, reagents, methods and instruments in the art unless otherwise specified, and can be obtained through commercial channels by those skilled in the art.

[0050] The polar region ship risk analysis and decision-making system designed by the present invention is divided into three levels based on Python language: user interaction layer, data processing layer and data storage layer. Figure 1 shown.

[0051] The user interaction layer is used to select the current risk node status, display the reasoning results and auxiliary decision suggestions, and display the economic loss results; user interaction simply refers to the communication between people and computers. There are five main elements of interactive behavior that are widely recognized and respected in the interactive field: people, actions, purposes, media, and scenes. Specifically, in this invention, it mainly focuses on the interaction between the polar ship risk analysis and decision-making system and the crew. As a polar ship risk analysis and decision-making system, the interface is as follows Figure 2 As shown, the human-computer interface display content of the user interaction layer includes current situation risk assessment, loss calculation, system data update and system exit.

[0052] The design of this interface uses the third-party library Tkinter in Python, which is a standard GUI (Graphical User Interface) library in the Python language and supports cross-platform GUI program development. It is a module in Python specifically used for window design. It has the characteristics of simple structure and high compatibility, and is suitable for small program writing.

[0053] The data processing layer performs parameter learning and data reasoning through the Bayesian network model; data processing is a key step in the realization of a system. In the process of risk assessment, the parameter transmission path of the data processing layer is as follows: the human-computer interface converts the ice area and ship accident data into the computer engine, and through Python software, the input computer data is converted into Python type, and then the Bayesian network model is constructed using the pgmpy library for analysis and calculation;

[0054] The Bayesian network returns the inference data to the Python engine, which converts the data into the original type of data of the computer engine and transmits it back to the computer engine, displays the results on the human-computer interface, and realizes the functions of providing risk analysis and auxiliary decision-making. The working process of the processing layer is as follows Figure 3 shown.

[0055] The data storage layer is used to store accident samples, recommended measures and parameters.

[0056] The software data storage of the present invention is written using the Pandas library in Python. The Pandas library is a third-party library in Python and is a tool based on NumPy, mainly for solving data analysis tasks. The read_csv() and to_csv() commands of the Pandas library can read and save csv files of a specified path, and are written as the data storage layer of the software.

[0057] Correspondingly, the system of the present invention includes a current situation risk assessment module, a loss calculation module and a system data update module;

[0058] The user interaction layer provides an interface for the three modules to interact with the crew, and the crew operates each module through this layer;

[0059] The data processing layer provides support for the construction, analysis and calculation of the Bayesian network model of the current situation risk assessment module, and also provides data processing capabilities for the calculation of various expenses in the loss calculation module, while realizing data conversion and storage in the system data update module;

[0060] The data storage layer provides data storage and reading services for the three modules, ensuring that the modules can obtain the required data.

[0061] Current Situation Risk Assessment Module Figure 4As shown, the main display content includes risk factor selection, Bayesian network reasoning results and recommended measures, etc., with risk assessment and decision-making support functions. The Bayesian network model is mainly built based on the pgmpy library in Python. Pgmpy is an open source project and a Python library that can be used to process probabilistic graphical models. The BayeisanModel function is used to build the Bayesian network model structure, and then the TabularCPD function is used to build the conditional probability distribution CPD (condition probability distribution) table. Finally, the parameter data of CPD is added to the Bayesian network structure to complete the Bayesian network model establishment.

[0062] The loss calculation module is mainly based on the brief calculation of the economic losses after the ship is trapped in ice or damaged by ice, such as Figure 5 As shown in the figure, the main parameters include whether to dock after the accident, whether to return empty, the segment where the accident occurred, the remaining mileage of the segment, and the thrust loss after the accident. The accident loss calculation of this system takes into account the maintenance cost F1 (including annual maintenance and single maintenance costs such as propellers), the increased fuel cost F2 caused by the reduction of thrust due to propeller structural damage, the transit port cost F3, and the possible loss F4 caused by returning to the maintenance port empty, as shown in the following formula.

[0063] F l =F1+F2+F3+F4

[0064] The calculation of the maintenance cost F1 is based on the following assumptions: the annual maintenance cost of container ships is assumed to be 1.095% of the ship cost. According to the assumptions in relevant literature, the annual maintenance rate of ice-resistant ships is about 10%-25% higher than that of ordinary ships of the same size, and the cost of ice-resistant ships is about 25% higher than that of ordinary ships of the same size, so it is assumed that the annual maintenance rate of ice-resistant ships is 1.606%.

