Intelligent auxiliary decision-making method and system for ship state

Abstract

The invention discloses an intelligent auxiliary decision-making method and system for a ship state, and relates to the field of ship operation auxiliary systems. According to the intelligent auxiliary decision-making method and system for the ship state, the risk information of various ships is acquired, the risk assessment function is established according to the risk information, and when the ship state is judged, various internal and external risk information of the current ship is substituted into the risk assessment function for calculation; threshold value setting and risk level number setting are carried out on various information items in advance, when each item of risk information is calculated, according to a threshold value principle, when any item of risk information reaches the maximum threshold value, a negative result is output, and under the condition that no risk item reaches the threshold value, an accumulated risk coefficient total value R < total > is obtained; and then ship state evaluation is carried out according to the total risk coefficient value, so that an intelligent auxiliary decision is made for ship navigation decision, and decision errors caused by manual judgment only in a traditional decision process are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of ship operation auxiliary systems, and in particular to an intelligent auxiliary decision-making method and system for ship status. Background Art

[0002] During the voyage, a ship normally departs from the initial port, then sails along the designated route and arrives at the designated port within the target time range, thus completing the entire shipping journey.

[0003] However, in the actual route, it is affected by various internal and external factors. Internal factors include the ship's own personnel situation, equipment failure and energy reserves, while external factors include weather, hydrology, ports and route restrictions. Both of the above factors will affect the actual navigation of the ship. Therefore, it is necessary to analyze the current internal and external status of the ship and make correct decisions based on the analysis results. The decision-making direction includes but is not limited to: changing the navigation route, adjusting the speed, changing the port of call and returning, etc.

[0004] However, in the actual navigation process, the decision-making process is usually made by the captain, who obtains the current internal condition information and external environment information of the ship and then makes manual analysis and judgment. However, personal judgment has certain errors and cannot make accurate and reasonable judgments, which will make the energy consumption, navigation time and navigation safety of the ship's actual navigation unable to be optimized. For this reason, an intelligent auxiliary decision-making method and system for ship status is provided. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent auxiliary decision-making method and system for the ship status, which solves the problem that in the actual navigation process, the decision-making process is usually made by the captain, by obtaining the current internal condition information and external environment information of the ship, and then performing manual analysis and judgment. However, personal judgment has a certain degree of error and cannot make accurate and reasonable judgments, which will make it impossible to optimize the energy consumption, navigation time and navigation safety of the actual navigation of the ship.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent auxiliary decision-making method for ship status, comprising the following steps;

[0007] Step 1: Establish a ship intelligent decision-making support system;

[0008] Step 2: Obtain risk information of various types of ships through the ship intelligent decision-making support system;

[0009] Step 3: Establish a risk assessment function for ship risk information, and set thresholds and risk levels for various information items;

[0010] Step 4: Output the ship status analysis results through the risk assessment function;

[0011] In the risk assessment process in step 4, the risk type item information is obtained, and then the threshold value is compared for the risk item. If the threshold value is reached, it ends directly and the result is output. If the threshold value is not reached, the risk item is assigned a value according to the risk coefficient, and then the next risk type item data is obtained. All risk type item assessments are completed in sequence, and finally the risk coefficient value is output to assist in decision-making on the ship status.

[0012] Preferably, in step 2, the types of risk information include:

[0013] External information, including meteorological information, hydrological information, route information and port information;

[0014] Internal information, including hull information, loading information, equipment information and energy information.

[0015] Preferably, the meteorological information includes wind information, wave information and sea fog information; the hydrological information includes water temperature information and tidal current information; the route information includes waterway number information and ship information in the waterway; the port information is the number of ports passed by each waterway and port operation information.

[0016] Preferably, the hull information includes the age, type, load, draft and maintenance information of the vessel; the loading information is the quantity, type and agreed arrival date of the cargo currently loaded on the ship; the equipment information is the operating status and energy consumption information of various equipment in the ship; the energy information is the fossil energy, electric energy, fresh water energy and food energy reserve information of the ship.

[0017] Preferably, the risk assessment function is:

[0018] R=S1*A1+S2*A2+S3*A3…+Sn*An

[0019] Where R is the total value of the risk factor, S is the corresponding risk item level number, A is the corresponding risk weight coefficient of the risk item, and the level number threshold of a single risk item is a termination signal.

[0020] Preferably, when the total value R of the risk coefficient is actually calculated, the level number of the risk item is first identified and judged according to the set division. If the level number reaches the risk threshold, the calculation can be terminated according to the single risk item and output as the maximum risk value. If the level number does not reach the risk threshold, the risk item is assigned a value by multiplying the level number with the risk weight coefficient to obtain the risk value R1 of the risk item, and then the risk value calculation of the next risk type item is performed to obtain Rn, and it is added and accumulated with the previous risk item value. Finally, when no risk item reaches the threshold throughout the process, the accumulated total value of the risk coefficient Rtotal is obtained, and then the ship status is evaluated based on the total value of the risk coefficient.

