CN114565253A - Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model - Google Patents
Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model Download PDFInfo
- Publication number
- CN114565253A CN114565253A CN202210158716.9A CN202210158716A CN114565253A CN 114565253 A CN114565253 A CN 114565253A CN 202210158716 A CN202210158716 A CN 202210158716A CN 114565253 A CN114565253 A CN 114565253A
- Authority
- CN
- China
- Prior art keywords
- cloud
- risk
- evaluation
- weight
- index
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000005096 rolling process Methods 0.000 title claims abstract description 21
- 238000012502 risk assessment Methods 0.000 title claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 76
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000007726 management method Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007667 floating Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- OVBPIULPVIDEAO-LBPRGKRZSA-N folic acid Chemical compound C=1N=C2NC(N)=NC(=O)C2=NC=1CNC1=CC=C(C(=O)N[C@@H](CCC(O)=O)C(O)=O)C=C1 OVBPIULPVIDEAO-LBPRGKRZSA-N 0.000 claims description 2
- 238000001556 precipitation Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 239000010410 layer Substances 0.000 description 18
- 238000011160 research Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 8
- 239000008186 active pharmaceutical agent Substances 0.000 description 6
- 238000013278 delphi method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000006854 communication Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Radar, Positioning & Navigation (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Ocean & Marine Engineering (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a combined empowerment-cloud model-based cruise risk assessment method for a ro-ro passenger ship, aiming at risks possibly occurring in the course of cruise of the ro-passenger ship, on the basis of considering environment, ships, vehicles/goods, personnel and management factors, a system engineering theory and a game theory idea are introduced into a cruise risk assessment model for the ro-passenger ship, and a multi-factor cruise risk assessment model for the ro-passenger ship is established. The method comprehensively considers the influence of each factor on the navigation risk of the rolling vessel, constructs a rolling vessel navigation risk assessment index system, calculates the subjective and objective weights of each index by using an analytic hierarchy process and an entropy weight method, performs combined weighting through a game variable weight theory to obtain the comprehensive weight of each index factor, and then performs quantitative assessment on the comment set by using a cloud model. The navigation risk of the ro-ro passenger ship can be evaluated by applying the established model, the navigation adaptability is obtained, and reference and basis are provided for the operation of ro-passenger ship transportation enterprises and the supervision and management of relevant maritime departments.
Description
Technical Field
The invention belongs to the technical field of marine ship risk assessment, and particularly relates to a method for assessing the sailing risk of a ro-ro passenger ship based on a combined empowerment-cloud model.
Background
The transport of the ro-ro passenger is an important component of a comprehensive transportation system, the navigation safety of the ro-passenger has higher and higher attention, and the research on the navigation risk of the ro-passenger has important practical significance. The ro-ro passenger ship is different from a common ship, so that the number of cross lattice bulkheads in the ship is reduced to facilitate the entrance and exit of various vehicles, and the sinking resistance of the ship is weakened; the deck is often of a multilayer structure, so that the center of gravity of the ship is high, and the stability is relatively poor; the variety of ship carriers and ship-carrying vehicles is wide, and the ship carriers and the ship-carrying vehicles have different degrees of influence during the navigation. Therefore, a reasonable risk assessment method is established, risk factors in the carrying process of the ship are identified, the ship operation safety is guaranteed, and the method has great practical significance.
In the prior art, the security evaluation of the ro-ro passenger ship generally adopts the following method:
1) fuzzy mathematics: fuzzy mathematics is a new branch of mathematics that uses mathematical methods to study and deal with the phenomenon of ambiguity, based on the "fuzzy set" theory. Fuzzy mathematics provides a new method for dealing with the problems of uncertainty and inaccuracy, and is a powerful tool for describing human brain thinking and processing fuzzy information. It can be used in both "hard" and "soft" science. Fuzzy mathematics has many branches and is widely applied, such as fuzzy planning, fuzzy optimization design, fuzzy comprehensive evaluation, fuzzy cluster analysis, fuzzy sequencing and the like.
2) Analytic hierarchy process: the method is a systematic method which takes a complex multi-target decision problem as a system, decomposes a target into a plurality of targets or criteria, further decomposes the targets into a plurality of layers of multi-index (or criteria, constraint), and calculates the single-layer ordering (weight) and the total ordering of the layers by a qualitative index fuzzy quantization method to be taken as the target (multi-index) and multi-scheme optimization decision. The method is characterized in that on the basis of deep analysis of the essence, influence factors, internal relations and the like of a complex decision problem, the thinking process of decision is mathematized by using less quantitative information, so that a simple decision method is provided for the complex decision problem with multiple targets, multiple criteria or no structural characteristics, and the method is particularly suitable for occasions where the decision result is difficult to directly and accurately measure. The analytic hierarchy process is used for layering a complex decision-making system, and provides quantitative basis for analysis and decision-making by comparing the importance of various associated factors layer by layer.