[0065] The additional fuel cost F2 depends on the fuel consumption rate (f), fuel price (bp) and single voyage time (time). The fuel cost is defined as:

[0066] F2=f×time×b p

[0067] Assume the fuel price is 500USD / ton. According to the propeller law, the fuel consumption rate (f) can be calculated as follows:

[0068] f=SFOC×BHP

[0069]

[0070] Among them, SFOC stands for specific fuel consumption (unit: g / kW·h), with a fixed value of 185g / kW·h; BHP is the engine brake horsepower (unit: kW); m is the proportional factor, Vi is the speed of the container ship sailing in different sections. BHPmax is the maximum output power of the main engine; Vmax is the maximum ship speed.

[0071] Transshipment port charges F3 mainly include (a) port charges, (b) container loading and unloading charges, (c) port pilotage charges and (d) icebreaking charges at specific ports. The various charges are generally calculated based on the net tonnage or container volume of the ship and the relevant rate standards, as shown in the following formula:

[0072]

[0073] (b) Container handling charges = handling rate (unit: USD / TEU) × vessel container capacity (unit: TEU)

[0074] (c) Port pilotage fee = pilotage rate (unit: USD / ton) × net ton;

[0075] (d) Icebreaking fee for a specific port = Icebreaking rate (unit: USD / ton) × gross tonnage

[0076] Among them, the icebreaking rate is obtained by the Russia Northern Sea Route Administration.

[0077] The loss F4 caused by returning to the repair port empty is calculated based on the China Container Freight Index from 2017 to 2019 released by the Shanghai Shipping Exchange, assuming that the container freight rate is 900USD / TEU.

[0078] System data update module such as Figure 6 As shown in Figure 2, this module is mainly divided into accident data update and accident loss parameter update parts, such as Figure 7 and Figure 8 As shown. System users can discretize the 24 risk factors classified by this system according to the newly occurred ice entrapment and ice damage accident reports, and enter them into the corresponding box in the accident data update section. Then click the "Accident Data Update" button below to update and add to the software accident database. In view of the different losses after ice entrapment and ice damage accidents of different ship types, the accident loss parameter update module can modify the corresponding parameters according to the specific type of ship where the system user is located, so as to obtain a more accurate economic loss estimate.

[0079] Let’s take the example of a ship departing from a port on the East China Sea coast of China and traveling through the Northeast Passage to the Port of Rotterdam in the Netherlands.

[0080] Assume that the crew is negligent in looking out when sailing to a certain area, and it is known that the thickness of the sea ice in this area is 1.1m. In the "Current Risk Assessment" module, set the "Negligence in Looking Out" node to "True" and the thickness of the sea ice to 1.1m. Fig. 9 As shown in the figure, click Data Update to perform risk analysis and auxiliary decision-making in the current state. After Bayesian network calculation, the risk factors with increased probability of occurrence will be displayed in the blank space, and the corresponding navigation precautions and suggestions will be displayed in the blank space on the right. Fig.10 As shown in the figure, nodes such as "Insufficient Information", "Insufficient Danger Estimate", "Fatigue", and "Visibility" are displayed in the blank box of "Risk Factors" in the middle of the software due to the increased probability of occurrence. The display order is the set occurred nodes, two risk nodes, and other nodes. Click the node names in the middle risk factor box to display the corresponding suggestions on the right side of the software interface to assist the crew in making decisions. The figure shows the relevant suggestions given by the node software when the "poor ice conditions" situation occurs.

[0081] The loss calculation module is mainly based on a brief calculation of the economic losses after the ship is trapped in ice or damaged by ice. It is assumed that the sample ship has a load rate of 100% and the original return eastbound load rate is 50%. The ship encountered ice damage in the middle of the Velikytsky Strait, and the propeller was damaged, causing the speed to drop to 80% of the original speed at the same engine power. During the period, it stopped at the Port of Murmansk to inspect the damage and then continued to the Port of Rotterdam to unload, and then returned to the port on the East China Sea coast empty for repairs. System settings are as follows Fig.11 As shown in a, click the result calculation and the output result is as follows Fig.11 As shown in b, the system estimates the accident loss to be USD 5.68 million.

[0082] It can be seen that the risk assessment and decision-making system designed in the present invention can be actually applied to ships sailing in polar ice areas. It is simple, convenient and fast to operate, and can assess the risks of ice entrapment and ice damage that ships may encounter, assist in decision-making and calculate losses, provide effective support and navigation suggestions for crew members, and provide support for actual polar ship risk management.

