CN116597693A - A monitoring system and method for inland waterway transportation - Google Patents

Abstract

The present disclosure relates to a inland navigation monitoring system and method, the system comprising: the acquisition module is used for acquiring multisource information of navigation of the target ship; the data processing module is in communication connection with the acquisition module and is used for receiving the multi-source information and obtaining a prediction result of the future navigation condition of the target ship according to the multi-source information; the pre-warning module is in communication connection with the data processing module and is used for judging whether the target ship needs to perform pre-warning or warning according to the obtained prediction result; the data transmission module is respectively in communication connection with the data processing module and the pre-alarm module and is used for constructing a wireless self-organizing communication network by taking each ship and/or shore as an interaction node. The method is applied to the system. The method has the advantages of high coverage and reliability, can accurately monitor, early warn and alarm the inland shipping ships, is favorable for reducing the accident occurrence probability of the inland shipping ships, reduces personnel and property loss, has low application cost, and is suitable for inland shipping scenes.

Description

A monitoring system and method for inland waterway transportation

technical field

The present disclosure relates to the technical field of shipping monitoring, in particular to an inland shipping monitoring system and method.

Background technique

The inland shipping industry occupies an important position in the development of my country's national economy. At present, inland shipping ships are basically equipped with AIS (Automatic Identification System, automatic identification system for ships), and at the same time are auxiliary equipped with ship positioning equipment, marine radar, ship-borne sensing instruments, etc., but currently Each system or equipment is applied separately, and it is not well integrated in the inland waterway shipping security system, and the current shipping monitoring system is mostly used on sea transport ships, which has the following defects:

First, the current shipping monitoring system mostly uses traditional wireless networks for communication, ignoring the natural conditions and construction cost constraints of inland waterways. It is difficult to effectively cover remote inland waterways and most navigation areas lacking base station construction, which affects the effectiveness of shipping monitoring systems. coverage and reliability;

Second, there is currently no reliable early warning and alarm system dedicated to inland waterway shipping scenarios for special navigation conditions of inland waterway shipping and common ship accidents, resulting in the inability to provide early warning and alarm to inland waterway shipping ships in a timely manner, resulting in loss of personnel and property.

To sum up, the existing maritime shipping monitoring system has not been well applied to the inland shipping system, and has the defects of low coverage and reliability, and ineffective early warning and alarm.

Contents of the invention

In order to solve the above-mentioned problems in the prior art, the purpose of the present disclosure is to provide a monitoring system and method for inland waterway transportation. The disclosure has high coverage and reliability, can accurately monitor, warn and alarm inland waterway ships, is conducive to reducing the accident probability of inland waterway ships, reduces personnel and property losses, and has low application cost, and is suitable for inland waterway shipping scene.

An inland waterway monitoring system described in the present disclosure includes:

A collection module, which is used to collect multi-source information of the navigation of the target ship, and the multi-source information includes environmental information, ship positioning information and ship status information;

A data processing module, which is connected in communication with the acquisition module, and is used to receive the multi-source information, and obtain a prediction result of the future navigation status of the target ship according to the multi-source information;

A pre-alarm module, which is connected in communication with the data processing module, is used to judge whether the target ship needs to perform an early warning or an alarm according to the obtained prediction result;

Data transmission module, it is connected with described data processing module, described pre-alarm module communication respectively, is used for building wireless ad hoc communication network with each ship and/or shore base as interactive node; Described pre-alarm module judges target When the ship needs to perform early warning or alarm, the early warning information or alarm information is transmitted to other ships and/or shore bases through the wireless self-organizing communication network.

Preferably, the collection module includes:

Shipborne sensor unit, which includes at least one or more of a ship attitude sensor, a wind speed sensor, a ship draft sensor, and a positioning module;

AIS service unit, which is used to obtain the ship name, symbol, ship position, ship speed and ship direction information of the target ship;

The marine radar unit is used to assist in obtaining the positioning information of the target ship.