3) Statistical analysis method: the statistical analysis method refers to research activities performed from the combination of quantification and qualification by using a statistical method and knowledge related to an analysis object, and realizes and reveals interrelations, change rules and development trends among things by analyzing and researching the quantitative relations of the research object such as scale, speed, range, degree and the like, so as to achieve correct explanation and prediction of the things.
4) Literature research methods: according to a certain research purpose or subject, documents are collected, identified and organized, and through the research on the documents, a method for grasping the problem to be researched is comprehensively and accurately known.
5) The Delphi method: the expert opinion method is a management technology which adopts a mode of issuing opinions anonymously according to a system program, namely team members cannot discuss with each other, do not have horizontal relation, only have relation with investigators, fill in questionnaires repeatedly, gather the consensus of the questionnaires and collect opinions of all parties, and can be used for constructing a team communication process and dealing with complex task problems.
Comprehensive security assessment (FSA) is commonly used abroad: in 1993, the concept of FSA was first proposed to be introduced into shipping circles by the International maritime organization in UK, and the introduction of FSA is proposed as a strategic idea, which is gradually applied to the establishment of safety regulations, the design of ships and the management of ship operation. At present, the FSA application guide in the process of establishing safety rules by IMO is passed, and countries are encouraged to actively develop test application to obtain experience so as to further improve the new method. The method comprises five steps of risk identification, risk assessment, risk control measure proposition, cost benefit assessment, decision suggestion proposition and the like. The method is to estimate the possibility of the occurrence of the accident before the accident occurs, systematically and comprehensively consider all aspects influencing the safety from the whole, thereby taking necessary safety measures, avoiding the occurrence of the accident or reducing the probability of the occurrence of the accident or lightening the consequences of the accident, and carrying out cost benefit evaluation on risk control measures, thereby providing scientific basis for making or modifying convention and rules. The Danish government submits SAFEDOR-completed safety assessment of the ro-ro passenger ships to IMO in 2008, and the security assessment of the ro-passenger ships applies an FSA method, carries out active exploration on the safety assessment of the ro-passenger ships, and provides suggestions for improving damage stability and survival capacity of the ro-passenger ships after water enters, sailing safety conditions, evacuation deployment, fire prevention and protection measures and the like. The method is not mature in China.
The security evaluation of the passenger roller boat or some link thereof is generally adopted in China: in China, the research mainly comprises qualitative evaluation and local evaluation, various scientific evaluation methods are adopted to carry out systematic evaluation research on the ro-ro passenger ship or a link related to the security of the ro-passenger ship, most of the quantitative research is to establish some indexes, and fuzzy evaluation is carried out on the security of the ro-passenger ship by directly quantifying or establishing a mathematical model, so that suggestion is provided. For example: the university of maritime work flood and Bilight professor rolling passenger ship operation safety evaluation adopts a basic risk analysis theory of safety system engineering and combines an accident rate statistical result to identify risk factors so as to evaluate the safety of the rolling passenger ship operation; the university of maritime affairs Master studies produce the research on the comprehensive safety evaluation of Bohai Bay of Yangshan to carry out risk identification on the major risk source of the ro-ro passenger ship from the longitudinal angle, and carry out comprehensive safety evaluation on the ro-passenger ship from the transverse angle by using methods such as fuzzy mathematics, event trees and the like; the university of Dalian aquatic works starts with the single roll-in passenger ship, comprehensively considers internal factors influencing the navigation safety of the ship and natural environment factors influencing the navigation, and pre-judges the safety degree of the roll-in passenger ship by using a comprehensive judgment method of fuzzy mathematics; other researches are as shown in the Profibonary of Chenlixiong Master, "research on weather sea conditions affecting navigation safety of Bohai sea ro-ro passenger roller vessels", the Wanxi master "evaluation on navigation safety of passenger roller vessels in Bohai sea area in severe weather", the Suchen master "research on navigation safety in Bohai sea gul passenger roller vessels in storm waves", the King master "evaluation and control research on passenger roller transport human factors", the Sun Shao Wei master "evaluation research on risk of Bohai gul passenger roller transport", and the King master "evaluation on passenger roller vessel operation risk based on BP neural network".
So far, the research field of the navigation risk of the ro-ro passenger ship is relatively short of operable quantitative processing methods, and the research plays a certain role in the navigation risk evaluation of the ro-ro passenger ship, but does not give consideration to the ambiguity and uncertainty contained in the risk evaluation problem, and does not avoid the influence of subjective factors as much as possible.
