CN113379223A - Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model - Google Patents

Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model Download PDF

Info

Publication number
CN113379223A
CN113379223A CN202110625084.8A CN202110625084A CN113379223A CN 113379223 A CN113379223 A CN 113379223A CN 202110625084 A CN202110625084 A CN 202110625084A CN 113379223 A CN113379223 A CN 113379223A
Authority
CN
China
Prior art keywords
host
spare part
fault
state
ship
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.)
Withdrawn
Application number
CN202110625084.8A
Other languages
Chinese (zh)
Inventor
景旭文
陈冶
周宏根
康超
刘金锋
李炳强
陈宇
叶双
郑海南
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University of Science and Technology
Original Assignee
Jiangsu University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University of Science and Technology filed Critical Jiangsu University of Science and Technology
Priority to CN202110625084.8A priority Critical patent/CN113379223A/en
Publication of CN113379223A publication Critical patent/CN113379223A/en
Withdrawn legal-status Critical Current

Links

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • 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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or 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
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • 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
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Marketing (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Computer Hardware Design (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Evolutionary Biology (AREA)

Abstract

The invention discloses a fault association model-based ship host and ship spare part multi-level configuration method, which comprises the following steps: acquiring dynamic perception information and static historical data information representing the state of a ship host, and then constructing a host state parameter database; carrying out abnormity judgment on data information representing the state of the host to obtain a corresponding component of abnormal state data, realizing service life prediction of the component corresponding to the abnormal state data based on a service life prediction model, and carrying out spare part evaluation judgment; analyzing the feasibility of the associated spare parts through the associated state matrix, the fault association model and the associated spare part service life prediction model; and taking the maintenance cost as a constraint, carrying out shipboard configuration judgment on the main-associated spare parts, and obtaining a spare part list. Compared with the prior art, the method has the advantages that the fault association factors are considered in the prediction of the ship main engine and the ship spare parts, the guarantee rate of the ship main engine spare parts can be effectively improved, the navigation risk is reduced, and meanwhile the investment cost of the spare parts can be reduced.