[0021] Preferably, a ship intelligent auxiliary decision-making system includes a monitoring module, a communication module, a data module, an evaluation model, an interaction module and a storage module.

[0022] Preferably, the monitoring module is controllably connected to the sensor equipment and monitoring equipment used to monitor various equipment on the ship, so as to obtain the operation information and status information of various equipment on the ship; the communication module is used to connect to the external Internet to collect external information on the ship's operation.

[0023] Preferably, the data module includes data collection, data processing and data storage, and obtains internal and external information of the ship through the monitoring module and the communication module. The data is then processed and handed over to the evaluation model for data evaluation, and finally the data is stored through the storage module, and the information is output and input through the interactive module.

[0024] Preferably, the basic functional architecture of the evaluation model includes data cleaning, feature extraction, data output and model training. The data provided by the data module is cleaned, abnormal data is eliminated, and then the data features are extracted and applied to the evaluation model for intelligent analysis, and finally the data is output. At the same time, a neural network model is used to take historical data on normal operation and fault status of ships as a training set to train a model that can distinguish between normal and abnormal states of ships. When new real-time data is input, the model can output the probability of the ship being normal or in a certain type of fault, thereby continuously improving the accuracy of auxiliary decision-making.

[0025] The present invention discloses an intelligent auxiliary decision-making method and system for ship status, which has the following beneficial effects:

[0026] 1. The intelligent auxiliary decision-making method for the ship status obtains the risk information of various ships and establishes a risk assessment function based on the various risk information. When judging the ship status, the various internal and external risk information of the current ship is substituted into the risk assessment function for calculation. By setting thresholds and risk levels for various information items in advance, when calculating each risk information, according to the threshold principle, when any risk information reaches the maximum threshold, the veto result is output. When no risk item reaches the threshold, the total value R of the accumulated risk coefficient is obtained, and then the ship status is evaluated according to the total value of the risk coefficient, so as to make intelligent auxiliary decisions for the navigation decision of the ship.

[0027] 2. The intelligent auxiliary decision-making system for the ship status includes a monitoring module, a communication module, a data module, an evaluation model, an interaction module and a storage module. In actual application, the monitoring module is used to obtain the operation and maintenance information of various equipment on the ship, and the communication module is used to obtain various weather, hydrological, port and route information within the operating range of the ship. Then, the data module is used to collect, process and store various types of information, and the data information is handed over to the evaluation model. The evaluation model cleans, extracts features and intelligently analyzes the data. Finally, based on the risk assessment function, the decision system makes intelligent judgments to assist manual decision-making and reduce decision-making errors caused by relying solely on manual judgment in the traditional decision-making process.

[0028] 3. The intelligent auxiliary decision-making system for the ship status uses the model training architecture of the assessment model and the neural network model to take the historical ship normal operation and fault status data as the training set for long-term data training, so that the assessment model can improve the assessment accuracy as the use time increases. At the same time, by continuously comparing and analyzing the training feedback with the actual decision results, the threshold setting, level division and risk weight coefficient of various risk item information in the risk assessment function are continuously adjusted, so that the system can further improve the assessment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 This is a flow chart of the structural intelligent decision-making assistance method of the present invention;

[0031] Figure 2 A schematic diagram of the risk information types of the present invention is shown;

[0032] Figure 3 is a risk assessment flow chart of the present invention;

[0033] Figure 4 This is a functional architecture diagram of the intelligent decision-making support system of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are 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.

[0035] The embodiments of the present application provide an intelligent auxiliary decision-making method and system for the status of a ship, thereby solving the problem that in the actual navigation process, the decision-making process is usually made by the captain, who obtains the current internal condition information and external environment information of the ship and then performs manual analysis and judgment. However, personal judgment has certain errors and cannot make accurate and reasonable judgments, which will result in the energy consumption, navigation time and navigation safety of the actual navigation of the ship not being optimized.

[0036] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0037] The embodiment of the present invention discloses an intelligent auxiliary decision-making method and system for ship status.

[0038] Embodiment 1

[0039] According to the attached Figure 1-4 As shown, an intelligent auxiliary decision-making method for ship status includes the following steps:

[0040] Step 1: Establish a ship intelligent decision-making support system;

[0041] Step 2: Obtain risk information of various types of ships through the ship intelligent decision-making support system;

[0042] Step 3: Establish a risk assessment function for ship risk information, and set thresholds and risk levels for various information items;

[0043] Step 4: Output the ship status analysis results through the risk assessment function;

[0044] In the risk assessment process in step 4, the risk type item information is obtained, and then the threshold value is compared for the risk item. If the threshold value is reached, the process ends directly and the result is output. If the threshold value is not reached, the risk item is assigned a value according to the risk coefficient, and then the next risk type item data is obtained. All risk type item assessments are completed in sequence, and finally the risk coefficient value is output to assist in decision-making on the ship status.