Disclosure of Invention
The invention aims to provide a method for evaluating the sailing risk of a ro-ro passenger ship based on a combined empowerment-cloud model, aiming at the problems in the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
a combined empowerment-cloud model-based cruise risk assessment method for a ro-ro passenger ship comprises the following steps:
s1, analyzing main influence factors of the navigation risk of the ro-ro passenger ship by combining the history navigation accident rule of the ro-passenger ship, and constructing an evaluation index system of the navigation risk of the ro-passenger ship;
s2, determining the comprehensive weight of the index system;
s3, constructing an evaluation cloud model based on the comprehensive weight;
and S4, evaluating the risk level of the ro-ro passenger ship according to the evaluation cloud model.
Specifically, in step S1, the index system includes 5 factor layers, which are respectively:
personnel factors including theoretical knowledge reserve, vessel operational skills, physiological factors, and psychological factors;
ship factors including age, speed, length, width and tonnage;
vehicle/cargo factors including vehicle self condition, vehicle tie-down, vehicle load and cargo physicochemical properties;
environmental factors including wind, precipitation, haze, wave height and tidal current;
and management factors including a safety management system and the operation condition thereof.
Further, the main influence factors of the sailing risk of the passenger rolling vessel are analyzed, and the specific method comprises the following steps:
screening out the most representative key indexes under each factor layer, wherein the quantitative standard of objective observation variables (wind speed, wave height, ship speed and the like) is investigated or directly measured, and subjective hidden variables are determined according to the properties of each variable according to the Delphi method, such as theoretical knowledge reserve level evaluation results, crew titles and certificates, past navigation records, energy detection results before navigation, body detection reports, psychological factor questionnaire survey conditions, vehicle conditions of vehicles in a ferry and the like, and establishing a maritime navigation risk assessment index system for passenger rolling ships according to the evaluation results.
Specifically, step S2 specifically includes the following steps:
s201, determining subjective weight of the index system by using an analytic hierarchy process;
s202, determining the objective weight of the index system by using an entropy weight method;
and S203, obtaining the comprehensive weight of the index system by using a game theory improved combined weighting method.
Further, in step S201, the method for determining the subjective weight of the index system includes:
constructing a multi-level structure of a risk element index system, and establishing a pairwise factor judgment matrix;
determining a maximum characteristic root λ of a deterministic matrixmaxAnd corresponding index weight w'jAnd carrying out consistency check;
when the consistency ratio CR is less than 0.1, the consistency check is passed; otherwise, the judgment matrix needs to be corrected and the steps are repeatedly executed until the consistency check is passed.
Further, in step S202, the method for determining the objective weight of the index system includes:
constructing an m multiplied by n dimensional data matrix;
carrying out standardization processing on data of each index in the index system, and converting an initial matrix into a standardized data matrix;
calculating the characteristic specific gravity p of each indexijAnd information entropy EijAnd further determining the objective weight value of each index.
Further, in step S203, the method for improving combined weighting by using the game theory includes:
assuming that the total number of risk evaluation indexes is n, p weight calculation methods are applied to obtain p basic weight vectors in total to form an initial game matrix wp×n；
Compute an arbitrary combination of p basis weight vectors:
in the formula: a isjGame configuration coefficients for jth basis weight vector, and ajGreater than 0; w is ajIs the jth basis weight vector; w is a game comprehensive weight vector of an index system;
according to an objective function of the improved game theory, an optimization model is established by combining corresponding constraint conditions:
solving the model by utilizing a Lagrange function to obtain a game configuration coefficient aj：
In the formula: w is aiIs the ith basis weight vector.
