CN115659263A - Ship control behavior risk assessment system and assessment method based on big data - Google Patents
Ship control behavior risk assessment system and assessment method based on big data Download PDFInfo
- Publication number
- CN115659263A CN115659263A CN202211260297.6A CN202211260297A CN115659263A CN 115659263 A CN115659263 A CN 115659263A CN 202211260297 A CN202211260297 A CN 202211260297A CN 115659263 A CN115659263 A CN 115659263A
- Authority
- CN
- China
- Prior art keywords
- ship
- data
- navigation
- module
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention discloses a ship control behavior risk assessment system and method based on big data, which are used for assessing ship control behaviors; based on the Internet of things and big data technology, ship azimuth data and engine room monitoring data of the whole process of ship starting, sailing and stopping are collected, a ship control rule knowledge base is fused by using a machine learning algorithm to form a ship control behavior standard model base, the ship control behavior standard evaluation result and the evaluation report can be automatically and continuously output, information support is provided for monitoring and early warning of ship control behaviors, and the ship control behavior model base has comprehensiveness, economy and timeliness, and the timeliness and the accuracy of ship management are improved.
Description
Technical Field
The invention relates to a ship control behavior risk assessment system and method based on big data, belongs to the technical field of ship navigation safety, and is used for assessing ship control behaviors.
Background
The ship control behaviors are very important for safe navigation of the ship, and some irregular control behaviors exist in actual navigation, so that potential safety hazards exist. The ship control behaviors refer to various control behaviors of a ship driver on the ship in the driving process, and the control behaviors comprise starting, stopping, forward and backward switching and the like. In the actual navigation process, some irregular behaviors often exist, and the irregular ship control behaviors can damage ship equipment and cause potential safety hazards. For example, if the water temperature does not reach a preset value during the starting process, the vehicle starts to drive, the lubrication condition of the equipment is insufficient, the abrasion of parts of the main machine and the auxiliary machine is possibly aggravated, the maintenance cost of the ship is slightly increased, the equipment such as the main machine and the auxiliary machine is seriously failed, the navigation safety of the ship and the safety of personnel on the ship are influenced, and the ship accident is caused. Therefore, whether the ship control behavior is standard or not is very critical to safe navigation of the ship. And the important means for ensuring the ship control behavior specification is to carry out normative supervision on the ship control behavior specification.
At present, the supervision means of the normative control behaviors of ships is single, the automation and datamation degrees are not enough, and the comprehensiveness and timeliness are lacked. The traditional supervision mode is to check a navigation log and a turbine log, and carry out remote supervision on a conditional ship through video monitoring equipment or check and judge whether the ship control behavior meets the standard through manual inspection. However, the navigation time of the ship is often very long, the manual checking workload is large, the efficiency is low, the accuracy is not high, the influence of subjective judgment is large, and the video cannot be associated with various operation parameters of the ship in the navigation process, so that comprehensive and deep normative judgment and excavation are difficult to complete. Therefore, an informatization means is needed to assist a manager to automatically supervise, discover irregular behaviors and prompt.
Disclosure of Invention
The invention aims to solve the technical problem of providing a ship control behavior risk assessment system and method based on big data, which can be used for assessing ship control behaviors; based on the Internet of things and big data technology, ship azimuth data and engine room monitoring data of the whole process of ship starting, sailing and stopping are collected, a ship control rule knowledge base is fused by using a machine learning algorithm to form a ship control behavior standard model base, the ship control behavior standard evaluation result and the evaluation report can be automatically and continuously output, information support is provided for monitoring and early warning of ship control behaviors, and the ship control behavior model base has comprehensiveness, economy and timeliness, and the timeliness and the accuracy of ship management are improved.
In order to achieve the technical characteristics, the invention aims to realize that: a ship control behavior risk assessment system based on big data comprises a control parameter acquisition module, a data cleaning module, a sample big database module, a decision comparison analysis module, a risk grade assessment module and an assessment result feedback module;
the control parameter acquisition module comprises a ship navigation data acquisition module and an engine room monitoring data acquisition module, the ship navigation data acquisition module is used for acquiring ship navigation data, and the engine room monitoring data acquisition module is used for acquiring engine room monitoring data;
the data cleaning module is used for cleaning the data acquired by the control parameter acquisition module;
the large sample database module comprises a static large data module and a dynamic large data module, wherein the static large data module is used for storing initial data of each inherent static parameter of a ship input in advance, the dynamic large data module is used for acquiring ship navigation data and engine room monitoring data acquired when the ship is formed through operation meeting the standard requirement in a period of normal navigation and forming dynamic parameters, and the dynamic parameters and the static parameters are combined to form standard sample parameters;
the decision comparison and analysis module is used for extracting ship navigation data and engine room monitoring data processed by the data cleaning module, performing comparison and analysis on the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal, acquiring control behavior models corresponding to different control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements;
the risk grade evaluation module is used for collecting an analysis judgment result obtained by the decision comparison analysis module aiming at the control behavior model, evaluating the judgment result to obtain a corresponding score, giving different weights to the different control behavior models, and evaluating the risk grade after weighting all the scores to obtain the risk grade of the navigation;
and the evaluation result feedback module is used for counting and storing the risk level of the navigation in the past in a period of time to form an evaluation report in the period of time.
The ship navigation data comprises ship navigation starting and ending time, navigation speed and navigation track; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine.
The static big data module is used for storing initial data of various inherent static parameters of a ship, which are input in advance, and comprises ship type parameters, displacement, host parameters, auxiliary engine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters;
the dynamic big data module is used for collecting ship navigation data and engine room monitoring data which are collected when a ship is operated and formed in normal navigation in a period of time and meet the standard requirements, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters.