Preferably, the data processing module obtains the prediction result of the future navigation status of the target ship according to the multi-source information, specifically:

Accident classification: Obtain the analysis of multiple shipping accident reports with different causes of accidents in the navigation channel of the target ship, and classify the analysis of the multiple shipping accident reports according to the type of accident as a training set;

Model training: use the obtained training set as the input data of the ISM-BN model to construct a prediction model for predicting the probability of various types of accidents on ships;

Result prediction: obtain the multi-source information of the target ship in real time, input the multi-source information of the target ship into the obtained prediction model, and obtain the probability of various types of accidents on the target ship, which is the prediction result of the future navigation status of the target ship.

Preferably, in the accident classification, accident types are classified into collision, self-submersion, grounding, contact or others.

Preferably, the model training is specifically:

Ship navigation parameters are set according to the cause of the accident, and the ship navigation parameters include ship navigation status, ship condition, ship age, ship size, ship type, cargo status, weather conditions, hydrological conditions, channel conditions and water conditions;

According to whether there is mutual influence between the navigation parameters of each ship, an adjacency matrix used to characterize the relationship between the navigation parameters of each ship is constructed, and the accessibility matrix is obtained according to the obtained adjacency matrix, and the classification of different ship navigation parameters is determined according to the obtained accessibility matrix Influencing factors ISM of navigation accidents of ships in the channel can be obtained;

Construct the fuzzy logic relationship about the ISM of each navigation accident influencing factor;

The obtained training set is used as input data to construct a topological network for characterizing the mapping relationship between the type of accident and the ISM of each navigation accident influencing factor, and the topological network is the prediction model.

Preferably, the result prediction is specifically:

The corresponding parameters in the multi-source information of the target ship are input into the prediction model to obtain the probability of various types of accidents occurring on the target ship.

Preferably, the pre-alarm module judges whether the target ship needs to carry out early warning or alarm according to the obtained prediction result, specifically:

When the occurrence probability of any type of accident is greater than 75%, or the accident weighted total probability When it is greater than 80%, it is judged that the target ship needs to carry out early warning;

When the occurrence probability of any type of accident is greater than 95%, or the accident weighted total probability When it is greater than 90%, it is judged that the target ship needs to give an alarm.

Preferably, the accident weighted total probability Calculate according to the following formula:

Among them, a=47% represents the weight of the probability of the collision accident of the target ship, and p _a represents the probability of the collision accident of the target ship;

b=18% represents the weight of the probability of self-sinking of the target ship, and p _b represents the probability of self-sinking of the target ship;

c=13% represents the weight of the probability of the grounding accident of the target ship, and p _c represents the probability of the grounding accident of the target ship;

d=12% represents the weight of the probability of a collision accident occurring on the target ship, and p _d represents the probability of a collision accident occurring on the target ship;

e=10% represents the weight of the probability of other accidents occurring to the target ship, and p _e represents the probability of other accidents occurring on the target ship.

Preferably, the wireless ad hoc communication network is a MANET network.

An inland shipping monitoring method of the present disclosure is characterized in that applying the above-mentioned inland shipping monitoring system includes the following steps:

Construct a wireless self-organizing communication network with each ship and/or shore base as an interactive node;

Collecting multi-source information on the navigation of the target ship, the multi-source information includes environmental information, ship positioning information and ship status information;

According to the multi-source information, the prediction result of the future navigation status of the target ship is obtained;

According to the obtained prediction results, it is judged whether the target ship needs to carry out early warning or alarm;

When it is judged that the target ship needs to perform early warning or alarm, the early warning information or alarm information is transmitted to other ships and/or shore bases through the wireless self-organizing communication network.

The advantages of the inland waterway monitoring system and method described in the present disclosure are:

1. This disclosure aims at the characteristics of small tonnage, slow transportation speed, low operating cost, and large number of inland waterway shipping ships. Using wireless self-organizing communication network technology, each sailing ship is used as an interactive node to establish a multi-node interconnection network. , can provide a large number of information transmission services for inland ships, and can timely transmit early warning information and alarm information of ships to nearby navigation ships and shore bases, realizing fast and efficient transmission of early warning information and alarm information, which can be quickly established and does not rely on It is suitable for fixed backbone networks, especially for remote inland natural waterways and most navigation areas lacking base station construction. It will effectively improve the coverage and reliability of the inland waterway system, and has the advantages of low application difficulty, low application cost and wide applicability. advantage;

2. This disclosure builds a prediction model for predicting the probability of various types of accidents on ships. The multi-source information of the target ship is obtained in real time through the acquisition module, and based on the multi-source information, the predicted probability of various types of accidents on the target ship can be obtained. Based on the obtained prediction Timely and accurate early warning and alarm for target ships is beneficial to reduce the accident probability of inland waterway ships and reduce the loss of personnel and property.