[0045] Preferably, in step 2, the types of risk information include:

[0046] External information, including meteorological information, hydrological information, route information and port information;

[0047] Internal information: internal information includes hull information, loading information, equipment information and energy information.

[0048] Preferably, the meteorological information includes wind information, wave information and sea fog information; the hydrological information includes water temperature information and tidal current information; the route information includes the number of waterways and information on ships in the waterways; and the port information includes the number of ports passed by each waterway and port operation information.

[0049] Preferably, the hull information includes the age, type, load, draft and maintenance information of the vessel; the loading information is the quantity, type and agreed arrival date of the cargo currently loaded on the ship; the equipment information is the operating status and energy consumption information of various equipment in the ship; the energy information is the fossil energy, electric energy, fresh water energy and food energy reserve information of the ship.

[0050] Preferably, the risk assessment function is:

[0051] R=S1*A1+S2*A2+S3*A3…+Sn*An

[0052] Where R is the total value of the risk factor, S is the corresponding risk item level number, A is the corresponding risk weight coefficient of the risk item, and the level number threshold of a single risk item is a termination signal.

[0053] Preferably, when the total value of the risk coefficient R is actually calculated, the level number of the risk item is first identified and judged according to the set division. If the level number reaches the risk threshold, the calculation can be terminated according to the single risk item and output as the maximum risk value. If the level number does not reach the risk threshold, the risk item is assigned a value by multiplying the level number with the risk weight coefficient to obtain the risk value R1 of the risk item, and then the risk value calculation of the next risk type item is performed to obtain Rn, and it is added and accumulated with the previous risk item value. Finally, when no risk item reaches the threshold throughout the process, the accumulated total value of the risk coefficient Rtotal is obtained, and then the ship status is evaluated based on the total value of the risk coefficient.

[0054] Working principle: This intelligent decision-making assistance method obtains risk information of various types of ships and establishes a risk assessment function based on the risk information. When judging the ship's status, the various internal and external risk information of the current ship is substituted into the risk assessment function for calculation. By setting thresholds and risk levels for various information items in advance, when calculating each risk information, according to the threshold principle, when any risk information reaches the maximum threshold, the veto result is output. When no risk item reaches the threshold, the total value R of the accumulated risk coefficient is obtained, and then the ship's status is evaluated based on the total value of the risk coefficient, so as to make intelligent auxiliary decisions for the ship's navigation decisions.

[0055] Embodiment 2

[0056] See attached Figure 1-4 ,A ship intelligent auxiliary decision system includes a monitoring module, a communication module, a data module, an evaluation model, an interaction module and a storage module.

[0057] Preferably, the monitoring module is controlled and connected with the sensor equipment and monitoring equipment used for monitoring various equipment on the ship, so as to obtain the operation information and status information of various equipment on the ship; the communication module is used to connect with the external Internet to collect external information on the ship's operation.

[0058] Preferably, the data module includes data collection, data processing and data storage, and obtains internal and external information of the ship through the monitoring module and the communication module. The data is then processed and handed over to the evaluation model for data evaluation, and finally the data is stored through the storage module, and the information is output and input through the interactive module.

[0059] Preferably, the basic functional architecture of the evaluation model includes data cleaning, feature extraction, data output and model training. The data provided by the data module is cleaned, abnormal data is eliminated, and then the data features are extracted and applied to the evaluation model for intelligent analysis, and finally the data is output. At the same time, a neural network model is used to take historical ship normal operation and fault status data as a training set to train a model that can distinguish between normal and abnormal states of the ship. When new real-time data is input, the model can output the probability of the ship being normal or in a certain type of fault, thereby continuously improving the accuracy of auxiliary decision-making.

[0060] In this embodiment, an intelligent auxiliary decision-making system for ship status analysis is specifically proposed. The system mainly includes a monitoring module, a communication module, a data module, an evaluation model, an interaction module and a storage module. In actual application, the monitoring module is used to obtain operation and maintenance information of various equipment on the ship, and the communication module is used to obtain various weather, hydrological, port and route information within the ship's operating range. Then, the data module is used to collect, process and store various types of information, and the data information is handed over to the evaluation model. The evaluation model cleans, extracts features and intelligently analyzes the data. Finally, based on the risk assessment function, the decision system makes intelligent judgments and gives analysis results.