The different steering behavior models include: the system comprises an open-voyage behavior analysis model, a shut-down behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process communication equipment analysis model, a night voyage process analysis model, a driving process analysis model and a ship berthing correct-use light analysis model.
The assessment method of the ship control behavior risk assessment system based on big data comprises the following steps:
s100, obtaining standard sample data through a sample big database module, wherein the sample big database module comprises a static big data module and a dynamic big data module, and the static big data module is used for storing initial data of each inherent static parameter of a ship input in advance; the dynamic big data module is used for acquiring ship navigation data and engine room monitoring data acquired when a ship is formed through control meeting the standard requirements in normal navigation for a period of time, forming dynamic parameters, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters;
s200, acquiring control parameter data of the navigation through a control parameter acquisition module, wherein the control parameter acquisition module comprises a ship navigation data acquisition module and an engine room monitoring data acquisition module, the ship navigation data acquisition module is used for acquiring ship navigation data, and the engine room monitoring data acquisition module is used for acquiring engine room monitoring data;
s300, data cleaning; cleaning and denoising the navigation data acquisition module and the cabin monitoring data acquisition module acquired by the control parameter acquisition module through the data cleaning module;
s400, extracting ship navigation data and engine room monitoring data processed by the data cleaning module through a decision comparison analysis module, comparing and analyzing the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal, acquiring different control behavior models corresponding to control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements;
s500, collecting analysis judgment results obtained by the decision comparison analysis module aiming at the different control behavior models through a risk grade evaluation module, evaluating the judgment results to obtain scores of the analysis judgment results, giving weights to the different control behavior models, and evaluating the risk grade after weighting all the scores to obtain the risk grade of the navigation, wherein the risk grade is divided into the following parts: high risk, medium risk, low risk, no risk;
s600, the evaluation result feedback module is used for counting and storing the risk level of the navigation in the past in a period of time to form an evaluation report in the period of time.
The different steering behavior models include: the system comprises a starting behavior analysis model, a stopping behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process navigation equipment analysis model, a night navigation process analysis model, a driving process analysis model and a correct ship light use analysis model.
The ship navigation data comprises ship navigation starting and ending time, navigation speed and navigation track; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine; data acquisition is realized by adopting the acquisition of a sensor or a measuring instrument;
in the data cleaning process in the step S300, processing is performed on the partial null values and the abnormal values, because the data volume is large, the partial null values are directly deleted, and the abnormal values are removed after being detected by adopting a quartile interval;
the ship navigation data and the engine room monitoring data are mainly time sequence data, and the average number, the median number, the standard deviation, the maximum value, the minimum value, the slope, the skewness and the kurtosis of the data in a time period are extracted by adopting a sliding window method to serve as characteristics, so that a proper characteristic data set is finally formed;
and extracting different characteristic values for different control behaviors.
The static big data module is used for storing initial data of various inherent static parameters of a ship, which are input in advance, and comprises ship type parameters, displacement, host parameters, auxiliary engine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters; the dynamic big data module is used for acquiring ship navigation data and engine room monitoring data acquired when a ship is formed through operation meeting the standard requirements in a period of normal navigation, forming dynamic parameters, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters.
In the decision tree algorithm in S400, the decision tree learns through a training dataset to obtain a top-down tree model, and then applies test data to the tree model to obtain a prediction classification result, which is a binary tree model including a root node, a middle node, and leaf nodes, where each node is determined and selected according to a splitting criterion of each attribute, and the leaf nodes are final classification categories of the sample;
the Gini index represents attribute classification uncertainty, the smaller the value of the Gini index is, the lower the uncertainty is, namely the Gini index is used as a standard for selecting optimal characteristics, and a decision tree based on the Gini index serving as an attribute splitting standard comprises CART, SLIQ and SPRINT; gini formula is as follows, pi represents the probability that a sample belongs to the i class, and the probability that a sample is misclassified is 1-pi:
the CART algorithm is a classification regression binary decision tree, that is, when a certain feature is used for sample division, the sample division can be only divided into two sets: equal to the set of given sample features, not equal to the set of given sample features; wherein S is a sample data set, and S1 and S2 are subsample sets:
and (3) generating a model: inputting a condition comprising a training data set S and stopping calculation; the output is a CART decision tree, and according to the training data set, the following processing is sequentially carried out on each node from the root node to construct a binary decision tree:
(1) Setting the training data set of the nodes as S, calculating the Gini index of the existing characteristic about the data set, in this case, dividing each possibly-obtained value a of each characteristic A into two parts of S1 and S2 according to the test condition that whether the sample point meets A = a, and calculating the Gini index Gini (S, a) when A = a by using a formula (4);
(2) And selecting the feature with the smallest Gini index and the corresponding segmentation point as the optimal feature and the optimal segmentation point from all the possible features A and all the possible segmentation points a thereof. Generating two sub-nodes from the current node according to the optimal characteristics and the optimal segmentation points, and distributing the training data set to the two sub-nodes according to the characteristics;
(3) Recursively calling the expression (1) and the expression (2) for the two sub-nodes until a stop condition is met, namely the number of samples in the nodes is smaller than a preset threshold, the Gini index of the sample set is smaller than the threshold, or no more features exist;
(4) Generating a CART decision tree.