Description of drawings

Fig. 1 is a structural block diagram of a kind of inland navigation monitoring system described in the present embodiment;

Fig. 2 is a hierarchical relationship diagram of the ISM of the influencing factors of the inland ship navigation accident described in the present embodiment;

Fig. 3 is a schematic diagram of a topological network used to characterize the mapping relationship between accident types and navigation accident influencing factors ISM according to this embodiment.

Detailed ways

As shown in FIG. 1 , a monitoring system for inland waterway transportation described in the present disclosure includes:

The collection module is used to collect multi-source information of the target ship's navigation. The multi-source information includes environmental information, ship positioning information and ship status information. Specifically, the collection module includes:

The shipborne sensor unit includes a ship attitude sensor, a wind speed sensor, a ship draft sensor and a positioning module. The ship attitude sensor is used to sense the ship attitude, the wind speed sensor is used to sense the wind speed of the navigation environment, and the ship draft sensor is used to sense the ship's draft , the positioning module is used to obtain ship positioning information, and the ship-mounted sensor unit is mainly used to obtain ship navigation information and channel natural environment information that cannot be obtained by the AIS system, so as to improve the prediction accuracy of the subsequent structure prediction model.

The AIS service unit, specifically the existing AIS system, mainly includes radar, VHF communicator, GPS/Beidou positioning system, and is mainly used to collect the ship name, symbol, ship position, ship speed and ship direction information of the target ship;

The inland river marine radar unit is mainly used in inland waterway shipping vessels equipped with inland river marine radar, and mainly plays the role of assisting positioning to obtain accurate ship specific azimuths.

The data processing module is connected with the acquisition module by communication, and is used to receive the multi-source information collected by the acquisition module, gather the multi-source information, and use relevant algorithms to construct a mathematical model of the ship's navigation status, and use the ship's distress experience coefficient, combined with the target The accident data of the waterway is used to judge the current navigation status, and then further predict the probability of various types of accidents to obtain the prediction results of the target ship's future navigation status.

The accident prediction model for inland ships is mainly constructed on the basis of the ISM-BN mathematical model, as follows:

Accident Classification: Collect target ship navigation channels from the official website of the China Maritime Safety Administration, such as the Pearl River Channel, for the analysis of multiple shipping accident reports with different causes, and classify the analysis of multiple shipping accident reports by accident type as a training set, exemplary classification as follows:

The types of accidents are divided into a collision, b self-sinking, c grounding, d touch or e other, among which other accidents include explosion, capsizing and other rare shipping accidents.

Model training: use the obtained training set as the input data of the ISM-BN model to construct a prediction model for predicting the probability of various types of accidents on ships; specifically:

Ship navigation parameters are set according to the cause of the accident, and the ship navigation parameters include ship navigation status x1, ship condition x2, ship age x3, ship size x4, ship type x5, cargo status x6, weather conditions x7, hydrological conditions x8, channel conditions x9 and water conditions x10;

Among them, different parameter acquisition methods are: ship condition x2, ship age x3, ship size x4, ship type x5 are static data, which will not change during the voyage, and can be obtained through shipping companies or AIS;

Cargo status x6 is a variable value, which is set and input by the crew before transportation, and can be adjusted during the shipping process. Weather conditions x7, hydrological conditions x8, channel conditions x9 and water conditions x10 are acquired and input through on-board sensors and AIS systems.

Ship navigation status x1 is a number of dynamic data when the ship is sailing, including ship attitude, draft, main engine speed, etc., which can be obtained by corresponding sensors or by reading the ship control system.