Specifically, step S3 specifically includes the following steps:
s301, constructing a standard evaluation cloud model;
the maritime navigation risk level of the ro-ro passenger ship is divided, and the comment set is divided into 5 levels: hp ═ H1, H2, H3, H4, H5 ═ low risk, general risk, high risk };
establishing a maritime navigation risk assessment standard cloud of the ro-ro passenger ship by adopting a model driving method based on golden ratio segmentation; let the domain be [ x ]min,xmax]＝[0,1]，He0Taking a value of 0.005, and respectively contrasting 5 evaluation grades in the comment set with 5 standard cloud models to obtain a standard evaluation cloud model of the golden section:
| grade | Ex，En，He |
| Low risk | (0，0.1031，0.013) |
| Lower risk | (0.309，0.064，0.008) |
| General risks | (0.5，0.039，0.005) |
| Higher risk | (0.691，0.064，0.008) |
| High risk | (1，0.1031，0.013) |
S302, generating a final evaluation cloud model;
calculating each index factor U according to the comprehensive cloud algorithmijThe comprehensive evaluation cloud:
Uijis Cij＝(Ex，En，He) Obtaining n bottom layer comprehensive evaluation clouds for the n bottom layer risk index factors;
aggregating the bottom risk index factors by adopting a floating cloud algorithm in the virtual cloud to form a cloud model of a factor layer:
in the formula: w is aiThe game comprehensive weight of each index factor is i ═ 1,2, …, n;
and (3) adopting a comprehensive cloud algorithm in the virtual cloud to aggregate a parent cloud with the highest concept, wherein the parent cloud can cover all domains of k child clouds, namely the final evaluation cloud of the criterion layer:
in the formula: in the formula: exTo finally evaluate the expectations of the cloud, ExiComprehensively evaluating the expectations of the cloud for each underlying layer, i ═ (1,2, …, n); enTo finally assess the entropy of the cloud, EniThe entropy of the cloud was evaluated comprehensively for each floor, i ═ (1,2, …, N); heFor final assessment of cloud hyper-entropy, HeiThe super entropy of the cloud is evaluated for each underlying synthesis, i ═ N (1,2, …, N). Expectation of ExRepresenting a point value which can represent a certain concept most in the number domain and represents the cloud gravity center of the cloud droplet cluster of the concept; entropy EnThe fuzzy characteristic and the probability of the concept are measured, and the correlation between the fuzziness and the randomness is reflected; hyper entropy HeTo characterize the entropy EnThe numerical value of the uncertainty of (2) can indirectly reflect the dispersion and thickness of the cloud layer.
Further, in step S4, performing cloud similarity analysis, comparing the final evaluation cloud of the obtained criterion layer with the evaluation standard cloud, performing cloud similarity analysis based on the maximum membership, and determining the risk level of the ship, specifically including the following steps:
s401, inputting a cloud model cloud1(Ex1，En1，He1) And cloud model cloud2(Ex2，En2，He2)；
S402, the two cloud models generate n cloud drops through cloud generators respectively, the number of the cloud drops of the two cloud models is set as n1 and n2, and the cloud drops are stored in sets of drop1 and drop 2;
s404, rearranging the cloud droplets according to the size sequence of the abscissa, and screening the cloud droplets falling on [ E ]x-3En,Ex+3En]Cloud droplets within range;
s406, if n1 is larger than or equal to n2, randomly discarding redundant cloud drops in drop1, and updating a drop1 set; otherwise, randomly discarding redundant cloud drops in drop2, and updating a drop2 set;
s407, the two sets are calculated according to the corresponding size order:
s408, outputting the cloud similarity AMMCM (c1, c2), and determining the risk level of the ship according to the cloud similarity.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the subjective and objective weights are determined by an analytic hierarchy process and an entropy weight method, the idea of improved game theory is used for combined weighting, then the evaluation is carried out by combining a cloud model, objective data and expert experience judgment are utilized, the fuzziness and randomness are effectively processed, meanwhile, the man-made interference of subjective consciousness is reduced, the subjective and objective unification is realized to a certain extent, meanwhile, the process is refined, the steps are clear, and the risk level can be more directly reflected. Therefore, the system can provide reference and basis for the operation of the ro-ro passenger transportation enterprises and the supervision and management of relevant maritime departments.
Drawings
FIG. 1 is a schematic diagram of an indicator system for evaluating a sailing risk of a ro-ro vessel with strait.
Fig. 2 is a schematic diagram comparing a human factor evaluation cloud and a standard cloud according to an embodiment of the present invention.
Fig. 3 is a schematic diagram comparing a ship factor evaluation cloud and a standard cloud according to an embodiment of the present invention.
Fig. 4 is a schematic diagram comparing a vehicle/cargo factor evaluation cloud with a standard cloud according to an embodiment of the present invention.
Fig. 5 is a schematic diagram illustrating comparison between the environment factor evaluation cloud and the standard cloud according to the embodiment of the present invention.
Fig. 6 is a schematic diagram illustrating comparison between a management factor evaluation cloud and a standard cloud according to an embodiment of the present invention.
FIG. 7 is a schematic diagram illustrating a result of evaluating a maritime navigation risk of a ro-ro passenger ship according to an embodiment of the present invention.