Generating 9 control behavior models by ship navigation data and engine room monitoring data, wherein main labels and main factors of the control behavior models comprise:
the control behavior model I and the driving behavior analysis model are labeled as follows: whether the driving control behavior is standard or not is determined by the following main factors: the slope of the water temperature curve, the maximum value of the water temperature, the slope of the main machine rotating speed curve and the phase difference of the water temperature-navigational speed curve;
a second control behavior model and an analysis model of the navigation stopping behavior, wherein the labels are as follows: whether the navigation stopping control behavior is standard or not is determined by the following main factors: the slope of the water temperature curve and the slope of the speed curve;
a third control behavior model and a forward and reverse switching analysis model are labeled as follows: whether the forward and reverse switching behaviors are standard or not is determined by the following main factors: the slope of a main engine rotating speed curve and the phase difference of a rotating speed-navigational speed curve;
the fourth control behavior model and the voyage speed analysis model are labeled as follows: whether the voyage is abnormal or not is determined by the following main factors: voyage statistics, voyage speed statistics and oil consumption statistics;
a fifth control behavior model and a full load running ratio analysis model are labeled as follows: whether the full load operation ratio is abnormal or not is determined by the following main factors: power distribution statistics, maximum power;
control action model six, navigation process admittance equipment analysis model, the label is: whether navigation process leads equipment unusual, the main factor is: the online time and the navigation time of the equipment are obtained;
a seventh control behavior model and a night voyage process analysis model are labeled as follows: whether the control behavior is standard in the night voyage process is determined by the following main factors: the method comprises the following steps of (1) navigating at night, navigating at night host rotating speed curve and navigating at night ship track curve;
control action model eight, driving process analysis model, the label is: whether the control behavior is standard or not in the driving process is determined by the following main factors: counting the rotating speed of a host, counting the navigational speed of a ship and obtaining a ship track curve;
the control behavior model nine is that the ship correctly uses the light analysis model, and the label is as follows: whether the behavior is normal or not is controlled by using the light, and the main factors are as follows: monitoring a main engine rotating speed curve, a ship navigation stopping track curve and a ship light state;
accordingly, the control behavior model is obtained through a decision tree algorithm, and whether the corresponding control behavior meets the standard requirement or not is judged.
The invention has the following beneficial effects:
according to the ship control behavior standardization method based on the Internet of things and big data technology, ship azimuth data and engine room monitoring data in the whole process of ship starting, sailing and stopping are collected, a ship control rule knowledge base is fused by using a machine learning algorithm to form a ship control behavior standardization model base, the ship control behavior standardization evaluation result and the evaluation report can be automatically and continuously output, informatization support is provided for monitoring and early warning of ship control behaviors, and the ship control behavior standardization method based on the Internet of things and big data technology has comprehensiveness, economy and timeliness, and the timeliness and the accuracy of ship management are improved.
Drawings
The invention is further illustrated by the following figures and examples.
FIG. 1 is a block diagram of a risk assessment system of the present invention.
Fig. 2 is a block diagram of the manipulation parameter acquisition module according to the present invention.
FIG. 3 is a block diagram of a sample big database module of the present invention.
In the figure: the system comprises a control parameter acquisition module 1, a data cleaning module 2, a sample big database module 3, a decision comparison analysis module 4, a risk level evaluation module 5 and an evaluation result feedback module 6;
a ship navigation data acquisition module 101 and an engine room monitoring data acquisition module 102;
a static big data module 301 and a dynamic big data module 302.
Detailed Description
Embodiments of the present invention will be further described with reference to the accompanying drawings.
Example 1:
referring to fig. 1-3, a ship control behavior risk assessment system based on big data comprises a control parameter acquisition module 1, a data cleaning module 2, a sample big database module 3, a decision comparison analysis module 4, a risk level assessment module 5 and an assessment result feedback module 6; the control parameter acquisition module 1 comprises a ship navigation data acquisition module 101 and an engine room monitoring data acquisition module 102, wherein the ship navigation data acquisition module 101 is used for acquiring ship navigation data, and the engine room monitoring data acquisition module 102 is used for acquiring engine room monitoring data; the data cleaning module 2 is used for cleaning the data acquired by the control parameter acquisition module 1; the sample big database module 3 comprises a static big data module 301 and a dynamic big data module 302, wherein the static big data module 301 is used for storing initial data of each inherent static parameter of a ship input in advance, the dynamic big data module 302 is used for collecting ship navigation data and engine room monitoring data collected when the ship is formed through operation meeting the standard requirement in a period of normal navigation and forming a dynamic parameter, and the dynamic parameter and the static parameter are combined to form a standard sample parameter; the decision comparison and analysis module 4 is used for extracting ship navigation data and engine room monitoring data processed by the data cleaning module, comparing and analyzing the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal, acquiring control behavior models corresponding to different control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements; the risk level evaluation module 5 is configured to collect analysis determination results obtained by the decision comparison analysis module 4 for the control behavior models, evaluate the determination results to obtain corresponding scores, give different weights to the different control behavior models, and evaluate risk levels after weighting all the scores to obtain a risk level of the current navigation; and the evaluation result feedback module 6 is used for counting and storing the risk level of the past sailing within a period of time to form an evaluation report within the period of time. By adopting the system, based on the internet of things and big data technology, ship direction data and engine room monitoring data in the whole process of ship starting, sailing and stopping are collected, a machine learning algorithm is utilized, a ship control rule knowledge base is fused, a ship control behavior standard model base is formed, ship control behavior standard evaluation results and evaluation reports can be automatically and continuously output, information support is provided for monitoring and early warning of ship control behaviors, and the system has comprehensiveness, economy and timeliness, and the timeliness and accuracy of ship management are improved.