Description

Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model
Technical Field
The invention relates to the field of ship main engine spare part configuration, in particular to a fault association model-based ship main engine spare part multi-level configuration method.
Background
In the process of ship navigation, the guarantee of the spare parts of the ship main engine is a necessary guarantee that the main engine can normally run. Too early or too many spare parts can result in long-term use of the enterprise's capital and increased costs for navigation. However, the spare parts are not fully configured, so that the navigation is possibly risky, and the navigation task cannot be completed smoothly and timely. Therefore, reasonable arrangement of the main engine of the ship and spare parts of the ship is an important guarantee for smoothly completing the navigation task.
Zhang Xinhui et al optimizes a maintenance and spare part ordering combined strategy based on the remaining life prediction, predicts the remaining service life by using the equipment health state information, and makes maintenance and spare part ordering decisions to achieve the purpose of reducing the equipment maintenance cost and the spare part cost. The Liu Chong Yang and the like consider three maintenance effects of 'repairing if new', 'repairing if old' and 'incomplete repairing' of the repairable unit, apply a reliability theory and a random process method by taking the failure rate and the maintenance cost of the unit as constraint conditions, and establish a repairable spare part consumption prediction model on the basis of calculating the average service time of different service stages of the spare part. Chinese patent application 202010692410.2 discloses a system for predicting the demand of spare parts of equipment based on fault prediction and health management, which comprises: the data acquisition and edge calculation module acquires data by using edge equipment and extracts features required by modeling by analyzing and calculating the data; the data service module is used for uniformly managing data assets of the field equipment and the system and providing data support for the intelligent analysis model; the intelligent analysis module is used for carrying out signal processing and characteristic processing on the acquired data and carrying out health assessment according to the processed signal data; and the visual application module is used for visually displaying the results of the fault prediction and the health assessment.
The existing spare part prediction technology is mainly focused on the state change of equipment or parts, and the spare part is replaced according to a one-to-one principle, namely, the problem that a host machine fails is solved by replacing the spare part once, no related failure occurs, and no domino effect exists. However, in actual operation, the related failure of the host is still ubiquitous.
Therefore, a new technical solution is needed to solve this problem.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects in the prior art, the ship host spare part-associated multi-level configuration method based on the fault association model is provided, the fault association factors are considered in the prediction of the ship host spare part, and the guarantee rate of the ship host spare part can be effectively improved.
The technical scheme is as follows: in order to achieve the above object, the present invention provides a multi-level configuration method of a ship main engine and a ship spare part based on a fault correlation model, comprising the following steps:
s1: acquiring dynamic perception information and static historical data information representing the state of a ship host, and then constructing a host state parameter database;
s2: carrying out abnormity judgment on data information representing the state of the host to obtain a corresponding component of abnormal state data, realizing service life prediction of the component corresponding to the abnormal state data based on a service life prediction model, and carrying out spare part evaluation judgment;
s3: analyzing the feasibility of the associated spare parts through the associated state matrix, the fault association model and the associated spare part service life prediction model;
s4: and taking the maintenance cost as a constraint, carrying out shipboard configuration judgment on the main-associated spare parts, and obtaining a spare part list.
Further, the dynamic sensing information in step S1 is real-time data detected by a sensor mounted on the marine main engine equipment, and mainly includes information such as pressure, temperature, position, noise, and the like, and the sensor mainly includes a pressure sensor, a temperature sensor, a crankshaft position sensor, a camshaft position sensor, a piston rod position sensor, a noise sensor, and the like;
the static historical data information is historical data information of daily inspection of the marine main engine, and mainly comprises diesel engine appearance inspection, diesel oil supply system inspection, lubricating system inspection, cooling system inspection, starting and operating system inspection, turning inspection, failure evaluation related information and the like.
Further, the host status parameter database in step S1 includes historical operating status parameters of the host, historical data of routine inspection of the host, historical maintenance data, basic parameters of the host, early warning values and fault values of fault modes and corresponding status parameters, and data generated during life prediction.
Further, in the step S1, the warning value and the fault value are obtained by learning the historical maintenance record and the historical host operating state parameter through an intelligent algorithm.