FIG. 8 is a diagram of a basic confidence triangular model in an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment provides a combined empowerment-cloud model-based cruise risk assessment method for a ro-ro passenger ship, and the embodiment takes a sailing example of the ro-ro passenger ship in the Johnson state as a case to assess the sailing risk of the ro-ro passenger ship; the method comprises the following specific steps:
in this embodiment, 10 ro-ro passenger ships on a route from 7-8 months old in 2020 to the new channel to the xu hong harbor are selected, ship voyage data and relevant weather information are collected, and averaging processing is performed. Simultaneously inviting professors and auxiliary professors in the field of 10 subjects; 7 front-line crew with the experience of rolling and passenger sailing; the management personnel (20 persons in total) of the relevant departments of the 3 strait shares company score the risk factors influencing the navigation of the ro-ro vessel by combining the actual situation of the jone state strait.
In the embodiment, the main influence factors of the navigation risk of the rolling passenger are analyzed by combining the historical navigation accident rule of the rolling passenger, and an evaluation index system of the navigation risk of the rolling passenger is established, as shown in figure 1;
calculating the comprehensive weight of each factor game
Firstly, collecting expert opinions according to a Delphi method for hierarchical analysis, constructing pairwise judgment matrixes in each layer, and determining subjective weight; then according to collected data of accidents of sailing of the Johnson state strait ro-ro-ro passenger rolling vessel from 2015 to 2019, processing to obtain the times of accidents caused by the fact that various evaluation indexes from 2015 to 2019 are key factors, and performing operation on the data matrix by using Matlab software to determine objective weight; obtaining a game configuration coefficient a according to an improved game theory formula1＝0.503，a20.497 according to the formula
Determining the maritime navigation risk index game comprehensive weight of the ro-ro passenger ship, which is shown in the following table 1:
TABLE 1 Game Integrated weights for Each index
Combined empowerment-cloud model comprehensive evaluation
And for the quantitative risk index, collecting and sorting data, then taking a mean value, unifying dimensions with qualitative evaluation values, and carrying out normalization processing. Meanwhile, for qualitative risk indexes, the qualitative risk indexes are scored secondarily by 20 questionnaire survey objects according to the actual situation of the Johnson channel, the qualitative risk indexes are given in the form of highest scores and lowest scores respectively, a maximum cloud model and a minimum cloud model of each index under each factor are generated through cloud model evaluation, and then a maximum and minimum cloud model is synthesized according to a formula, so that comprehensive evaluation clouds are obtained, as shown in the following table 2.
Table 2 comprehensive evaluation cloud of each risk index
And according to a floating cloud algorithm in the virtual cloud, aggregating the comprehensive evaluation clouds of the bottom-layer risk indexes to obtain a factor-layer evaluation cloud model, as shown in table 3. Respectively generating corresponding evaluation cloud pictures as shown in the figures 2-6, and then carrying out cloud similarity analysis, wherein the results are shown in the table 4;
TABLE 3 factor layer evaluation cloud model
Table 4 analysis results of cloud similarity for each factor
According to the figures 2-6 and in combination with the table 4, the risk levels of the various influencing factors of the rolling passenger ship navigation of the airline can be sequenced, namely: environmental factors > vehicle/cargo factors > personnel factors > ship factors > management factors. The management factors are at a lower risk level, because the management factors have lower comprehensive weight in a navigation system, and the research of Hainan harbor navigation and stock control company Limited shows that a reasonable system is made and good operation is maintained in the aspects of navigation safety idea education, emergency situation command and emergency facility distribution; personnel factors and ship factors are in a common risk level, and mainly because the age of most passenger-rolling ships of the air route is higher, carrying personnel relate to various drivers, passengers and workers, the number of the carrying personnel is large, personnel safety and literacy differentiation is obvious, and fine management is not easy to realize; the factors of the vehicle/goods and the environmental factors are at a higher risk level, and are important potential factors causing navigation safety accidents mainly because the vehicle conditions are difficult to realize comprehensive inspection under the condition of lacking necessary detection tools, the change of the physical and chemical properties of the vehicle and the loaded goods under the special navigation condition is difficult to perceive, and the factors of the vehicle/goods and the environmental factors have higher comprehensive weight.
The calculated and obtained criterion layer finally evaluates the cloud to be (0.548,0.052,0.006), namely the rolling passenger ship maritime navigation risk level of the new harbor to the xu hong harbor route in the Johnson State channel is a general risk, the rolling passenger ship navigation system in the environment is good in overall condition, but has a certain degree of potential safety hazard, and a targeted improvement needs to be carried out appropriately. The cloud chart is shown in fig. 7, and the cloud similarity analysis results are shown in table 5.
Table 5 final evaluation cloud similarity analysis results
Combined empowerment-cloud model evaluation effect verification
In order to illustrate the reasonability and applicability of evaluation by adopting a combined empowerment-cloud model in the rolling passenger ship navigation risk assessment, the same data source is used in the embodiment, and a Dempster-Shafer evidence theory model (namely DS evidence theory) is used for assessing the rolling passenger ship navigation risk of the route.