According to whether there is mutual influence between the navigation parameters of each ship, an adjacency matrix used to characterize the relationship between the navigation parameters of each ship is constructed. If there is an influence between different parameters, it is set to 1, and if there is no influence, it is set to 0. Then, according to the adjacency matrix, the Boolean The algebraic rule operation obtains the reachable matrix as shown in Table 1:

Table 1. Reachability matrix

According to the accessibility matrix to determine the grading between the navigation parameters of different ships, the hierarchical relationship of ISM on the factors affecting navigation accidents of ships in this channel can be obtained as shown in Figure 2;

Based on the above-mentioned reachable matrix, the fuzzy logic relationship of the ISM of each navigation accident influencing factor is constructed as shown in Table 2:

Table 2. Parameter fuzzy logic relationship

After obtaining the hierarchical relationship of the ISM of the navigation accident influencing factors of the channel ship, the topological network used to characterize the mapping relationship between the accident type and each navigation accident influencing factor ISM is constructed by inputting the obtained training set. The topological network is shown in Figure 3. Including 11 nodes, this topological network is the prediction model.

Result prediction: obtain the multi-source information of the target ship in real time, input the multi-source information of the target ship into the obtained prediction model, and obtain the probability of various types of accidents on the target ship, which is the prediction result of the future navigation status of the target ship.

The result predictions are specifically:

The corresponding parameters in the multi-source information of the target ship are input into the prediction model to obtain the probability of various types of accidents occurring on the target ship.

Specifically, the corresponding parameters in the multi-source information are input into the obtained prediction model, and each node is made to calculate the posterior probability by counting learning method.

A pre-alarm module, which is connected in communication with the data processing module, is used to judge whether the target ship needs to carry out an early warning or an alarm according to the obtained prediction result; specifically:

When the occurrence probability of any type of accident is greater than 75%, or the accident weighted total probability When it is greater than 80%, it is judged that the target ship needs to carry out early warning;

When the occurrence probability of any type of accident is greater than 95%, or the accident weighted total probability When it is greater than 90%, it is judged that the target ship needs to issue an alarm;

More specifically, in order to improve the prediction accuracy in the specific scene of inland waterways, weighting calculations are performed on each accident type according to the common accident types of inland waterways, as follows:

Among them, a=47% represents the weight of the probability of the collision accident of the target ship, and p _a represents the probability of the collision accident of the target ship;

b=18% represents the weight of the probability of self-sinking of the target ship, and p _b represents the probability of self-sinking of the target ship;

c=13% represents the weight of the probability of the grounding accident of the target ship, and p _c represents the probability of the grounding accident of the target ship;

d=12% represents the weight of the probability of a collision accident occurring on the target ship, and p _d represents the probability of a collision accident occurring on the target ship;

e=10% represents the weight of the probability of other accidents occurring to the target ship, and p _e represents the probability of other accidents occurring on the target ship.

The structure of the above prediction model remains unchanged in the subsequent application process, and the future navigation status of different target ships is predicted by modifying the input information of different ships.

The data transmission module is connected with the data processing module and the pre-alarm module respectively, and is used to construct a wireless self-organizing communication network with each ship and/or shore base as an interactive node; specifically, the wireless self-organizing communication network is a MANET network , using each ship or shore base in the shipping system as an interactive node to realize the transmission of ship early warning and alarm information.

A pre-alarm module, which is connected in communication with the data processing module, is used to judge whether the target ship needs to perform an early warning or an alarm according to the obtained prediction result;

The pre-alarm module is a system that can occur throughout the whole process. Generally speaking, decisions are made before the data transmission module and run through all subsequent rescue links. However, in case of special circumstances, all links can be skipped and the subjective role can be played directly in front of the data transmission module. It can be used flexibly, and it stores solidified international distress signal information and transmission system activation information inside. Once non-programmed activation, it will transmit the worst distress data of the ship to other ships or shore-based rescue organizations.

The working process of the inland waterway monitoring system described in this embodiment is:

For normal shipping tasks of inland ships, the acquisition module acquires ship navigation information in real time and transmits it to the data processing module at time intervals. When the conditions for sending early warning information or alarm information are met, the data transmission module sends early warning information or alarm information to the shore-based rescue system and nearby ships equipped with the system through the wireless self-organizing network, and the rescue process ends.

If the analysis result does not meet the conditions for issuing early warning information or alarm information, the analysis result is stored in the on-board server or other mobile memory, and the information is used to predict the possibility of changes in ship parameters in different time periods in the future.

In other preferred embodiments, the data processing module can also combine the collected multi-source information to display the two-dimensional plane navigation status at sea by integrating into a three-dimensional structure to make the analysis model more intuitive and accurate.

Aiming at the characteristics of small tonnage, slow transportation speed, low operating cost and large number of inland waterway shipping ships, this disclosure uses wireless self-organizing communication network technology to use each sailing ship as an interactive node to establish a multi-node interconnection network, which can Provide a large number of information transmission services for inland ships, and can timely transmit early warning information and alarm information of ships to nearby navigation ships and shore bases, realize fast and efficient transmission of early warning information and alarm information, can be quickly established, and do not rely on fixed The backbone network, especially suitable for remote inland natural waterways and most navigation areas lacking base station construction, will effectively improve the coverage and reliability of the inland waterway system, and has the advantages of low application difficulty, low application cost, and wide applicability;

This disclosure builds a prediction model for predicting the probability of various types of accidents on ships. The multi-source information of the target ship is obtained in real time through the acquisition module, and based on the multi-source information, the predicted probability of various types of accidents on the target ship can be obtained. The timely and accurate early warning and alarm of the target ship is conducive to reducing the accident probability of inland waterway ships and reducing the loss of personnel and property.

This embodiment also provides a method for monitoring inland waterway transportation, using the above-mentioned river navigation monitoring system, including the following steps:

Construct a wireless self-organizing communication network with each ship and/or shore base as an interactive node;

Collecting multi-source information on the navigation of the target ship, the multi-source information includes environmental information, ship positioning information and ship status information;

According to the multi-source information, the prediction result of the future navigation status of the target ship is obtained;

According to the obtained prediction results, it is judged whether the target ship needs to carry out early warning or alarm;

When it is judged that the target ship needs to perform early warning or alarm, the early warning information or alarm information is transmitted to other ships and/or shore bases through the wireless self-organizing communication network.

The method of this embodiment belongs to the same inventive concept as the above-mentioned monitoring system, which can be understood with reference to the above description, and will not be repeated here.

In the description of the present disclosure, it should be understood that orientation words such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" etc. indicate the orientation or position The relationship is generally based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present disclosure and simplifying the description. In the absence of a contrary statement, these orientation words do not indicate and imply that the referred device or element must have A particular orientation, or construction and operation in a particular orientation, should therefore not be construed as limiting the scope of the present disclosure.

For those skilled in the art, various other corresponding changes and deformations can be made according to the above-described technical solutions and ideas, and all these changes and deformations should fall within the protection scope of the claims of the present disclosure.

Claims (10)

1. A monitoring system for inland waterway transportation, characterized in that it comprises: A collection module, which is used to collect multi-source information of the navigation of the target ship, and the multi-source information includes environmental information, ship positioning information and ship status information; A data processing module, which is connected in communication with the acquisition module, and is used to receive the multi-source information, and obtain a prediction result of the future navigation status of the target ship according to the multi-source information; A pre-alarm module, which is connected in communication with the data processing module, is used to judge whether the target ship needs to perform an early warning or an alarm according to the obtained prediction result; Data transmission module, it is connected with described data processing module, described pre-alarm module communication respectively, is used for building wireless ad hoc communication network with each ship and/or shore base as interactive node; Described pre-alarm module judges target When the ship needs to perform early warning or alarm, the early warning information or alarm information is transmitted to other ships and/or shore bases through the wireless self-organizing communication network. 2. according to the described inland waterway transportation monitoring system of claim 1, it is characterized in that, described acquisition module comprises: Shipborne sensor unit, which includes at least one or more of a ship attitude sensor, a wind speed sensor, a ship draft sensor, and a positioning module; AIS service unit, which is used to obtain the ship name, symbol, ship position, ship speed and ship direction information of the target ship; The marine radar unit is used to assist in obtaining the positioning information of the target ship. 3. according to the described inland shipping monitoring system of claim 1, it is characterized in that, according to described multi-source information, described data processing module obtains the prediction result of target ship's future voyage condition specifically as follows: Accident classification: Obtain the analysis of multiple shipping accident reports with different causes of accidents in the navigation channel of the target ship, and classify the analysis of the multiple shipping accident reports according to the type of accident as a training set; Model training: use the obtained training set as the input data of the ISM-BN model to construct a prediction model for predicting the probability of various types of accidents on ships; Result prediction: obtain the multi-source information of the target ship in real time, input the multi-source information of the target ship into the obtained prediction model, and obtain the probability of various types of accidents on the target ship, which is the prediction result of the future navigation status of the target ship. 4. The inland shipping monitoring system according to claim 3, wherein in the accident classification, accident types are classified into collision, self-sinking, grounding, contact or others. 5. according to the described inland shipping monitoring system of claim 4, it is characterized in that, described model training is specifically: Ship navigation parameters are set according to the cause of the accident, and the ship navigation parameters include ship navigation status, ship condition, ship age, ship size, ship type, cargo status, weather conditions, hydrological conditions, channel conditions and water conditions; According to whether there is mutual influence between the navigation parameters of each ship, an adjacency matrix used to characterize the relationship between the navigation parameters of each ship is constructed, and the accessibility matrix is obtained according to the obtained adjacency matrix, and the classification of different ship navigation parameters is determined according to the obtained accessibility matrix Influencing factors ISM of navigation accidents of ships in the channel can be obtained; Construct the fuzzy logic relationship about the ISM of each navigation accident influencing factor; The obtained training set is used as input data to construct a topological network for characterizing the mapping relationship between the type of accident and the ISM of each navigation accident influencing factor, and the topological network is the prediction model. 6. according to the described inland shipping monitoring system of claim 5, it is characterized in that, described result prediction is specifically: The corresponding parameters in the multi-source information of the target ship are input into the prediction model to obtain the probability of various types of accidents occurring on the target ship. 7. According to the inland shipping monitoring system described in claim 6, it is characterized in that, the said pre-alarm module judges whether the target ship needs to carry out early warning or alarm according to the obtained prediction result, specifically: When the occurrence probability of any type of accident is greater than 75%, or the accident weighted total probability When it is greater than 80%, it is judged that the target ship needs to carry out early warning; When the occurrence probability of any type of accident is greater than 95%, or the accident weighted total probability When it is greater than 90%, it is judged that the target ship needs to give an alarm. 8. The inland shipping monitoring system according to claim 7, wherein the weighted total probability of the accident Calculate according to the following formula: Among them, a=47% represents the weight of the probability of the collision accident of the target ship, and p _a represents the probability of the collision accident of the target ship; b=18% represents the weight of the probability of self-sinking of the target ship, and p _b represents the probability of self-sinking of the target ship; c=13% represents the weight of the probability of the grounding accident of the target ship, and p _c represents the probability of the grounding accident of the target ship; d=12% represents the weight of the probability of a collision accident occurring on the target ship, and p _d represents the probability of a collision accident occurring on the target ship; e=10% represents the weight of the probability of other accidents occurring to the target ship, and p _e represents the probability of other accidents occurring on the target ship. 9. The inland waterway transportation monitoring system according to claim 1, characterized in that, the wireless ad hoc communication network is a MANET network. 10. A method for monitoring inland waterway transportation, characterized in that, applying the inland waterway transportation monitoring system according to any one of claims 1-9, comprising the following steps: Construct a wireless self-organizing communication network with each ship and/or shore base as an interactive node; Collecting multi-source information on the navigation of the target ship, the multi-source information includes environmental information, ship positioning information and ship status information; According to the multi-source information, the prediction result of the future navigation status of the target ship is obtained; According to the obtained prediction results, it is judged whether the target ship needs to carry out early warning or alarm; When it is judged that the target ship needs to perform early warning or alarm, the early warning information or alarm information is transmitted to other ships and/or shore bases through the wireless self-organizing communication network.