Further, in step S2, after normalization processing is performed on the data information representing the host status, abnormality determination is performed, and the normalization processing is used to reduce the cost of data transmission, storage and subsequent data processing.
Further, the method for acquiring the corresponding component of the abnormal state data in step S2 is as follows: judging the abnormality of the data information representing the state of the host, and if the data is abnormal, judging an abnormal component by combining a host state parameter database; the abnormal component is judged by combining the host state parameter database, the state parameters of the host are compared with the state parameter early warning values in the host state parameter database in real time, and when the fact that the real-time running state parameters of the host are within the range of the state parameter early warning values in the fault mode is detected, the abnormal component and the corresponding original fault code can be determined.
Further, the life prediction model in step S2 includes an empirical model, a theoretical model, or a numerical training model of the host status information.
Further, the method for evaluating and judging spare parts in step S2 includes: the main abnormal component carries out spare part evaluation, which comprises judging whether to carry out spare part on the abnormal component, namely judging whether the life prediction result of the abnormal component is smaller than a life threshold value g1If it is larger than the threshold value g1Spare parts are not carried out on the abnormal component, and if the value is less than the threshold value g1And performing spare part evaluation on the main abnormal component.
Further, the correlation state matrix in step S3 is used to describe the correlation states between the failure modes of the marine main engine, and if the total number of the failure modes is N, the correlation state matrix is,
Figure BDA0003100684370000031
in the formula, aijAs the degree of association of failure mode i with failure mode j, aij∈[0,1](ii) a For degree of correlation with primary failure modeAnd confirming the corresponding component by utilizing the host state database in the fault mode larger than the preset value k. The preset value k can be obtained by analyzing the host historical maintenance record and the spare part replacement record by utilizing grey correlation analysis.
The host fault association model is as follows:
Figure BDA0003100684370000032
in the formula, yiRepresenting a quantified degree of correlation of the correlated fault i with respect to the original fault; bi0，bi1，…，binRepresenting a regression coefficient; f. ofi1，fi2，…，finRepresents the measured point t1，t2，…，tnCollecting state parameters of data;
Figure BDA0003100684370000033
indicating the degree of correlation with the measured point tnAnd collecting a relation function of the state parameters extracted by the data.
Further, the feasibility analysis of the associated spare parts in step S3 specifically includes: and establishing a spare part judging standard through the established associated spare part service life prediction model, and determining whether the associated spare part carries out spare part or not by utilizing the fault association model and the associated spare part service life prediction model. Here, the associated spare part life prediction model is established in the same manner as the life prediction model in step S2, but the performance evaluation threshold is different from the main spare part threshold, and whether the spare part criterion is the same as in step S2 is determined.
Further, in the step S4, the maintainability assessment is performed on the main-associated spare parts with the maintenance cost as a constraint, and it is determined whether to perform on-board configuration. The maintenance cost includes direct cost of single maintenance, fixed cost of single maintenance, material cost of single maintenance, down time conversion cost required by maintenance, and the like, which are directly or indirectly related to the cost. The spare part cost includes the transportation and installation cost of the spare part, the purchase cost of the spare part and the like. And if the maintenance cost is larger than the spare part cost, selecting to carry out the spare part. And if the maintenance cost is less than the spare part cost, performing maintenance.
Has the advantages that: compared with the prior art, the method has the advantages that the fault association factors are effectively considered in the prediction of the ship main engine and the ship spare parts through the application of technical means such as abnormity judgment, the association state matrix, the fault association model, the associated spare part service life prediction model and the like, the technical defects of the existing method are overcome, the guarantee rate of the ship main engine spare parts can be effectively improved, and the investment cost of the spare parts can be reduced while the navigation risk is reduced.
Drawings
FIG. 1 is a level diagram of a method for multi-level configuration of marine host machines with marine spare parts;
FIG. 2 is a flow chart of a method for multi-level configuration of marine main engines with marine spare parts;
FIG. 3 is a graph of exhaust manifold temperature predictions;
FIG. 4 is a graph showing the predicted inlet temperature of the lubricant.
Detailed Description
The present invention is further illustrated by the following figures and specific examples, which are to be understood as illustrative only and not as limiting the scope of the invention, which is to be given the full breadth of the appended claims and any and all equivalent modifications thereof which may occur to those skilled in the art upon reading the present specification.