An evaluation set H is constructed according to the common evaluation grade classification criterion and the 'water traffic accident division standard' issued by the department of transportationp＝{H1，H2，H3，H4，H5And (4) quantifying the evaluation set by preference, wherein the evaluation set is dangerous, general, safe and safe, and is quantified as: p { H }j}＝{p{H1}，p{H2}，p{H3}，p{H4}，p{H5}}＝{-2，-1，0，1，2}。
Converting the scoring result into a percentile and substituting the percentile into a corresponding membership formula to obtain the safety membership value (H) of each factor in the systemi) The membership calculation formula is as follows:
in the formula: x is the number ofsThe safety value of each factor is obtained by the delphi method.
Then, a basic credibility triangular model is constructed by taking the safety membership as a high abscissa and the bottom side length as 1, as shown in FIG. 8, so that the credibility beta of each evaluation index of the evaluation set can be obtainedmn(Sij)。
Combining the comprehensive weight and the error coefficient lambda (taking the value of 0.9) to betamn(Sij) And correcting to obtain a mass value, and then sequentially performing evidence fusion on the mass values of the indexes according to the DS synthesis rule, wherein the results are shown in the following table 6:
TABLE 6 evaluation results of DS evidence theoretical model
| H1 | H2 | H3 | H4 | H5 | |
| Evaluation value | 0.0271 | 0.1473 | 0.2862 | 0.3745 | 0.1156 |
Therefore, the evaluation value of the DS evidence theoretical model is 0.3788, which shows that the overall safety state of the navigation system is between a general state and a safer state.
The evaluation results of the combined weight-cloud model and the DS evidence theoretical model are generally consistent and accord with the actual sailing situation of the ship with the air route through comparison, but the combined weight-cloud model effectively combines qualitative analysis and quantitative analysis, can visualize the evaluation results, more intuitively reflects the risk level of sailing of the passenger rolling ship, displays the uncertainty and the fuzziness contained in the problem by the scattered distribution situation of cloud droplets, has clear flow and definite steps, is complicated in the DS evidence theoretical model, and has larger influence on the evaluation results selected by different membership functions, so that the combined weight-cloud model is reasonable and effective in evaluating the sailing risk of the passenger rolling ship, and has more advantages compared with other common risk evaluation models.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A passenger rolling vessel navigation risk assessment method based on a combined empowerment-cloud model is characterized by comprising the following steps:
s1, analyzing main influence factors of the navigation risk of the ro-ro passenger ship by combining the history navigation accident rule of the ro-passenger ship, and constructing an evaluation index system of the navigation risk of the ro-passenger ship;
s2, determining the comprehensive weight of the index system;
s3, constructing an evaluation cloud model based on the comprehensive weight;
and S4, evaluating the risk level of the ro-ro passenger ship according to the evaluation cloud model.
2. The method according to claim 1, wherein in step S1, the index system comprises 5 factor layers, which are:
personnel factors including theoretical knowledge reserve, vessel operational skills, physiological factors, and psychological factors;
ship factors including age, speed, length, width and tonnage;
vehicle/cargo factors including vehicle self condition, vehicle tie-down, vehicle load and cargo physicochemical properties;
environmental factors including wind, precipitation, haze, wave height and tidal current;
and management factors including a safety management system and the operation condition thereof.
3. The method for assessing the sailing risk of the ro-ro passenger ship based on the combined empowerment-cloud model according to claim 1, wherein the step S2 specifically comprises the following steps:
s201, determining subjective weight of the index system by using an analytic hierarchy process;
s202, determining the objective weight of the index system by using an entropy weight method;
and S203, obtaining the comprehensive weight of the index system by using a game theory improved combined weighting method.
4. The method for assessing the sailing risk of a ro-ro passenger ship based on a combined weighted cloud model according to claim 3, wherein in step S201, the method for determining the subjective weight of the index system comprises:
constructing a multi-level structure of a risk element index system, and establishing a pairwise factor judgment matrix;
determining the maximum characteristic root of the judgment matrix and the corresponding index weight, and carrying out consistency check;
when the consistency ratio is less than 0.1, the consistency check is passed; otherwise, the judgment matrix needs to be corrected and the steps are repeatedly executed until the consistency check is passed.
5. The method for assessing the sailing risk of a ro-ro passenger ship based on a combined weighted-cloud model according to claim 3, wherein in step S202, the method for determining the objective weight of the index system comprises:
constructing an m multiplied by n dimensional data matrix;
carrying out standardization processing on data of each index in the index system, and converting an initial matrix into a standardized data matrix;
and calculating the characteristic specific gravity and the information entropy of each index, and further determining the objective weight value of each index.