Further, the ship navigation data comprises ship navigation starting and ending time, navigation speed and navigation track; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine. The static big data module 301 is used for storing initial data of each inherent static parameter of a ship, which are input in advance, and comprises ship type parameters, water displacement, host parameters, auxiliary engine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters; the dynamic big data module 302 is used for collecting ship navigation data and engine room monitoring data collected when a ship is operated and formed in normal navigation in accordance with the standard requirements in a period of time, forming standard sample parameters matched with the ship type by combining the dynamic parameters and the static parameters. By adopting the ship navigation data and the cabin monitoring data, standard sample parameters can be formed by subsequently collecting the static big data module 301 and the dynamic big data module 302 conveniently.
Further, the different steering behavior models include: the system comprises an open-voyage behavior analysis model, a shut-down behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process communication equipment analysis model, a night voyage process analysis model, a driving process analysis model and a ship berthing correct-use light analysis model. The different control behavior models are convenient for subsequent utilization of a machine learning algorithm, a ship control rule knowledge base is fused to form a ship control behavior standard model base, ship control behavior standardization evaluation results and evaluation reports can be automatically and continuously output, and informatization support is provided for monitoring and early warning of ship control behaviors.
Example 2:
the assessment method of the ship control behavior risk assessment system based on big data comprises the following steps:
s100, obtaining standard sample data through a sample big database module 3, wherein the sample big database module comprises a static big data module and a dynamic big data module, and the static big data module is used for storing initial data of each inherent static parameter of a ship input in advance; the dynamic big data module is used for acquiring ship navigation data and engine room monitoring data acquired when a ship is formed through control meeting the standard requirements in normal navigation for a period of time, forming dynamic parameters, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters;
s200, acquiring control parameter data of the navigation through a control parameter acquisition module 1, wherein the control parameter acquisition module comprises a ship navigation data acquisition module and an engine room monitoring data acquisition module, the ship navigation data acquisition module is used for acquiring ship navigation data, and the engine room monitoring data acquisition module is used for acquiring engine room monitoring data;
s300, data cleaning; cleaning and denoising the navigation data acquisition module and the cabin monitoring data acquisition module acquired by the control parameter acquisition module 1 through the data cleaning module 2;
s400, extracting ship navigation data and engine room monitoring data processed by the data cleaning module 2 through the decision comparison analysis module 4, performing comparison analysis on the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal, acquiring different control behavior models corresponding to control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements;
s500, collecting analysis judgment results obtained by the decision comparison analysis module 4 aiming at the different control behavior models through a risk grade evaluation module 5, evaluating the judgment results to obtain scores of the analysis judgment results, giving weights to the different control behavior models, carrying out risk grade evaluation after weighting all the scores to obtain the risk grade of the navigation, wherein the risk grade is divided into the following parts: high risk, medium risk, low risk, no risk;
s600, the evaluation result feedback module 6 is used for counting and storing the risk level of the past sailing within a period of time to form an evaluation report within the period of time.
Further, the different steering behavior models include: the system comprises a starting behavior analysis model, a stopping behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process navigation equipment analysis model, a night navigation process analysis model, a driving process analysis model and a correct ship light use analysis model.
Further, the ship navigation data comprises ship navigation starting and ending time, navigation speed and navigation track; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine; data acquisition is realized by adopting the acquisition of a sensor or a measuring instrument;
further, in the data cleaning process in S300, processing is performed on a part of null values and abnormal values, because the data size is large, the part of null values is directly deleted, and the abnormal values are removed after being detected by adopting a quartile interval;
further, ship navigation data and engine room monitoring data are mainly time sequence data, the average number, the median, the standard deviation, the maximum value, the minimum value, the slope, the skewness and the kurtosis of time section data are extracted by adopting a sliding window method to serve as characteristics, and finally a proper characteristic data set is formed; and extracting different characteristic values for different control behaviors.
Further, the static big data module is used for storing initial data of various inherent static parameters of the ship, which are input in advance, and the initial data comprise ship type parameters, water displacement, host parameters, auxiliary machine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters; the dynamic big data module is used for collecting ship navigation data and engine room monitoring data which are collected when a ship is formed through operation meeting the standard requirements in normal navigation for a period of time, forming dynamic parameters, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters.
Example 3:
in the decision tree algorithm in S400, the decision tree learns through a training data set to obtain a top-down tree model, and then applies test data to the tree model to obtain a prediction classification result, which is a binary tree model including a root node, a middle node, and leaf nodes, where each node is judged and selected according to a splitting criterion of each attribute, and the leaf nodes are final classification categories of the sample;
the Gini index represents attribute classification uncertainty, the smaller the value of the Gini index is, the lower the uncertainty is, namely the Gini index is used as a standard for selecting optimal characteristics, and a decision tree based on the Gini index as an attribute splitting standard comprises CART, SLIQ and SPRINT; gini formula is as follows, pi represents the probability that a sample belongs to the i class, and the probability that a sample is misclassified is 1-pi:
the CART algorithm is a classification regression binary decision tree, that is, when a certain feature is used for sample division, the sample division can be divided into two sets: equal to the set of given sample features, not equal to the set of given sample features; wherein S is a sample data set, and S1 and S2 are subsample sets:
and (3) generating a model: inputting a condition comprising a training data set S and stopping calculation; the output is a CART decision tree, and according to the training data set, the following processing is sequentially carried out on each node from the root node to construct a binary decision tree:
(1) Setting the training data set of the nodes as S, calculating the Gini index of the existing characteristic about the data set, in this case, dividing each value a which can be taken by each characteristic A into two parts of S1 and S2 according to the test condition that whether the sample point meets A = a, and calculating the Gini index Gini (S, a) when A = a by using a formula (4);
(2) And selecting the feature with the smallest Gini index and the corresponding segmentation point as an optimal feature and an optimal segmentation point from all the possible features A and all the possible segmentation points a thereof. Generating two sub-nodes from the current node according to the optimal characteristics and the optimal segmentation points, and distributing the training data set to the two sub-nodes according to the characteristics;
(3) Recursively calling the expression (1) and the expression (2) for the two sub-nodes until a stop condition is met, namely the number of samples in the nodes is smaller than a preset threshold, the Gini index of the sample set is smaller than the threshold, or no more features exist;
(4) And generating a CART decision tree.