The invention provides a ship main engine spare part multi-level configuration method based on a fault correlation characteristic model, which comprises three levels as shown in figure 1.
The first level is a main and standby device fault judgment layer, and comprises data sensing and preprocessing, establishment of a host state parameter database, confirmation of a main abnormal component and life prediction.
And the second level is a related spare part fault judging layer which comprises a fault related model and a related fault spare part service life prediction.
And the third level is a spare part decision level, and the maintainability evaluation is carried out on the main-associated spare parts confirmed by the first two levels, and a spare part list suggestion is given.
In this embodiment, taking a 10000DWT bulk carrier host of a certain model as an example, effective configuration of parts can be found and judged in time by the multi-level master-associated spare part information association, a specific flow is shown in fig. 2, and the specific implementation of the multi-level configuration method includes the following steps:
(1) and acquiring dynamic perception information and static historical data information representing the state of the ship host, and then constructing a host state parameter database.
Firstly, a host state sensing system is established, and host running state parameters are obtained. The sensor of the host state perception system mainly comprises a pressure sensor, a temperature sensor, a crankshaft position sensor, a camshaft position sensor, a piston rod position sensor, an acoustic wave sensor and the like.
Secondly, after the host status sensing system is constructed, a host status database is established, and the host status database stores historical operating status parameters of the host, historical data information of daily inspection of the host, historical maintenance data, basic parameters of the host, and early warning values and fault values of the status parameters corresponding to the fault modes. The state parameter early warning value and the fault value corresponding to the fault mode are obtained by a deep neural network method based on historical sample information. And inputting historical fault records and corresponding host state parameters, and learning data by using a deep neural network algorithm to finally obtain early warning values and fault values of the state parameters corresponding to the fault modes.
The historical data information of daily inspection of the marine main engine mainly comprises diesel engine appearance inspection, diesel oil supply system inspection, lubricating system inspection, cooling system inspection, starting and operating system inspection, turning inspection and fire fighting facility inspection.
(2) And realizing the life prediction of the component corresponding to the abnormal state data based on the life prediction model, and carrying out the evaluation and judgment of the spare parts.
The data information which is sensed by the sensor and represents the state of the host is preprocessed, namely, the sensed data is normalized, so that the cost of data transmission, storage and subsequent data processing is reduced. The normalization method is as follows,
Figure BDA0003100684370000051
in the formula, X*The normalized state parameter of the host is x, min and max, wherein x is the acquired original data, min is the minimum value of the original data, and max is the maximum value of the original data.
Table 1 shows the results of the normalization process of the partial host status parameters.
TABLE 1
Figure BDA0003100684370000052
And comparing the state parameters of the host with the state parameter early warning values in the host state parameter database in real time, and determining the main abnormal component and the corresponding original fault code when detecting that the real-time running state parameters of the host are within the fault mode state parameter early warning value range.
For the life prediction model, a Support Vector Machine (SVM) is used to train the samples (x)i，yi) Performing learning, wherein xiAs a component historical state parameter, xi∈RnAs an input variable, yiAnd the residual life of the component corresponding to the historical state parameters of the component is used as an output variable. i is 1,2,3, …, m is the number of samples.
The regression function is:
f(x)＝<ω.x>+b
in the formula, ω ∈ RnFor weight vectors, b ∈ R is the deviation. The weight ω and the deviation b can be solved by the following equations.
Figure BDA0003100684370000061
Wherein C is a penalty factor xii，ξi *Is a relaxation factor and epsilon is a sensitive factor. In this example, C is 597.9, and ε is 0.5.
The nonlinear regression problem is converted into a linear problem by utilizing a kernel function for solving, wherein the commonly used kernel functions are Gaussian RBF kernel functions and Poly kernel functions.
The present example employs a Gauss radial basis kernel function.
Linear regression function:
Figure BDA0003100684370000062
in the formula, alphai，αi *Is a lagrange function multiplier.
If the calculated residual life of the main abnormal component is greater than the threshold value g1If so, spare parts are not carried out on the component; if less than threshold value g1Then a serviceability evaluation is performed on the component.
Fig. 3 shows the result of learning and predicting abnormal data by using SVM.
According to the prediction result, the temperature of the exhaust main pipe of the main engine reaches the parameter early warning value after the main engine runs for 467 hours, the system calls the service life prediction model to predict the temperature of the exhaust main pipe, and the prediction result shows that the exhaust main pipe reaches the fault value after the main engine runs for 536 hours. And (3) according to the host state parameter database constructed in the step (1), the overhigh temperature of the exhaust manifold is caused by the failure of the supercharger. I.e., the remaining effective operating time of the supercharger is 69 hours, less than the threshold g1, and a serviceability assessment of the component is required.