6. The method for assessing the sailing risk of the ro-ro passenger ship based on the combined weight-cloud model of claim 3, wherein in the step S203, the method for improving the combined weight by using the game theory comprises:
assuming that the total number of risk evaluation indexes is n, p weight calculation methods are applied to obtain p basic weight vectors in total to form an initial game matrix wp×n；
Compute an arbitrary combination of p basis weight vectors:
in the formula: a isjGame configuration coefficients for jth basis weight vector, and ajGreater than 0; w is ajIs the jth basis weight vector; w is a game comprehensive weight vector of an index system;
according to an objective function of the improved game theory, an optimization model is established by combining corresponding constraint conditions:
solving the model by utilizing a Lagrange function to obtain a game configuration coefficient aj：
In the formula: w is aiIs the ith basis weight vector.
7. The method for assessing the sailing risk of the ro-ro passenger ship based on the combined empowerment-cloud model according to claim 1, wherein the step S3 specifically comprises the following steps:
s301, constructing a standard evaluation cloud model;
dividing the maritime navigation risk level of the ro-ro passenger ship, and dividing the comment set into 5 levels; establishing a maritime navigation risk assessment standard cloud of the ro-ro passenger ship by adopting a model driving method based on golden ratio segmentation; let the domain of discourse be [ x ]min，xmax]＝[0，1]，He0Taking a value of 0.005, and respectively contrasting 5 evaluation grades in the comment set with 5 standard cloud models to obtain a standard evaluation cloud model of the golden section;
s302, generating a final evaluation cloud model;
calculating each index factor U according to the comprehensive cloud algorithmijThe comprehensive evaluation cloud:
Uijis Cij＝(Ex，En，He) Obtaining n bottom layer comprehensive evaluation clouds for the n bottom layer risk index factors;
clustering the bottom risk index factors by adopting a floating cloud algorithm in the virtual cloud to form a cloud model of a factor layer:
in the formula: w is aiFor the game comprehensive weight of each index factor, i is (1,2, …, n);
and (3) adopting a comprehensive cloud algorithm in the virtual cloud to aggregate a parent cloud with the highest concept, wherein the parent cloud can cover all domains of k child clouds, namely the final evaluation cloud of the criterion layer:
in the formula: exTo finally evaluate the expectation of the cloud, ExiComprehensively evaluating the expectations of the cloud for each underlying layer, i ═ (1,2, …, n); enTo finally assess the entropy of the cloud, EniThe entropy of the cloud was evaluated comprehensively for each floor, i ═ (1,2, …, N); heFor final assessment of cloud hyper-entropy, HeiThe cloud's hyper-entropy, i ═ 1,2, …, N, was evaluated comprehensively for each underlying layer.
8. The method for assessing the sailing risk of the ro-ro passenger ship based on the combined weighted cloud model as claimed in claim 7, wherein in step S4, the obtained final assessment cloud of the criterion layer is compared with the assessment standard cloud, and the cloud similarity analysis is performed based on the principle that the membership degree is the maximum to determine the risk level of the ship, specifically comprising the following steps:
s401, inputting a cloud model cloud1(Ex1，En1，He1) And cloud model cloud2(Ex2，En2，He2)；
S402, the two cloud models generate n cloud drops through cloud generators respectively, the number of the cloud drops of the two cloud models is set as n1 and n2, and the cloud drops are stored in sets of drop1 and drop 2;
s404, rearranging the cloud droplets according to the size sequence of the abscissa, and screening the cloud droplets falling on [ E ]x-3En，Ex+3En]Cloud droplets within range;
s406, if n1 is larger than or equal to n2, randomly discarding redundant cloud drops in drop1, and updating a drop1 set; otherwise, randomly discarding redundant cloud drops in drop2, and updating a drop2 set;
s407, the two sets are calculated according to the corresponding size order:
s408, outputting the cloud similarity AMMCM (c1, c2), and determining the risk level of the ship according to the cloud similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158716.9A CN114565253A (en) | 2022-02-21 | 2022-02-21 | Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158716.9A CN114565253A (en) | 2022-02-21 | 2022-02-21 | Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114565253A true CN114565253A (en) | 2022-05-31 |
Family
ID=81713681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210158716.9A Pending CN114565253A (en) | 2022-02-21 | 2022-02-21 | Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114565253A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062935A (en) * | 2022-06-02 | 2022-09-16 | 华南理工大学 | Method for constructing hydrogen fuel cell automobile safety evaluation system |