[0061] At the same time, the system uses the model training architecture of the assessment model. By using the neural network model, the historical ship normal operation and fault status data are used as training sets for long-term data training, so that the assessment model can improve the assessment accuracy as the usage time increases. At the same time, by continuously comparing and analyzing the training feedback with the actual decision results, the threshold setting, level division and risk weight coefficient of various risk item information in the risk assessment function are continuously adjusted, so that the system can further improve the assessment accuracy.

[0062] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent auxiliary decision-making method for ship status, characterized in that: The steps include: Step 1: Establish a ship intelligent decision-making support system; Step 2: Obtain risk information of various types of ships through the ship intelligent decision-making support system; Step 3: Establish a risk assessment function for ship risk information, and set thresholds and risk levels for various information items; Step 4: Output the ship status analysis results through the risk assessment function; In the risk assessment process in step 4, the risk type item information is obtained, and then the threshold value is compared for the risk item. If the threshold value is reached, it ends directly and the result is output. If the threshold value is not reached, the risk item is assigned a value according to the risk coefficient, and then the next risk type item data is obtained. All risk type item assessments are completed in sequence, and finally the risk coefficient value is output to assist in decision-making on the ship status.

2. The intelligent auxiliary decision-making method for ship status according to claim 1 is characterized in that: In the step 2, the types of risk information include: External information, including meteorological information, hydrological information, route information and port information; Internal information, including hull information, loading information, equipment information and energy information.

3. The intelligent auxiliary decision-making method for ship status according to claim 2 is characterized in that: The meteorological information includes wind information, wave information and sea fog information; the hydrological information includes water temperature information and tidal current information; the route information includes the number of waterways and information on ships in the waterways; the port information is the number of ports passed by each waterway and port operation information.

4. The intelligent auxiliary decision-making method for ship status according to claim 2 is characterized in that: The hull information includes the age, type, load, draft and maintenance information of the vessel; the loading information is the quantity, type and agreed arrival date of the cargo currently loaded on the ship; the equipment information is the operating status and energy consumption information of various equipment in the ship; the energy information is the fossil energy, electric energy, fresh water energy and food energy reserve information of the ship.

5. The intelligent auxiliary decision-making method for ship status according to claim 1 is characterized in that: The risk assessment function is: R=S1*A1+S2*A2+S3*A3…+Sn*An Where R is the total value of the risk factor, S is the corresponding risk item level number, A is the corresponding risk weight coefficient of the risk item, and the level number threshold of a single risk item is a termination signal.

6. The intelligent auxiliary decision-making method for ship status according to claim 5, characterized in that: When the total value R of the risk coefficient is actually calculated, the level number of the risk item is first identified and judged according to the set division. If the level number reaches the risk threshold, the calculation can be terminated according to the single risk item and output as the maximum risk value. If the level number does not reach the risk threshold, the risk item is assigned a value by multiplying the level number with the risk weight coefficient to obtain the risk value R1 of the risk item. Then the risk value calculation of the next risk type item is performed to obtain Rn, and it is added and accumulated with the previous risk item value. Finally, when no risk item reaches the threshold throughout the process, the accumulated total value of the risk coefficient Rtotal is obtained, and then the ship status is evaluated based on the total value of the risk coefficient.

7. A ship intelligent auxiliary decision system, based on the ship intelligent auxiliary decision method according to any one of claims 1 to 6, characterized in that: It includes monitoring module, communication module, data module, evaluation model, interaction module and storage module.

8. The intelligent auxiliary decision-making system for ship status according to claim 7, characterized in that: The monitoring module is controlled and connected with the sensor equipment and monitoring equipment used for monitoring various equipment on the ship, and is used to obtain the operation information and status information of various equipment on the ship; the communication module is used to connect to the external Internet to collect external information on the ship's operation.

9. The intelligent auxiliary decision-making system for ship status according to claim 7, characterized in that: The data module includes data collection, data processing and data storage. The internal and external information of the ship is obtained through the monitoring module and the communication module. The data is then processed and handed over to the evaluation model for data evaluation. Finally, the data is stored through the storage module, and the information is output and input through the interactive module.

10. The intelligent auxiliary decision-making system for ship status according to claim 7, characterized in that: The basic functional architecture of the evaluation model includes data cleaning, feature extraction, data output and model training. The data provided by the data module is cleaned, abnormal data is eliminated, and then the data features are extracted and applied to the evaluation model for intelligent analysis, and finally the data is output. At the same time, a neural network model is used to take the historical ship normal operation and fault status data as a training set to train a model that can distinguish between normal and abnormal states of the ship. When new real-time data is input, the model can output the probability of the ship being normal or in a certain fault type, thereby continuously improving the accuracy of auxiliary decision-making.

Images