(3) And analyzing the feasibility of the associated spare parts through the associated state matrix, the fault association model and the associated spare part service life prediction model.
The matrix A is used for describing the correlation state between the fault modes of the ship main engine, and the total number of the fault modes is N.
Figure BDA0003100684370000071
In the formula, aijThe degree of correlation of failure mode i with respect to failure mode j. a isij∈[0,1]
The fault association model is as follows:
Figure BDA0003100684370000072
in the formula, yiRepresenting a quantified degree of correlation of the correlated fault i with respect to the original fault; bi0，bi1，…，binRepresenting a regression coefficient; f. ofi1，fi2，…，finRepresents the measured point t1，t2，…，tnCollecting state parameters of data;
Figure BDA0003100684370000073
indicating the degree of correlation with the measured point tnAnd collecting a relation function of the state parameters extracted by the data.
Solving the correlation model, taking m groups of host running state parameters to form a training sample, wherein an observed value vector matrix is B:
Figure BDA0003100684370000074
in the formula: m is the number of training samples; n is the number of data acquisition points;
Figure BDA0003100684370000075
relating the fault degree to the measuring point tnAnd collecting a relation function of the state indexes extracted by the data.
Correlation degree model parameter C:
C＝(BTB)-1BTY
wherein A is an observed value vector matrix; and Y is a real fault association degree vector corresponding to the training sample.
The correlation state among the fault modes in the sample to be tested is as follows:
A＝B1C
in the formula B1An observed value vector matrix corresponding to a data sample to be evaluated; c is a fault correlation degree model parameter; and A is the correlation state between the fault modes in the sample to be tested.
And comparing the calculated association degree with a preset value k, and if the association degree is greater than the preset value k, predicting the service life of the component corresponding to the association fault mode. And if the current value is less than the preset value k, not predicting the service life of the battery. The preset value k can use grey correlation analysis to discuss the host history maintenance record and the spare part replacement record to determine the preset value of the correlation degree.
In this embodiment, N is 4, and the failure modes are a supercharger failure, a governor failure, an injection pump failure, and a lube pump failure, respectively. The number n of the measuring points is 4, and the value of k is 0.3.
While taking into account the measuring point fi1，fi2，fi3，fi4The 2 nd order polynomial correlation model is:
Figure BDA0003100684370000076
the failure mode associated state matrix calculation results are as follows:
Figure BDA0003100684370000081
the fault mode correlation state matrix A can be obtained, and the correlation degree between the main fault mode and the fault of the lubricating oil pump is larger than the preset value of 0.3, so that the feeding temperature of the lubricating oil is predicted.
And (4) predicting the service life of the related component obtained by calculation by using the service life prediction model in the step (3), and if the residual service life of the related component obtained by calculation is larger than a threshold value g2If so, spare parts are not carried out on the component; if less than threshold value g2Then a serviceability evaluation is performed on the component.
The prediction result is shown in FIG. 4, and the residual effective working time of the component is greater than the threshold value g2So that no serviceability evaluation of the member is required.
(4) And taking the maintenance cost as a constraint, carrying out shipboard configuration judgment on the main-associated spare parts, and obtaining a spare part list.
And (4) evaluating the main-associated spare parts by taking the maintenance cost as a constraint to judge whether the on-board configuration is carried out. And if the maintenance cost is larger than the spare part cost, selecting to carry out the spare part. And if the maintenance cost is less than the spare part cost, performing maintenance. The part maintenance cost specifically is:
C1＝Kh+Cf+Cm+Cg
in the formula, C1、Kh、Cf、Cm、CgRepresenting the total planned maintenance cost, the direct cost of a single maintenance, the fixed cost of a single maintenance, the material cost of a single maintenance, and the down time converted cost required for maintenance, respectively. The direct maintenance cost is the product of planned maintenance man-hour (h) and average man-hour rate (p), the fixed cost is the comprehensive value of maintenance tool use, aviation material depreciation cost, dispatching transportation management cost and the like, and the material cost is determined by maintenance projects and is independent of specific maintenance strategies and task combination modes.
The spare part cost specifically is:
C2＝M0+K1
in the formula, C2For the total cost of spare parts, M0For transporting and installing spare parts, K1The purchase cost of spare parts.
Comparison C1And C2It is determined whether to spare the component, and a spare part list is available.
This embodiment calculates the maintenance and spare part cost of booster:
C164 × 80+40000+21000+55400 ═ 121520 (unit: yuan)
C220000+94000 as 114000 (unit: yuan)
By comparison, the maintenance cost C of the supercharger1Greater than spare part cost C2Therefore, the result of the calculation is to prepare the supercharger.