Example 4:
in the specific implementation process, 9 control behavior models are generated by ship navigation data and engine room monitoring data, and main labels and main factors of the control behavior models comprise:
the control behavior model I and the driving behavior analysis model are labeled as follows: whether the driving control behavior is standard or not is determined by the following main factors: the water temperature curve slope, the water temperature maximum value, the host machine rotating speed curve slope and the water temperature-navigational speed curve phase difference;
a second control behavior model and an analysis model of the navigation stopping behavior, wherein the labels are as follows: whether the navigation stopping control behavior is standard or not is determined by the following main factors: the slope of a water temperature curve and the slope of a navigational speed curve;
a third control behavior model and a forward and reverse switching analysis model are labeled as follows: whether the forward and reverse switching behaviors are standard or not is determined by the following main factors: the slope of the main machine rotation speed curve and the phase difference of the rotation speed-navigational speed curve;
a fourth control behavior model and a range speed analysis model, wherein the labels are as follows: whether the voyage is abnormal or not is determined by the following main factors: voyage statistics, voyage speed statistics and oil consumption statistics;
a fifth control behavior model and a full load running ratio analysis model are labeled as follows: whether the full load operation ratio is abnormal or not is determined by the following main factors: power distribution statistics, maximum power;
control action model six, navigation process admittance equipment analysis model, the label is: whether navigation process leads equipment unusual, the main factor is: the online time and the navigation time of the equipment are prolonged;
a seventh control behavior model and a night voyage process analysis model, wherein the labels are as follows: whether the control behavior is standard in the night navigation process is determined by the following main factors: the method comprises the following steps of (1) navigating at night, navigating at night host rotating speed curve and navigating at night ship track curve;
control action model eight, driving process analysis model, the label is: whether the control behavior is standard or not in the driving process is determined by the following main factors: counting the rotating speed of a host, counting the navigational speed of a ship and obtaining a ship track curve;
the control behavior model nine and the ship correctly use the light analysis model, and the labels are as follows: whether the light manipulation behavior is normal or not is used, and the main factors are as follows: monitoring a main engine rotating speed curve, a ship navigation stopping track curve and a ship light state;
therefore, the control behavior model is obtained through a decision tree algorithm, and whether the corresponding control behavior meets the standard requirement or not is judged.
Claims (10)
1. A ship control behavior risk assessment system based on big data is characterized by comprising a control parameter acquisition module (1), a data cleaning module (2), a sample big database module (3), a decision comparison analysis module (4), a risk grade assessment module (5) and an assessment result feedback module (6);
the control parameter acquisition module (1) comprises a ship navigation data acquisition module (101) and an engine room monitoring data acquisition module (102), wherein the ship navigation data acquisition module (101) is used for acquiring ship navigation data, and the engine room monitoring data acquisition module (102) is used for acquiring engine room monitoring data;
the data cleaning module (2) is used for cleaning the data acquired by the control parameter acquisition module (1);
the sample big database module (3) comprises a static big data module (301) and a dynamic big data module (302), wherein the static big data module (301) is used for storing initial data of each inherent static parameter of a ship input in advance, the dynamic big data module (302) is used for collecting ship navigation data and engine room monitoring data collected when the ship is formed through operation meeting the standard requirement in a period of normal navigation and forming dynamic parameters, and the dynamic parameters and the static parameters are combined to form standard sample parameters;
the decision comparison and analysis module (4) is used for extracting ship navigation data and engine room monitoring data processed by the data cleaning module, comparing and analyzing the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal or not, acquiring control behavior models corresponding to different control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements or not;
the risk level evaluation module (5) is used for collecting analysis judgment results obtained by the decision comparison analysis module (4) aiming at the control behavior model, evaluating the judgment results to obtain corresponding scores, giving different weights to the different control behavior models, and evaluating the risk level after weighting all the scores to obtain the risk level of the navigation;
and the evaluation result feedback module (6) is used for counting and storing the risk level of the past sailing within a period of time to form an evaluation report within the period of time.
2. The big-data-based ship maneuvering behavior risk assessment system according to claim 1, characterized in that the ship voyage data comprises ship voyage start-stop time, ship voyage speed and ship voyage trajectory; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine.
3. The ship maneuvering behavior risk assessment system based on big data as claimed in claim 1, characterized in that the static big data module (301) is used for storing initial data of each inherent static parameter of the ship input in advance, including ship type parameters, water displacement, main engine parameters, auxiliary engine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters;
the dynamic big data module (302) is used for collecting ship navigation data and engine room monitoring data collected when a ship is formed through operation meeting the standard requirements in a period of normal navigation and forming dynamic parameters, and standard sample parameters matched with the ship type are formed through combination of the dynamic parameters and the static parameters.
4. The big-data-based ship maneuvering behavior risk assessment system according to claim 1, wherein the different maneuvering behavior models comprise: the system comprises a starting behavior analysis model, a stopping behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process navigation equipment analysis model, a night navigation process analysis model, a driving process analysis model and a correct light use analysis model for ship berthing.