| CN115239110A (en) * | 2022-07-14 | 2022-10-25 | 武汉理工大学 | Navigation risk evaluation method based on improved TOPSIS method |
| CN116664017A (en) * | 2023-07-28 | 2023-08-29 | 北京工业大学 | Rail transit public area aging adaptability evaluation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177172A (en) * | 2011-12-22 | 2013-06-26 | 中华人民共和国山东海事局 | Single vessel safety assessment method for roll on-roll off passenger ship |
| CN106951408A (en) * | 2017-03-17 | 2017-07-14 | 国信优易数据有限公司 | A kind of data digging method |
| CN111950918A (en) * | 2020-08-19 | 2020-11-17 | 江苏电力交易中心有限公司 | Market risk assessment method based on electric power transaction data |
-
2022
- 2022-02-21 CN CN202210158716.9A patent/CN114565253A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177172A (en) * | 2011-12-22 | 2013-06-26 | 中华人民共和国山东海事局 | Single vessel safety assessment method for roll on-roll off passenger ship |
| CN106951408A (en) * | 2017-03-17 | 2017-07-14 | 国信优易数据有限公司 | A kind of data digging method |
| CN111950918A (en) * | 2020-08-19 | 2020-11-17 | 江苏电力交易中心有限公司 | Market risk assessment method based on electric power transaction data |
Non-Patent Citations (1)
| Title |
|---|
| 孙星等: "基于云模型和熵权的青岛港邮轮航行安全评价", 《交通信息与安全》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062935A (en) * | 2022-06-02 | 2022-09-16 | 华南理工大学 | Method for constructing hydrogen fuel cell automobile safety evaluation system |
| CN115239110A (en) * | 2022-07-14 | 2022-10-25 | 武汉理工大学 | Navigation risk evaluation method based on improved TOPSIS method |
| CN116664017A (en) * | 2023-07-28 | 2023-08-29 | 北京工业大学 | Rail transit public area aging adaptability evaluation method and system |
| CN116664017B (en) * | 2023-07-28 | 2023-11-17 | 北京工业大学 | Rail transit public area aging adaptability evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114565253A (en) | Passenger-rolling ship navigation risk assessment method based on combined empowerment-cloud model | |
| Ung | Evaluation of human error contribution to oil tanker collision using fault tree analysis and modified fuzzy Bayesian Network based CREAM | |
| Akyuz | A hybrid accident analysis method to assess potential navigational contingencies: The case of ship grounding | |
| Wang et al. | Accident analysis model based on Bayesian Network and Evidential Reasoning approach | |
| Cakir et al. | An analysis of severity of oil spill caused by vessel accidents | |
| Silveira et al. | A multicriteria outranking approach for ship collision risk assessment | |
| Cao et al. | Analysis of factors affecting the severity of marine accidents using a data-driven Bayesian network | |
| CN105608548B (en) | A kind of automatic stowage method of bulk freighter safe load calculator | |
| Tran | Effect of ship loading on marine diesel engine fuel consumption for bulk carriers based on the fuzzy clustering method | |
| Decò et al. | Real-time risk of ship structures integrating structural health monitoring data: Application to multi-objective optimal ship routing | |
| CN111353222B (en) | Simulation test system and method for automatic berthing capability of intelligent ship | |
| Li et al. | AIS data-based decision model for navigation risk in sea areas | |
| CN102890875B (en) | Method for acquiring system collision risk of maritime intelligent transportation network | |
| Zhou | A comprehensive framework for assessing navigation risk and deploying maritime emergency resources in the South China Sea | |
| CN114662575A (en) | Wind power water area ship navigation risk estimation method and system and storage medium | |
| Vettor et al. | Reflecting the uncertainties of ensemble weather forecasts on the predictions of ship fuel consumption | |
| Hadi et al. | Achieving fuel efficiency of harbour craft vessel via combined time-series and classification machine learning model with operational data | |
| CN103177172B (en) | Single vessel safety assessment method for roll on-roll off passenger ship | |
| CN113011788A (en) | Emergency decision-making method for marine traffic accident, terminal equipment and storage medium | |
| Mentes et al. | Criticality analysis of probabilistic damage stability of ships with aggregation operators and additive ratio assessment | |
| CN110826891B (en) | Relative collision risk degree obtaining method based on ship cluster situation | |
| CN115239110A (en) | Navigation risk evaluation method based on improved TOPSIS method | |
| CN114254935A (en) | Method and system for estimating risk of cruise ship based on cloud model and entropy weight method | |
| Karaca et al. | Meteorological risk assessment based on fuzzy logic systems for maritime | |
| Gan et al. | Risk assessment for cruise ship navigation safety of inland waterway based on evidential reasoning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220531 |