Claims (10)

1. A ship host computer and ship spare part multi-level configuration method based on a fault correlation model is characterized by comprising the following steps:
s1: acquiring dynamic perception information and static historical data information representing the state of a ship host, and then constructing a host state parameter database;
s2: carrying out abnormity judgment on data information representing the state of the host to obtain a corresponding component of abnormal state data, realizing service life prediction of the component corresponding to the abnormal state data based on a service life prediction model, and carrying out spare part evaluation judgment;
s3: analyzing the feasibility of the associated spare parts through the associated state matrix, the fault association model and the associated spare part service life prediction model;
s4: and taking the maintenance cost as a constraint, carrying out shipboard configuration judgment on the main-associated spare parts, and obtaining a spare part list.
2. The method for the multi-level configuration of the marine main engine and the marine spare part based on the fault correlation model as claimed in claim 1, wherein the dynamic sensing information in the step S1 is real-time data detected by a sensor installed on the marine main engine equipment; the static historical data information is historical data information of daily inspection of the ship host.
3. The method as claimed in claim 1, wherein the database of host status parameters in step S1 includes historical operating status parameters of the host, historical data of routine inspection of the host, historical maintenance data, basic parameters of the host, early warning values and fault values of fault modes and corresponding status parameters, and data generated during life prediction.
4. The method as claimed in claim 3, wherein the early warning value and the fault value in step S1 are obtained by learning the historical maintenance record and the historical host operating state parameters through an intelligent algorithm.
5. The method as claimed in claim 1, wherein the step S2 is performed by normalizing data information for representing the state of the main engine and then performing anomaly determination.
6. The method for the multi-level configuration of the marine main engine and the marine spare parts based on the fault correlation model as claimed in claim 1, wherein the method for acquiring the corresponding component of the abnormal state data in the step S2 comprises: judging the abnormality of the data information representing the state of the host, and if the data is abnormal, judging an abnormal component by combining a host state parameter database; the abnormal component is judged by combining the host state parameter database, the state parameters of the host are compared with the state parameter early warning values in the host state parameter database in real time, and when the fact that the real-time running state parameters of the host are within the range of the state parameter early warning values in the fault mode is detected, the abnormal component and the corresponding original fault code can be determined.
7. The method for the multi-level configuration of the marine main engine and the marine spare parts based on the fault correlation model as claimed in claim 1, wherein the life prediction model in the step S2 comprises an empirical model, a theoretical model or a numerical training model of the state information of the main engine.
8. The method for the multi-level configuration of the ship main engine and the ship spare parts based on the fault correlation model as claimed in claim 1, wherein the method for the spare part evaluation and judgment in the step S2 is as follows: the main abnormal component carries out spare part evaluation, which comprises judging whether to carry out spare part on the abnormal component, namely judging whether the life prediction result of the abnormal component is smaller than a life threshold value g1If it is larger than the threshold value g1Spare parts are not carried out on the abnormal component, and if the value is less than the threshold value g1And performing spare part evaluation on the main abnormal component.
9. The method as claimed in claim 1, wherein the correlation matrix in step S3 is used to describe the correlation between the failure modes of the marine main engine, and if the total number of failure modes is N, the correlation matrix is,
Figure FDA0003100684360000021
in the formula, aijAs the degree of association of failure mode i with failure mode j, aij∈[0,1]；
The host fault association model is as follows:
Figure FDA0003100684360000022
in the formula, yiRepresenting a quantified degree of correlation of the correlated fault i with respect to the original fault; bi0，bi1，…，binRepresenting a regression coefficient; f. ofi1，fi2，…，finRepresents the measured point t1，t2，…，tnCollecting state parameters of data;
Figure FDA0003100684360000023
indicating the degree of correlation with the measured point tnAnd collecting a relation function of the state parameters extracted by the data.
10. The method according to claim 1, wherein the feasibility analysis of the associated spare parts in step S3 is specifically as follows: and establishing a spare part judging standard through the established associated spare part service life prediction model, and determining whether the associated spare part carries out spare part or not by utilizing the fault association model and the associated spare part service life prediction model.
CN202110625084.8A 2021-06-04 2021-06-04 Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model Withdrawn CN113379223A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110625084.8A CN113379223A (en) 2021-06-04 2021-06-04 Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110625084.8A CN113379223A (en) 2021-06-04 2021-06-04 Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model

Publications (1)

Publication Number Publication Date
CN113379223A true CN113379223A (en) 2021-09-10

Family

ID=77575818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110625084.8A Withdrawn CN113379223A (en) 2021-06-04 2021-06-04 Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model

Country Status (1)

Country Link
CN (1) CN113379223A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115828771A (en) * 2023-02-13 2023-03-21 深圳市仕瑞达自动化设备有限公司 Performance evaluation method, system and medium of mechanical transmission element
CN115994734A (en) * 2023-03-14 2023-04-21 百福工业缝纫机（张家港）有限公司 Production equipment maintenance part inventory management method and system
CN116976865A (en) * 2023-09-22 2023-10-31 中国船舶集团有限公司第七一九研究所 Ship maintenance device allocation management system based on big data analysis

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006327361A (en) * 2005-05-25 2006-12-07 Ihi Marine United Inc System, method and program for diagnosis and maintenance of ship
JP2008033908A (en) * 2006-06-30 2008-02-14 Hokyu System Service:Kk Maintenance supply system
KR101701278B1 (en) * 2015-09-11 2017-02-13 대우조선해양 주식회사 Remote inspection and maintenance system of ship and offshore plant
CN207008832U (en) * 2017-06-28 2018-02-13 广州鑫摩克船舶工程有限公司 A kind of marine main engine warning system
CN108062586A (en) * 2017-11-30 2018-05-22 中国船舶工业系统工程研究院 Marine main engine associated member state monitoring method and system based on decline contribution degree
CN108873859A (en) * 2018-05-31 2018-11-23 浙江工业大学 Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule
CN109932184A (en) * 2019-03-20 2019-06-25 杭州电子科技大学 Marine diesel inordinate wear diagnostic method based on union reliability rule-based reasoning
CN110334844A (en) * 2019-04-23 2019-10-15 武汉理工大学 Utilize the ship optimized use method of the main promotion diesel engine operating status of ship
CN110544038A (en) * 2019-09-05 2019-12-06 大连海事大学 intelligent operation and maintenance method and system for ship equipment
CN110738331A (en) * 2019-09-19 2020-01-31 智慧航海（青岛）科技有限公司 intelligent marine engine room system
CN110816781A (en) * 2019-11-07 2020-02-21 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） Ship running state identification method and device
CN111289256A (en) * 2018-12-07 2020-06-16 北京大学 Data-driven marine diesel engine fault detection method
AU2020101535A4 (en) * 2020-07-28 2020-09-03 Guangdong Ocean University Fault Diagnosis Method for Ship Power System Based on Integrated Learning

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006327361A (en) * 2005-05-25 2006-12-07 Ihi Marine United Inc System, method and program for diagnosis and maintenance of ship
JP2008033908A (en) * 2006-06-30 2008-02-14 Hokyu System Service:Kk Maintenance supply system
KR101701278B1 (en) * 2015-09-11 2017-02-13 대우조선해양 주식회사 Remote inspection and maintenance system of ship and offshore plant
CN207008832U (en) * 2017-06-28 2018-02-13 广州鑫摩克船舶工程有限公司 A kind of marine main engine warning system
CN108062586A (en) * 2017-11-30 2018-05-22 中国船舶工业系统工程研究院 Marine main engine associated member state monitoring method and system based on decline contribution degree
CN108873859A (en) * 2018-05-31 2018-11-23 浙江工业大学 Based on the bridge-type grab ship unloader fault prediction model method for improving correlation rule
CN111289256A (en) * 2018-12-07 2020-06-16 北京大学 Data-driven marine diesel engine fault detection method
CN109932184A (en) * 2019-03-20 2019-06-25 杭州电子科技大学 Marine diesel inordinate wear diagnostic method based on union reliability rule-based reasoning
CN110334844A (en) * 2019-04-23 2019-10-15 武汉理工大学 Utilize the ship optimized use method of the main promotion diesel engine operating status of ship
CN110544038A (en) * 2019-09-05 2019-12-06 大连海事大学 intelligent operation and maintenance method and system for ship equipment
CN110738331A (en) * 2019-09-19 2020-01-31 智慧航海（青岛）科技有限公司 intelligent marine engine room system
CN110816781A (en) * 2019-11-07 2020-02-21 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） Ship running state identification method and device
AU2020101535A4 (en) * 2020-07-28 2020-09-03 Guangdong Ocean University Fault Diagnosis Method for Ship Power System Based on Integrated Learning

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
杜林明;刘光涛;: "RCM和PHM混合故障诊断分析方法在机车远程运维的应用", 中国高新科技, no. 07 *
王彭;张克正;: "基于神经网络及光谱分析的船舶主机磨损状态研究", 科技创新与应用, no. 02 *
许小伟;范世东;姚玉南;: "On-line SVM在船舶设备故障预测中的应用", 武汉理工大学学报, no. 09 *
贾书丽;罗昊;杨青;: "无人船舶综合电力系统健康管理技术", 中国造船, no. 1 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115828771A (en) * 2023-02-13 2023-03-21 深圳市仕瑞达自动化设备有限公司 Performance evaluation method, system and medium of mechanical transmission element
CN115994734A (en) * 2023-03-14 2023-04-21 百福工业缝纫机（张家港）有限公司 Production equipment maintenance part inventory management method and system
CN115994734B (en) * 2023-03-14 2024-01-30 百福工业缝纫机（张家港）有限公司 Production equipment maintenance part inventory management method and system
CN116976865A (en) * 2023-09-22 2023-10-31 中国船舶集团有限公司第七一九研究所 Ship maintenance device allocation management system based on big data analysis
CN116976865B (en) * 2023-09-22 2023-12-19 中国船舶集团有限公司第七一九研究所 Ship maintenance device allocation management system based on big data analysis

Similar Documents

Publication Publication Date Title
CN113379223A (en) Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model
Lazakis et al. Predicting ship machinery system condition through analytical reliability tools and artificial neural networks
Mann et al. Statistical‐based or condition‐based preventive maintenance?
Lazakis et al. Advanced ship systems condition monitoring for enhanced inspection, maintenance and decision making in ship operations
Tinga et al. Physical model-based prognostics and health monitoring to enable predictive maintenance
US7457785B1 (en) Method and apparatus to predict the remaining service life of an operating system
Diez-Olivan et al. Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score
US20070244841A1 (en) Method and Apparatus for Data Processing, and Method and Apparatus for Diagnosis
Kobbacy et al. Condition-based maintenance modelling
KR102136141B1 (en) Emergency generator including function for fault prevention using artificial intelligence algorithm
Ochella et al. Adopting machine learning and condition monitoring PF curves in determining and prioritizing high-value assets for life extension
Raptodimos et al. Ship sensors data collection and analysis for condition monitoring of ship structures and machinery systems
Montgomery et al. Minor maintenance actions and their impact on diagnostic and prognostic CBM models
KR20220007641A (en) Analysis method and device therefor
Greitzer et al. Embedded prognostics health monitoring
Wang Key techniques in intelligent predictive maintenance (IPdM)–a framework of intelligent faults diagnosis and prognosis system (IFDaPS)
CN114048629A (en) Ship diesel engine health management and control system and management and control method
Dikis et al. Dynamic predictive reliability assessment of ship systems
Göksu et al. Prediction of ship main engine failures by artificial neural networks
Baker et al. Degrader analysis for diagnostic and predictive capabilities: a demonstration of progress in DoD CBM+ initiatives
Raptodimos et al. Collection and analysis of data for ship condition monitoring aiming at enhanced reliability & safety
Chen et al. BIM-and IoT-Based Data-Driven Decision Support System for Predictive Maintenance of Building Facilities
Tinga et al. Maintenance concepts
Ing et al. Approach for integrating condition monitoring information and forecasting methods to enhance spare parts supply chain planning
Morgan et al. Predicting future states with $ n $-dimensional Markov chains for fault diagnosis

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210910

WW01 Invention patent application withdrawn after publication