[0083] The polar region ship risk analysis and decision-making system proposed in the present invention is introduced in detail above, and the principle and implementation mode of the present invention are explained. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A polar region ship risk analysis and decision-making system, characterized by: The system includes a user interaction layer, a data processing layer and a data storage layer; The user interaction layer is used to select the current risk node status, display reasoning results and auxiliary decision-making suggestions, and display economic loss results; The data processing layer performs parameter learning and data reasoning through a Bayesian network model; The data storage layer is used to store accident samples, recommended measures and parameters.

2. The system according to claim 1, characterized in that: The human-computer interface display content of the user interaction layer includes current situation risk assessment, loss calculation, system data update and system exit.

3. The system according to claim 2, characterized in that: The specific parameter transmission path of the data processing layer is as follows: the human-computer interface converts the ice area and ship accident data into the computer engine, and through Python software, the input computer data is converted into Python type, and then the Bayesian network model is constructed using the pgmpy library for analysis and calculation; The Bayesian network returns the inference data to the Python engine, which converts the data into the original type of data of the computer engine and transmits it back to the computer engine, displays the results on the human-computer interface, and realizes the functions of providing risk analysis and auxiliary decision-making.

4. The system according to claim 3, characterized in that: The system includes a current situation risk assessment module, a loss calculation module and a system data update module; The user interaction layer provides an interface for the three modules to interact with the crew, and the crew operates each module through this layer; The data processing layer provides support for the construction, analysis and calculation of the Bayesian network model of the current situation risk assessment module, and also provides data processing capabilities for the calculation of various expenses in the loss calculation module, while realizing data conversion and storage in the system data update module; The data storage layer provides data storage and reading services for the three modules, ensuring that the modules can obtain the required data.

5. The system according to claim 4, characterized in that: The current situation risk assessment module displays content including risk factor selection, Bayesian network reasoning results and recommended measures, and has risk assessment and decision-making support functions; The loss calculation module briefly calculates the economic losses of the ship after an ice-trapped or ice-damaged accident. The parameters include whether the ship is docked after the accident, whether it returns empty-handed, the section where the accident occurred, the remaining mileage of the section, and the thrust loss after the accident.

6. The system according to claim 5, characterized in that: The calculation of accident losses takes into account the maintenance cost F1, which includes annual maintenance and single maintenance costs such as propellers, increased fuel costs F2 due to thrust reduction caused by propeller structural damage, transit port costs F3, and possible losses F4 caused by returning to the maintenance port empty, as shown in the following formula: <h2 style=";text-align:left;direction:ltr">F<h2 style=";text-align:left;direction:ltr"> l <h2 style=";text-align:left;direction:ltr"> (F1+F2+F3+F4) The calculation of maintenance cost F1 is based on the annual maintenance rate of ice-resistant ships being 1.606%; The additional fuel cost F2 depends on the fuel consumption rate (f), fuel price (bp) and single voyage time (time). The fuel cost is defined as: <h2 style=";text-align:left;direction:ltr">F2 = f × time × b<h2 style=";text-align:left;direction:ltr"> p Assuming the fuel price is 500USD / ton; according to the propeller law, the fuel consumption rate (f) can be calculated as follows: f=SFOC×BHP Among them, SFOC stands for specific fuel consumption (unit: g / kW·h), with a fixed value of 185g / kW·h; BHP is the engine brake horsepower (unit: kW); m is the proportional factor, Vi is the speed of the container ship sailing in different sections, BHPmax is the maximum output power of the main engine; Vmax is the maximum ship speed; The transit port fee F3 mainly includes (a) port fees, (b) container loading and unloading fees, (c) port pilotage fees and (d) icebreaking fees at specific ports; each fee is generally calculated based on the net tonnage or container volume of the ship and the relevant rate standards, as shown in the following formula: (b) Container handling charges = handling rate (unit: USD / TEU) × vessel container capacity (unit: TEU) (c) Port pilotage fee = pilotage rate (unit: USD / ton) × net ton; (d) Icebreaking fee for a specific port = Icebreaking rate (unit: USD / ton) × gross tonnage Among them, the icebreaking rate is obtained from the Russian Northern Sea Route Administration; The loss F4 caused by returning to the repair port empty is calculated based on the freight index, assuming that the container freight rate is 900USD / TEU.

7. The system according to claim 6, characterized in that: The system data update module is divided into accident data update and accident loss parameter update parts. System users discretize according to the risk factors according to the newly occurred ice trap and ice damage accident reports, and input them into the corresponding box of the accident data update part, and then update and add to the software accident database; In view of the different losses caused by ice entrapment and ice damage accidents on different ship types, the accident loss parameter update module modifies the corresponding parameters according to the specific type of ship on which the system user is located to obtain a more accurate estimate of economic losses.

Images