5. An assessment method using the big data based ship maneuvering behavior risk assessment system according to any one of claims 1-4, characterized by: the method comprises the following steps:
s100, obtaining standard sample data through a sample big database module (3), wherein the sample big database module comprises a static big data module and a dynamic big data module, and the static big data module is used for storing initial data of each inherent static parameter of a ship input in advance; the dynamic big data module is used for acquiring ship navigation data and engine room monitoring data acquired when a ship is formed through operation meeting the standard requirements in normal navigation for a period of time and forming dynamic parameters, and standard sample parameters matched with the ship model are formed through combination of the dynamic parameters and the static parameters;
s200, acquiring control parameter data of the navigation through a control parameter acquisition module (1), wherein the control parameter acquisition module comprises a ship navigation data acquisition module and an engine room monitoring data acquisition module, the ship navigation data acquisition module is used for acquiring ship navigation data, and the engine room monitoring data acquisition module is used for acquiring engine room monitoring data;
s300, data cleaning; the navigation data acquisition module and the cabin monitoring data acquisition module which are acquired by the control parameter acquisition module (1) are cleaned and denoised by the data cleaning module (2);
s400, extracting ship navigation data and engine room monitoring data processed by the data cleaning module (2) through the decision comparison analysis module (4), performing comparison analysis on the ship navigation data and the engine room monitoring data with standard sample parameters, judging whether the ship navigation data and the engine room monitoring data are normal, acquiring different control behavior models corresponding to control behaviors through a decision tree algorithm, and judging whether the corresponding control behaviors meet the standard requirements;
s500, collecting analysis judgment results obtained by the decision comparison analysis module (4) aiming at the different control behavior models through a risk grade evaluation module (5), evaluating the judgment results to obtain scores of the analysis judgment results, giving weights to the different control behavior models, carrying out risk grade evaluation after weighting all the scores to obtain the risk grade of the navigation, wherein the risk grade is divided into the following parts: high risk, medium risk, low risk, no risk;
s600, the evaluation result feedback module (6) is used for counting and storing the risk level of the navigation in the past in a period of time to form an evaluation report in the period of time.
6. The assessment method of the ship maneuvering behavior risk assessment system based on big data according to claim 5, characterized by comprising the following steps: the different steering behavior models include: the system comprises a starting behavior analysis model, a stopping behavior analysis model, a forward and reverse switching analysis model, a voyage speed analysis model, a full-load running ratio analysis model, a navigation process navigation equipment analysis model, a night navigation process analysis model, a driving process analysis model and a correct ship light use analysis model.
7. The assessment method of the ship maneuvering behavior risk assessment system based on the big data as claimed in claim 5, characterized in that: the ship navigation data comprises ship navigation starting and ending time, navigation speed and navigation track; the engine room monitoring data comprises the rotating speed, power, water temperature, oil pressure and oil tank liquid level of the ship main engine; data acquisition is realized by adopting the acquisition of a sensor or a measuring instrument;
in the data cleaning process in the step S300, processing is performed on the partial null values and the abnormal values, because the data volume is large, the partial null values are directly deleted, and the abnormal values are removed after being detected by adopting a quartile interval;
the ship navigation data and the engine room monitoring data are mainly time sequence data, and the average number, the median number, the standard deviation, the maximum value, the minimum value, the slope, the skewness and the kurtosis of time section data are extracted by adopting a sliding window method to serve as characteristics, so that a proper characteristic data set is finally formed;
for different manipulation behaviors, different feature values are extracted.
8. The assessment method of the ship maneuvering behavior risk assessment system based on the big data as claimed in claim 5, characterized in that: the static big data module is used for storing initial data of various inherent static parameters of a ship, which are input in advance, and comprises ship type parameters, displacement, host parameters, auxiliary engine parameters, cooling system parameters, steering engine parameters, shafting and propulsion system parameters; the dynamic big data module is used for acquiring ship navigation data and engine room monitoring data acquired when a ship is formed through operation meeting the standard requirements in a period of normal navigation, forming dynamic parameters, and forming standard sample parameters matched with the ship type through combination of the dynamic parameters and the static parameters.
9. The assessment method of the ship maneuvering behavior risk assessment system based on big data according to claim 5, characterized by comprising the following steps: in the decision tree algorithm in S400, the decision tree learns through a training data set to obtain a top-down tree model, and then applies test data to the tree model to obtain a prediction classification result, which is a binary tree model including a root node, a middle node, and leaf nodes, where each node is judged and selected according to a splitting criterion of each attribute, and the leaf nodes are final classification categories of the sample;
the Gini index represents attribute classification uncertainty, the smaller the value of the Gini index is, the lower the uncertainty is, namely the Gini index is used as a standard for selecting optimal characteristics, and a decision tree based on the Gini index serving as an attribute splitting standard comprises CART, SLIQ and SPRINT; gini formula is as follows, pi represents the probability that a sample belongs to the i class, and the probability that a sample is misclassified is 1-pi:
the CART algorithm is a classification regression binary decision tree, that is, when a certain feature is used for sample division, the sample division can be only divided into two sets: a set equal to the given sample characteristic, a set not equal to the given sample characteristic; wherein S is a sample data set, and S1 and S2 are subsample sets:
the generation process of the model comprises the following steps: inputting a condition comprising a training data set S and stopping calculation; outputting a CART decision tree, and sequentially performing the following processing on each node from the root node according to a training data set to construct a binary decision tree:
(1) Setting the training data set of the nodes as S, calculating the Gini index of the existing characteristic about the data set, in this case, dividing each possibly-obtained value a of each characteristic A into two parts of S1 and S2 according to the test condition that whether the sample point meets A = a, and calculating the Gini index Gini (S, a) when A = a by using a formula (4);
(2) And selecting the feature with the smallest Gini index and the corresponding segmentation point as an optimal feature and an optimal segmentation point from all the possible features A and all the possible segmentation points a thereof. Generating two sub-nodes from the current node according to the optimal characteristics and the optimal segmentation points, and distributing the training data set to the two sub-nodes according to the characteristics;
(3) Recursively calling the formula (1) and the formula (2) for the two sub-nodes until a stop condition is met, namely the number of samples in the nodes is smaller than a preset threshold, the Gini index of the sample set is smaller than the threshold, or no more features exist;
(4) Generating a CART decision tree.
10. The assessment method of the ship maneuvering behavior risk assessment system based on the big data as claimed in claim 9, characterized in that:
the ship navigation data and the engine room monitoring data generate 9 control behavior models, and main labels and main factors of the control behavior models comprise:
the control behavior model I and the driving behavior analysis model are labeled as follows: whether the driving operation behavior is standard or not is determined by the following main factors: the slope of the water temperature curve, the maximum value of the water temperature, the slope of the main machine rotating speed curve and the phase difference of the water temperature-navigational speed curve;
a second control behavior model and an analysis model of the navigation stopping behavior, wherein the labels are as follows: whether the navigation stopping control behavior is standard or not is determined by the following main factors: the slope of the water temperature curve and the slope of the speed curve;
a third control behavior model and a forward and reverse switching analysis model are labeled as follows: whether the forward and reverse switching behaviors are standard or not is determined by the following main factors: the slope of a main engine rotating speed curve and the phase difference of a rotating speed-navigational speed curve;
the fourth control behavior model and the voyage speed analysis model are labeled as follows: whether the voyage is abnormal or not is determined by the following main factors: voyage statistics, voyage speed statistics and oil consumption statistics;
a fifth control behavior model and a full load running ratio analysis model, wherein the labels are as follows: whether the full load operation ratio is abnormal or not is determined by the following main factors: power distribution statistics, maximum power;
control action model six, navigation process admittance equipment analysis model, the label is: whether navigation process leads equipment unusual, the main factor is: the online time and the navigation time of the equipment are prolonged;
a seventh control behavior model and a night voyage process analysis model, wherein the labels are as follows: whether the control behavior is standard in the night navigation process is determined by the following main factors: the method comprises the following steps of (1) navigating at night, and navigating at night at a host rotation speed curve and navigating at night on a ship track curve;
control action model eight, driving process analysis model, the label is: whether the control behavior is standard or not in the driving process is determined by the following main factors: counting the rotating speed of a host, counting the navigational speed of a ship and obtaining a ship track curve;
the control behavior model nine and the ship correctly use the light analysis model, and the labels are as follows: whether the behavior is normal or not is controlled by using the light, and the main factors are as follows: monitoring a main engine rotating speed curve, a ship navigation stopping track curve and a ship light state;
accordingly, the control behavior model is obtained through a decision tree algorithm, and whether the corresponding control behavior meets the standard requirement or not is judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211260297.6A CN115659263B (en) | 2022-10-14 | 2022-10-14 | Ship control behavior risk assessment system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211260297.6A CN115659263B (en) | 2022-10-14 | 2022-10-14 | Ship control behavior risk assessment system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115659263A true CN115659263A (en) | 2023-01-31 |
| CN115659263B CN115659263B (en) | 2023-08-08 |
Family
ID=84988267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211260297.6A Active CN115659263B (en) | 2022-10-14 | 2022-10-14 | Ship control behavior risk assessment system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115659263B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115880950A (en) * | 2023-02-27 | 2023-03-31 | 中国船舶集团有限公司第七一九研究所 | Data processing method of automatic ship identification system |
| CN117037089A (en) * | 2023-10-09 | 2023-11-10 | 亿海蓝（北京）数据技术股份公司 | Method and device for detecting ship unauthorized exit behavior and readable storage medium |
| CN117390762B (en) * | 2023-09-15 | 2024-05-14 | 中国人民解放军92942部队 | Full-flow ship safety design analysis method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009723A (en) * | 2017-12-01 | 2018-05-08 | 大连海事大学 | A kind of ship navigation state judges and energy efficiency state assessment system |
| CN109146195A (en) * | 2018-09-06 | 2019-01-04 | 北方爆破科技有限公司 | A kind of blast fragmentation size prediction technique based on cart tree regression algorithm |
| CN109657880A (en) * | 2019-01-09 | 2019-04-19 | 中交信息技术国家工程实验室有限公司 | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network |
| AU2020101965A4 (en) * | 2020-08-25 | 2020-10-01 | Wuhan University Of Technology | A method of navigational early warming for ship encounter, and system thereof |
| CN112208728A (en) * | 2020-09-30 | 2021-01-12 | 震兑工业智能科技有限公司 | Ship fouling monitoring and early warning method |
| CN112441196A (en) * | 2020-11-20 | 2021-03-05 | 武汉理工大学 | Processing method, system and storage medium of ship navigation risk assessment information |
| CN113032502A (en) * | 2021-02-09 | 2021-06-25 | 北京工业大学 | Ship anomaly detection method based on improved track segment DBSCAN clustering |
| CN113128826A (en) * | 2021-03-03 | 2021-07-16 | 武汉理工大学 | Navigation risk prediction method, navigation risk prediction device and storage medium |
| CN113212153A (en) * | 2021-04-15 | 2021-08-06 | 东风汽车集团股份有限公司 | Method, device, equipment and storage medium for high-low speed operation of fan |
| CN113762394A (en) * | 2021-09-09 | 2021-12-07 | 昆明理工大学 | Blasting block size prediction method |
| US20220036738A1 (en) * | 2020-07-29 | 2022-02-03 | Wuhan University Of Technology | Method and system for assessing and early warning ship collision risk |
| CN114662575A (en) * | 2022-03-09 | 2022-06-24 | 集美大学 | Wind power water area ship navigation risk estimation method and system and storage medium |
| CN115017684A (en) * | 2022-05-25 | 2022-09-06 | 广州星际海洋工程设计有限公司 | Intelligent energy efficiency management system for ship |
-
2022
- 2022-10-14 CN CN202211260297.6A patent/CN115659263B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009723A (en) * | 2017-12-01 | 2018-05-08 | 大连海事大学 | A kind of ship navigation state judges and energy efficiency state assessment system |
| CN109146195A (en) * | 2018-09-06 | 2019-01-04 | 北方爆破科技有限公司 | A kind of blast fragmentation size prediction technique based on cart tree regression algorithm |
| CN109657880A (en) * | 2019-01-09 | 2019-04-19 | 中交信息技术国家工程实验室有限公司 | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network |
| US20220036738A1 (en) * | 2020-07-29 | 2022-02-03 | Wuhan University Of Technology | Method and system for assessing and early warning ship collision risk |
| AU2020101965A4 (en) * | 2020-08-25 | 2020-10-01 | Wuhan University Of Technology | A method of navigational early warming for ship encounter, and system thereof |
| CN112208728A (en) * | 2020-09-30 | 2021-01-12 | 震兑工业智能科技有限公司 | Ship fouling monitoring and early warning method |
| CN112441196A (en) * | 2020-11-20 | 2021-03-05 | 武汉理工大学 | Processing method, system and storage medium of ship navigation risk assessment information |
| CN113032502A (en) * | 2021-02-09 | 2021-06-25 | 北京工业大学 | Ship anomaly detection method based on improved track segment DBSCAN clustering |
| CN113128826A (en) * | 2021-03-03 | 2021-07-16 | 武汉理工大学 | Navigation risk prediction method, navigation risk prediction device and storage medium |
| CN113212153A (en) * | 2021-04-15 | 2021-08-06 | 东风汽车集团股份有限公司 | Method, device, equipment and storage medium for high-low speed operation of fan |
| CN113762394A (en) * | 2021-09-09 | 2021-12-07 | 昆明理工大学 | Blasting block size prediction method |
| CN114662575A (en) * | 2022-03-09 | 2022-06-24 | 集美大学 | Wind power water area ship navigation risk estimation method and system and storage medium |
| CN115017684A (en) * | 2022-05-25 | 2022-09-06 | 广州星际海洋工程设计有限公司 | Intelligent energy efficiency management system for ship |
Non-Patent Citations (3)
| Title |
|---|
| PO-RUEY LEI: "Exploring Trajectory Behavior Model for Anomaly Detection in Maritime Moving Objects", pages 271 * |
| 尉浩然 等: "基于操舵规律的船舶行为预测的搁浅率动态风险研究", pages 74 - 75 * |
| 李义山: "基于随机森林的船舶碰撞风险预警研究", pages 1 - 77 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115880950A (en) * | 2023-02-27 | 2023-03-31 | 中国船舶集团有限公司第七一九研究所 | Data processing method of automatic ship identification system |
| CN117390762B (en) * | 2023-09-15 | 2024-05-14 | 中国人民解放军92942部队 | Full-flow ship safety design analysis method |
| CN117037089A (en) * | 2023-10-09 | 2023-11-10 | 亿海蓝（北京）数据技术股份公司 | Method and device for detecting ship unauthorized exit behavior and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115659263B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520080B (en) | Ship diesel generator fault prediction and health state online evaluation system and method | |
| CN115659263B (en) | Ship control behavior risk assessment system and method based on big data | |
| CN112596495B (en) | Industrial equipment fault diagnosis method and system based on knowledge graph | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN111311059B (en) | Waterwheel house fault diagnosis method based on knowledge graph | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN105590146A (en) | Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN111190349A (en) | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment | |
| CN114021932A (en) | Energy efficiency evaluation and diagnosis method, system and medium for wind turbine generator | |
| CN113847950A (en) | Intelligent ship equipment state monitoring system based on cloud computing and information interaction method | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN114492642A (en) | Mechanical fault online diagnosis method for multi-scale element depth residual shrinkage network | |
| CN115526515A (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN115392782A (en) | Method and system for monitoring and diagnosing health state of process system of nuclear power plant | |
| Chatterjee et al. | A dual transformer model for intelligent decision support for maintenance of wind turbines | |
| CN113590396A (en) | Method and system for diagnosing defect of primary device, electronic device and storage medium | |
| CN115650006B (en) | Elevator safety monitoring and early warning method and system based on big data | |
| CN114510994A (en) | Training method and device for urban underground gas leakage recognition model | |
| CN113515560A (en) | Vehicle fault analysis method and device, electronic equipment and storage medium | |
| He et al. | Probabilistic model based algorithms for prognostics | |
| Dui et al. | Reliability Evaluation and Prediction Method with Small Samples. | |
| Qian et al. | A diagnosis method for diesel engine wear fault based on grey rough set and SOM neural network | |
| CN116974265B (en) | Underground mine car fault diagnosis method and system under no-signal scene | |
| CN114279704B (en) | Method and system for monitoring planet-level running state of wind power gear box |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |