CN108062586A - Marine main engine associated member state monitoring method and system based on decline contribution degree - Google Patents
Marine main engine associated member state monitoring method and system based on decline contribution degree Download PDFInfo
- Publication number
- CN108062586A CN108062586A CN201711235510.7A CN201711235510A CN108062586A CN 108062586 A CN108062586 A CN 108062586A CN 201711235510 A CN201711235510 A CN 201711235510A CN 108062586 A CN108062586 A CN 108062586A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- economy
- mover
- associated member
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Medicines Containing Antibodies Or Antigens For Use As Internal Diagnostic Agents (AREA)
Abstract
The present invention relates to a kind of marine main engine associated member state monitoring methods and system based on decline contribution degree, the method selects input data of the steady working condition data as off-line training in history health sample, builds host economic evaluation baseline and the economic sex-health baseline of associated member；Economy correlation monitoring data are obtained, using the host economic evaluation baseline on-line analysis host economy state of structure, when economy state is normal, are terminated；When economy abnormal state, abnormal alarm is sent, and carries out the analysis of host associated member health status；Obtain the health status result of each component and the order of each parts for maintenance investigation.This method and system are from the health status monitoring for being carried out at the same time host economy condition adjudgement and host associated member, to effectively instructing the maintaining of host and associated member, recover the economic performance of host, exclude associated member security risk or exception/fault and reduce fuel cost, great realistic meaning.
Description
Technical field
The present invention relates to marine main engine economic performance analysis and assessment field more particularly to a kind of ships based on decline contribution degree
Oceangoing ship host associated member state monitoring method and system.
Background technology
The ship means of transport larger as communications and transportation middle freight volume, the 40-60% in operation costs are fuel consumption,
Wherein, power " heart " of the marine main engine as ship, fuel consumption usually account for more than the 90% of full ship fuel consumption；With one
Exemplified by the wheel of ten thousand tons of ocean, the host fuel consumption of one day is often navigated by water up to ton more than 20-30, extreme influence the ship of shipping enterprise
Oceangoing ship operation cost, especially in the market environment of current shipping market continued downturn, how cost efficiency, become each shipping enterprise
The emphasis that industry user is concerned about；Meanwhile the discharge of fuel consumption and pollutant is closely related, excessive fuel consumption will necessarily cause
The increase of discharged nitrous oxides influences to transport the naval air environment in marine site.
Therefore, how to effectively control host fuel consumption cost, accurate evaluation host economic performance, control host fuel oils to disappear
Consumption discharge etc. becomes shipping user and is extremely concerned about simultaneously urgent problem to be solved at present.For marine main engine, economy shadow
The factor of sound is numerous, if it is possible to which being directly quickly obtained economic evaluation result, (i.e. whether host consumption is normal, whether meets economy
Service condition), and influencing factor, the abnormal associated components of positioning can be quickly found when economy is abnormal, provide reply
Measure, will recover host economic performance, exclusion economy and safety risks in time or exception/fault, reduction fuel oil disappear
Consume and save fuel cost, promoted the feature of environmental protection of host operation.
In current technology scheme, host associated member measured in real time according to vessel motion process, quantitative there is no
State monitoring method.
The content of the invention
In view of above-mentioned analysis, the present invention is intended to provide a kind of marine main engine associated member state based on decline contribution degree
Monitoring method and system can not carry out in fact the host associated member health status of vessel motion process to solve the prior art
When the problem of monitoring.
The purpose of the present invention is mainly achieved through the following technical solutions：
On the one hand, a kind of marine main engine associated member state monitoring method based on decline contribution degree is provided, including such as
Lower step：
Input data of the steady working condition data in history health sample as off-line training is selected, according in input data
Engine speed and fuel consumption rate measured value build host economic evaluation baseline, according to engine speed and economy association portion
Part state parameter builds economy associated member health baseline using SOM methods；
Data monitoring is carried out using multi-parameter monitoring system, using the host economic evaluation baseline of structure to monitoring data
Host economy state analysis is carried out, when economy state is normal, is terminated；When economy abnormal state, abnormal report is sent
It is alert, and carry out the analysis of host associated member health status；The host associated member health status analysis, including：Utilize economy
Property associated member health baseline monitoring data are analyzed, obtain host economy associated member decline it is different to host economy
Normal decline contribution degree；
Above-mentioned decline contribution degree is ranked up, the forward positioning parts that will sort are exceptional part, and carry out corresponding portion
The repair investigation of part.
On the basis of said program, the present invention has also made following improvement：
Further, the economy associated member includes cylinder system, cooling system and supercharger systems.
Further, the monitoring data be the data consistent with the input data type of off-line training, including engine speed,
Fuel consumption, cylinder system state parameter, the state parameter of cooling system state parameter and supercharger systems.
Further, structure economy associated member health baseline comprises the following steps：
Selection and the relevant each associated member system status parameters of economy build the economy association portion of n-th of sample
Part observation vectorInput vector of the complete or collected works as networkWherein,The even running process sampling timeframe for being ship in boatIn be used for SOM network trainings sampling when
Carve set, s (n) be rotating speed, x1(n),x2(n),…,xm(n) the m shapes with the relevant each associated member system of economy are represented
State parameter；
According to j-th of weight vectors W of input vectorj(n) complete or collected works' weight vectors W is obtainedj；Wherein,
K is the neuron of SOM network trainings
Number；
The Euclidean distance of input vector and weight vectors is calculated, the minimum point of distance is found, as best match node Wc；
UsingAdjust weight, complete or collected works' weight after being adjusted to
Amount；Wherein, t is iterative step, and α is learning rate,For with best match node WcCentered on winning neighborhood in j-th
Neuron and best match node WcBetween topology distance function；
The repetitive exercise of SOM networks is carried out, terminates to train when convergence, be closed trained SOM networks as economy
Join component health baseline.
Further, the step of testing trained SOM networks is further included, test is not by, then re -training, directly
It is tested to passing through.
Further, described the step of testing trained SOM networks, includes：
Using in even running process sampling timeframeIn be different fromSampling instant setAs test
Process time scope, in the economy associated member observation vector of n-th of sampled point
The corresponding input for inputting trained SOM networks to
Measuring complete or collected works is
The estimate of SOM networks output is obtained by trained SOM networksIt is closed in the economy of n-th of sampled point
Join component estimate vector：
Calculate the corresponding economy associated member health baseline offset vector of test data：
When economy associated member health baseline offset vector ΔtIn each parameter error average when being no more than threshold value,
Think to pass through test.
Further, host economy state point is carried out to online monitoring data using the host economic evaluation baseline of structure
Analysis, comprises the following steps：
According to the relevant two-dimensional observation vector of fuel economyFor identical rotating speed, combustion is calculated
The equal Valued Statistics of oily efficiency are derived from even running process sampling timeframeIt is interior, with the relevant fuel efficiency of rotating speed
Statistical valueWherein, nsFor the number of different rotating speeds value；
By observation vectorMiddle different tachometer value si, i=1 ..., nsInput host fuel-economy
Property assessment baseline, obtain corresponding host fuel economy assessment baseline estimations value
Calculate the deviation of input data corresponding host fuel economy assessment baseline
If all deviations are respectively less than threshold value, economy state is normal, terminates；
If the arbitrary value in deviation is more than threshold value, economy abnormal state carries out host associated member health status point
Analysis.
Further, online monitoring data is analyzed using economy associated member health baseline, obtains host economy
Property associated member decline to the decline contribution degree of the economic sexual abnormality of host, comprise the following steps：
Select even running process sampling timeframeThe interior and relevant each associated member system status parameters of economy,
Form the economy associated member observation vector of l-th of sampled point
Economy associated member health baseline input vector of the complete or collected works as SOM net structures
Each parameter is inputted after SOM networks in calculating observation vector to nearest best match node WcThe distance between
Value, is denoted as minimum quantization difference MQE；The minimum quantization difference of the economy associated member of l-th of sampled point is：
Each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values,
ByInterior average obtains the decline contribution degree of whole each component
Foregoing invention has the beneficial effect that：
Host economic evaluation has been carried out at the same time to analyze with associated member health status：Pass through the fuel consumption and fortune of host
Row state computation goes out the fuel consumption rate in ship actual moving process, directly evaluates the fuel economy of host；Find institute
Have with the relevant associated member of host economy, by the means of data-driven, calculate each economy associated member decline for
Thus the contribution degree of the economic sexual abnormality of host quantitatively obtains corresponding economic influence factor and influence degree, so as to effectively refer to
Repair investigation and the maintaining of host and associated member are led, for recovering the economic performance of host, excluding security risk or different
Often/failure simultaneously reduces fuel cost, great realistic meaning.
On the other hand, a kind of marine main engine associated member condition monitoring system based on decline contribution degree is provided, including：
Data selecting module is configured execution and selects the steady working condition data in history health sample as off-line training
Input data；
Baseline builds module, is configured to perform structure host economic evaluation baseline and economy associated member health base
Line；
Online data acquisition module is configured to perform online acquisition economy correlation monitoring data；
Economy state analyzing module is configured to perform the host economic evaluation baseline analysis host warp using structure
Ji character state；
Judge selecting module, be configured to perform when being judged as that economy state is normal, selection terminates；When be judged as through
During Ji property abnormal state, the analysis of host associated member health status is carried out；
Host associated member health status analysis module is configured to perform based on economy associated member health baseline profit
The decline contribution degree of host economy associated member is obtained with SOM methods；
Service sequence determining module is configured execution and above-mentioned decline contribution degree is ranked up, and obtains the strong of each component
Health state outcome obtains the sequencing of each parts for maintenance investigation according to the result.
Further, host associated member health status analysis module is configured as performing following specific steps：
Select even running process sampling timeframeThe interior and relevant each associated member system status parameters of economy,
Form the economy associated member observation vector of l-th of sampled point
Economy associated member health baseline input vector of the complete or collected works as SOM net structuresS represents rotating speed, x1,x2,…,xmTable
Show the m state parameters with the relevant each associated member system of economy；L represents sampled point；
Each parameter is inputted after SOM networks in calculating observation vector to nearest best match node WcThe distance between
Value, is denoted as minimum quantization difference MQE；The minimum quantization difference of the economy associated member of l-th of sampled point is：
Each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values,
ByInterior average obtains the decline contribution degree of whole each component
Since present system is identical with above method principle, so also having technique effect corresponding with the above method.
It in the present invention, can also be mutually combined between above-mentioned each technical solution, to realize more preferred compositions schemes.This
Other feature and advantage of invention will illustrate in the following description, also, certain advantages can become from specification it is aobvious and
It is clear to or is understood by implementing the present invention.The purpose of the present invention and other advantages can by write specification, right
Specifically noted structure is realized and obtained in claim and attached drawing.
Description of the drawings
Attached drawing is only used for showing the purpose of specific embodiment, and is not considered as limitation of the present invention, in entire attached drawing
In, identical reference symbol represents identical component.
Fig. 1 is 1 method flow diagram of the embodiment of the present invention；
Fig. 2 is the cluster principle schematic diagram of 1 Self-organizing Maps figure of the embodiment of the present invention；
Fig. 3 is the clustering method schematic diagram of 1 Self-organizing Maps figure of the embodiment of the present invention；
Fig. 4 is 1 analysis method overview flow chart of the embodiment of the present invention；
Fig. 5 is 2 host economic evaluation baseline chart of the embodiment of the present invention；
Fig. 6 is 2 host economy associated member health baseline chart of the embodiment of the present invention；
Fig. 7 is 2 host economic analysis result of the embodiment of the present invention；
Fig. 8 is 2 host economy associated member decline degree ordering chart of the embodiment of the present invention.
Specific embodiment
The preferred embodiment of the present invention is specifically described below in conjunction with the accompanying drawings, wherein, attached drawing forms the application part, and
Together with embodiments of the present invention for illustrating the principle of the present invention, the scope of the present invention is not intended to limit.
The economic index of marine main engine is divided into direct characterization parameter and indirect characterization parameter.
1) direct characterization parameter,
2) it is direct economy key index.For marine main engine, the most critical of its machine economic performance is evaluated
Index is fuel consumption rate, also referred to as fuel efficiency, i.e. the amount of fuel of unit Effective power consumption per hour, usually with every kilowatt-hour
Fuel consumption represent.Therefore, the theoretical calculation formula of host fuel consumption rate is：
In formula,For fuel consumption rate value, unit g/kWh；For fuel consumption hourly, units/kg/h；
For the effective power of host, unit kW.
It should be noted that usual host dispatches from the factory, bench test can give the fuel consumption rate list under diesel engine rated power
Value, as the crucial economic performance index for evaluating the machine.However, when actual motion after host shipment, fuel consumption rate
Change with the variation of real-time rotating speed, the Numerical accuracy that dispatches from the factory is poor.That is, underway host fuel consumption rate geBe on turn
The nonlinear function of fast s can be denoted as ge(s), and fuel consumption is related with rotating speed to diesel engine power.
2) indirect characterization parameter, i.e., with the relevant each associated member system status parameters of economy.Host on-line monitoring system
In system, include cylinder system, cooling system (including jacket-cooling system and air-cooled with the relevant each associated member system of economy
Device), supercharger systems, multiple temperature that the status monitoring parameter of indirect characterization parameter, that is, above-mentioned component system includes cylinder join
Number, cooling system temperature parameter and supercharger speed parameter.
Two kinds of economic index parameters of summary, will host supervision parameter estimator vector X unifications relevant with economy
It is described as：
X (k)=[s (k), ge(k),x1(k),x2(k),…,xm(k)]T (2)
In formula, s (k) is the rotating speed of k-th of monitoring sampled point, represents host current operating condition (i.e. host work
Condition), ge(k) it is the fuel efficiency of k-th of monitoring sampled point, i.e. fuel consumption rate, rotating speed, fuel oil with directly measurement acquisition
Consumption, effective power are related, xi(k), i=1 ..., m is i-th of economy associated member state parameter, and m closes for economy
Join the number of unit status parameter.According to the measuring point condition of different online monitoring systems, the usually desirable cylinder systems of m, cooling system
System, state parameter (analog quantity) number of supercharger systems.
Embodiment 1
As shown in Figure 1, present embodiments providing a kind of low-speed diesel engine Economic Analysis Method, include the following steps：
Step S1 off-line trainings select input data of the history health sample data as off-line training, build low speed bavin
Oil machine economic evaluation baseline and economy associated member health baseline；
Step S2 on-line analyses carry out economy state analysis according to online monitoring data, when economy state is normal,
Terminate；When economy abnormal state, health status analysis is carried out；
Economy state analysis carries out fuel economy based on low-speed diesel engine economic evaluation baseline and analyzes to obtain low speed
Diesel Engine Fuel Economy state outcome；
Health status is analyzed, and low-speed diesel engine economy associated member is carried out based on economy associated member health baseline
Health status is analyzed to obtain economy associated member health status result.
Step S1 obtains steady working condition number by the cleaning to the trouble-free low-speed diesel engine economy related data of history
According to, and then low-speed diesel engine economy baseline is constructed, including low-speed diesel engine fuel economy assessment baseline, economy association portion
Part health baseline.
Low-speed diesel engine economic analysis of the step S2 based on decline contribution degree, i.e.,：For low in one section of run time
Fast engine fuel economy related data selects steady working condition data, carries out based on the online of low-speed diesel engine fuel oil assessment baseline
Fuel economy is analyzed, and when abnormal, further analysis causes each relating module decline contribution degree of economic sexual abnormality, in next step
It eliminates exception and gives data basis.
Step S1 is comprised the following specific steps that：
S101, input data of the history health sample data as off-line training is selected；
S102, structure low-speed diesel engine economic evaluation baseline；
S103, structure economy associated member health baseline.
It should be noted that the construction of the present embodiment low-speed diesel engine economy baseline includes two parts：First, structure
Low-speed diesel engine fuel economy assesses baseline, for characterizing direct economy key index；Second is that structure economy association
Component health baseline, for characterizing the indirect economy index of each associated member system health status related to economy.
Selection construction two economy baselines the reason for be, in order to improve the efficiency of economic analysis, first by with
Low-speed diesel engine fuel economy assess baseline, directly judge economy whether occur exception (contain only 2-D data, can be quick
Obtain analysis result), without further analyzing if normal, if abnormal triggering is for the decline in health of economy associated member
Analysis carries out obtaining analytical conclusions to provide maintenance guidance suggestion.However, if one is only constructed by direct indicator with referring to indirectly
Mark is all contained in interior baseline, then the calculation amount of on-line analysis can be caused to increase, and analysis time extends (the promptness change of analysis
Difference), and cause unnecessary computing resource waste.
Wherein, step S101 includes following sub-step：
Step S1011, data source obtains.
By marine low speed diesel engine monitoring system, historical time length T is set, and finds out nothing all in time span
Fault data is denoted as N number of healthy sample, is monitored at n-th of monitoring sampled point therein with the relevant low-speed diesel engine of economy
Parameter estimator vector X, can be described as according to (2)：
X (n)=[s (n), ge(n),x1(n),x2(n),…,xm(n)]T, n=1 ..., N (3)
Wherein, fuel efficiency g hereine(n) by the directly measured quantities fuel consumption G of n-th of monitoring sampled pointe(n)
With effective power Ne(n) calculated and obtained by formula (1).
Step S1012, determine steady working condition, obtain the relevant steady working condition data of economy.
In N number of healthy sample, select and stablize in the often small of endurance (rotating speed s ＞ 0 (unit RPM, i.e., rpm))
When fuel consumption measurement Ge(n；S ＞ 0), n ∈ 1 ..., N } and low-speed diesel engine output power measurement value Ne(n；S ＞ 0),
N ∈ { 1 ..., N } calculate corresponding moment and the relevant fuel consumption rate g of rotating speed according to formula (1)e(n；S ＞ 0), n ∈
{1,...,N}。
And then the stabilization in N number of healthy sample is found in the sample that navigates in boat even running process scopeIt obtains
Fuel consumption rate during even running
Insolation level α=0.05 is set, using the hypothesis testing mode of t-test, is calculated in each sampling instant fuel consumption
Rate sample value ge(n；S ＞ 0), the test statistics T of n ∈ { 1 ..., N }：
Wherein,For average of samples, μ0Assuming that the population average of sample, S is sample standard deviation,For s ＞ 0 when
Sample size.
Each fuel consumption rate sample value g is determined as a result,e(n；S ＞ 0), n ∈ 1 ..., and N } whether can pass through t-
The hypothesis testing of test insolation levels α=0.05, so as to get rid of, by the sample value of inspection, (i.e. fuel consumption rate is not unusual
Value), obtain the fuel consumption rate during even runningWherein,The steady fortune for being ship in boat
Row process sampling timeframe.
Meanwhile select the rotating speed measured value in the corresponding momentAnd in the corresponding moment, i.e., n-th
Steady working condition monitors at sampled point and the relevant low-speed diesel engine monitoring parameters observation vector of economyIt can be described according to (2)
For：
It is derived from the relevant steady working condition data of economy.
Step S102, fuel economy assessment baseline is built, including：
Step S1021, the rotating speed according to history during even running of navigatingIt is surveyed with fuel consumption rate
MagnitudeEstablish two-dimensional measurement incidence relation；
Step S1022, " rotating speed-fuel consumption rate " assessment models are obtained using nonlinear function approximation modeMake
Baseline is assessed for low-speed diesel engine fuel economy.
Step S103, economy associated member health baseline is built, is specially：
Preferably, SOM (Self-organizing Maps figure, Self-organizing Map or Self-organizing are utilized
Feature Map, abbreviation SOM) network, economy associated member health baseline is constructed, principle and method schematic diagram are referring to figure
2-3。
SOM is a kind of neuroid of simplified version, and the meaning of " self-organizing " is that it can be will be defeated by self study
The data entered are arranged and clustered automatically, without the attribute information of input data；SOM is a kind of typical " unsupervised
Learning method ", even if can still realize classification and similarity analysis on the premise of no data relationship and classification information.It is logical
Often, for just starting to put into the low-speed diesel engine that ship uses, the history economics of normal (fault-free) are readily available
Related data, and be difficult to obtain economy abnormal data, that is, it is difficult to obtain a variety of label datas, therefore, for such data
Economy anomaly analysis, this unsupervised learning methods of SOM are then splendid selections.
The step of using SOM net structure economy associated member health baselines, is as follows：
Step S1031, input vector (Input vector)：In formula (5) observation vectorIn, it selects related to economy
Each associated member system status parameters, including the status monitorings parameter such as rotating speed, cylinder system, cooling system, supercharger systems, group
Into the economy associated member observation vector of n-th of sampled point
Input vector of the complete or collected works as networkWherein,The even running process sampling timeframe for being ship in boatMiddle use
In the sampling instant set of SOM network trainings.
Step S1032, it is vectorial (Weight vector) to input initial weight：For j-th of weight vectors of input vector
It is denoted asK is neuron number, and complete or collected works are denoted as weight
Vectorial Wj.Initial weight can arbitrarily be set, for the sake of simplicity, [0,1,0,1... ,] can be set toT, later stage iteration adjustment restrained
The weight vectors at moment.
Step S1033, SOM network training process：
Find best match node BMU (Best Matching Unit)：Calculate the European of input vector and weight vectors
Distance therefrom finds the minimum point of distance, i.e.,
Wherein, WcIt is denoted as best match node BMU.
Adjustment weight is iterated：Weight adjustment is carried out using following learning rules：
Wherein, t is iterative step, and α is learning rate,For with best match node BMU (Wc) centered on winning neighbour
Topology distance function between j-th of neuron and BMU, selects conventional Gaussian function herein in domain.
Thus training is iterated, terminates to train when convergence, and using trained SOM networks as economy association portion
Part health baseline.
Preferably, step S1034, SOM network test process, the i.e. validation verification of baseline can also be included；
Using in even running process sampling timeframeIn be different fromSampling instant setAs test
Process time scope, then the input vector complete or collected works for corresponding to the trained SOM networks of input areI.e. in the warp of n-th of sampled point
Ji property associated member observation vector
By trained SOM networks (i.e. the economy associated member health baseline of SOM net structures), it is defeated to obtain SOM networks
The estimate gone outI.e. in the economy associated member estimate vector of n-th of sampled point
Calculate the corresponding economy associated member health baseline offset vector of test data：
When economy associated member health baseline offset vector ΔtIn each parameter error average when being no more than 5%, recognize
To pass through the validation verification of baseline；Otherwise the re -training of progress baseline is needed.
Step S2 on-line analyses specifically comprise the following steps：
Step S201, related data is obtained
Step S2011 monitors economy related data on-line.
It is online low when needing to carry out using the real-time monitoring parameters of multi-parameter monitoring system among the operational process of ship
During the analysis of fast engine fuel economy, input the node interior low-speed diesel engine economy related data for the previous period, obtain with
The relevant low-speed diesel engine monitoring parameters observation vector X of economy, can be described as according to (3)：
X (l)=[s (l), ge(l),x1(l),x2(l),…,xm(l)] T, l ' ＞ L, l=l '-L ..., l ' -1, l '
(9)
Wherein, l ' is current time, and L is time span.
Step S2012 selects steady working condition data.
Obtain the fuel consumption rate during even runningWherein,To be steady in input time
Operational process sampling timeframe (i.e. the sampling instant set of even running process), meanwhile, it can also select in the corresponding moment
Rotating speed measured valueAnd in the corresponding moment, i.e. l-th of steady working condition monitors at sampled point and economy
Relevant low-speed diesel engine monitoring parameters observation vectorIt can be described as according to (2)：
The relevant steady working condition data of economy in this period of input are derived from, wherein, fuel efficiency ge(l) by
The directly measured quantities fuel consumption G at sampled point is monitored during l-th of even runninge(l) with effective power Ne(l) pass through
Formula (1), which calculates, to be obtained.
Step S202, fuel economy analysis is carried out based on low-speed diesel engine fuel economy assessment baseline, including：
Step S2021 input datas count：
According to the relevant two-dimensional observation vector of fuel economyFor identical rotating speed, combustion is calculated
The equal Valued Statistics of oily efficiency are derived from even running process sampling timeframeIt is interior, with the relevant fuel efficiency of rotating speed
Statistical valueWherein, nsFor the number of different rotating speeds value；
Step S2022 base-line datas are estimated：
By observation vectorMiddle different tachometer value si, i=1 ..., nsIt inputs to low-speed diesel engine
Fuel economy assesses baselineThat is " rotating speed-fuel consumption rate " assessment models, obtain corresponding low-speed diesel engine fuel oil
Economic evaluation baseline estimations value
Step S2023 baseline offsets calculate：
Calculate the deviation that input data corresponds to low-speed diesel engine fuel economy assessment baseline
Using confidence level as 0.05 (baseline estimations value fluctuate 5%)
For standard：
Step S2024 judges selection：
If deviation deltag(si)≤5%, i=1 ..., ns, then economy state is normal, terminates；
If deviation deltag(si), i=1 ..., nsIn arbitrary value ＞ 5%, then trigger economy state abnormity early warning, and turn
The low-speed diesel engine economy associated member health status analysis based on decline contribution degree is carried out to step S203.
Step S203, the low-speed diesel engine economy associated member health status analysis based on decline contribution degree, bag are carried out
It includes：
Optionally, the SOM methods of the present embodiment selection " Self-organizing Maps figure-minimum quantization is poor (SOM-MQE) " calculate each
Associated member decline contribution degree：
Step S2031, even running process sampling timeframe is selectedThe interior and relevant each associated member system shape of economy
State parameter (including the status monitorings parameter such as rotating speed, cylinder system, cooling system, supercharger systems, and with the input of off-line training to
Amount is consistent), the economy associated member observation vector of l-th of sampled point of composition
Economy associated member health baseline input vector of the complete or collected works as SOM net structures
Step S2032, each parameter is inputted after SOM networks in calculating observation vector to nearest best match node BMU
(Wc) the distance between value, be denoted as that minimum quantization is poor (MQE), i.e., the minimum quantization of the economy associated member of l-th sampled point
Difference is：
Step S2033, each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values, i.e.,：
Whole each component decline contribution degree then byInterior average obtains, and is denoted as
Step S204：Orientation problem component carries out maintenance investigation.
I.e.：According to the decline contribution degree of each componentDraw the decline contribution degree point of each component
Butut is from high to low ranked up the decline contribution degree of all parts, and according to the sequence of each component decline contribution degree
The order for carrying out parts for maintenance investigation is provided successively, thus gives economic analysis guiding opinion.
Fig. 4 is the present embodiment detailed step flow chart.
The present embodiment：
(1) economic evaluation and analysis of Influential Factors are carried out from two angles：First, from direct angle, fuel consumption rate
(i.e. fuel efficiency) is one of important indicator for judging diesel engine performance quality, it is directly related to the economy of diesel engine, row
Index and reliability are put, i.e., calculating the fuel oil in ship actual moving process with operating status by the fuel consumption of host disappears
Consumption rate directly evaluates the fuel economy of host；Second is that from indirect angle, all and relevant pass of host economy is found
Join component, by the means of data-driven, calculate contribution degree of each economy associated member decline for the economic sexual abnormality of host,
Thus corresponding economic influence factor and influence degree are quantitatively obtained, it is extensive hence for the maintaining for effectively instructing host
The economic performance of multiple host excludes security risk or exception/fault and reduces fuel cost, great realistic meaning.
(2) by research and application to the relevant Multi-parameter data of economy, economic sexual abnormality is found accurately and in time, into
And corresponding economic influence factor and influence degree are quantitatively analyzed, so as to effectively instruct the maintaining of host, recover master
The economic performance of machine excludes security risk or exception/fault and reduces fuel cost.
Embodiment 2
The above method is used to put into host (brand MAN, model that certain 10,000 tons bulk freighter uses to one
Real ship monitoring 5S60ME) is carried out, which includes operating status, fuel consumption (direct economy
Property parameter), host cylinder system (delivery temperature containing cylinder, cylinder piston cooling-oil outlet temperature, cylinder liner cooling water outlet
Temperature, cylinder scavenging case catch fire temperature), supercharger systems (supercharger speed), (scavenging before and after air cooler of aerial cooler system
Temperature difference) etc. canonical parameters.
First portion：Off-line training result
According to the off-line training step of above-described embodiment 1, input fault-free in the ship 2016/8/15 to 2016/9/15 and put down
The economy related data surely run, it is cold including rotating speed, fuel efficiency, No.1-5 cylinder exhausts temperature, No.1-5 cylinder pistons
But oil export temperature, No.1-5 cylinder scavenging casees catch fire scavenging before and after temperature, No.1-5 jacket-cooling waters outlet temperature, air cooler
Temperature difference, the data of supercharger speed obtain host fuel economy assessment baseline and economy associated member health baseline；
Model baseline chart is as seen in figs. 5-6.
Trained SOM network verifications error is no more than 5%, meets economy associated member health baseline validation requirement
Available for carrying out on-line analysis.
Second portion：On-line analysis result
According to 1 on-line analysis process of embodiment, the economy of even running in the ship 2016/9/16 to 2016/10/15 is inputted
Property related data.
Fuel economy is carried out to analyze to obtain shown in Fig. 7 as a result, to obtaining the fuel economy baseline offset more than 5%,
Economy abnormity early warning is triggered, and carries out health status analysis, calculates and obtains each decline contribution degree distribution situation and ranking results
As shown in figure 8, the figure shows the decline degree of each associated components parameter successively from top to bottom, and corresponding each dependent part can be symbolized
Part recession level effective position trouble unit, for instructing specifically to repair investigation order.
Thus in accordance with said sequence provide repair investigation suggest, i.e., successively to host air cooler, cylinder piston, booster,
Scavenging air box, cylinder sleeve, inblock cylinder temperature are investigated.
The present embodiment demonstrates the validity of this method well.
Embodiment 3
A kind of host economic analysis system is present embodiments provided, including off-line training module and on-line analysis module；
Data selecting module is configured execution and selects the steady working condition data in history health sample as off-line training
Input data；
Baseline builds module, is configured to perform structure host economic evaluation baseline and economy associated member health base
Line；
Online data acquisition module is configured to perform online acquisition economy correlation monitoring data；
Economy state analyzing module is configured to perform the host economic evaluation baseline analysis host warp using structure
Ji character state；
Judge selecting module, be configured to perform when being judged as that economy state is normal, selection terminates；When be judged as through
During Ji property abnormal state, the analysis of host associated member health status is carried out；
Host associated member health status analysis module is configured to perform based on economy associated member health baseline profit
The decline contribution degree of host economy associated member is obtained with SOM methods；
Service sequence determining module is configured execution and above-mentioned decline contribution degree is ranked up, and obtains the strong of each component
Health state outcome obtains the sequencing of each parts for maintenance investigation according to the result.
Host associated member health status analysis module, is configured as performing following specific steps：
Select even running process sampling timeframeThe interior and relevant each associated member system status parameters of economy,
Form the economy associated member observation vector of l-th of sampled point
Economy associated member health baseline input vector of the complete or collected works as SOM net structuresS represents rotating speed, x1,x2,…,xmTable
Show the m state parameters with the relevant each associated member system of economy；L represents sampled point；
Each parameter is inputted after SOM networks in calculating observation vector to nearest best match node WcThe distance between
Value, is denoted as minimum quantization difference MQE；The minimum quantization difference of the economy associated member of l-th of sampled point is：
Each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values,
ByInterior average obtains the decline contribution degree of whole each component
Since present system is identical with above method principle, so also having technology corresponding with above-mentioned analysis method effect
Fruit, and related part can be cross-referenced, it is no longer repeated for this embodiment.
It will be understood by those skilled in the art that realizing all or part of flow of above-described embodiment method, meter can be passed through
Calculation machine program instructs relevant hardware to complete, and the program can be stored in computer readable storage medium.Wherein, institute
Computer readable storage medium is stated as disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of marine main engine associated member state monitoring method based on decline contribution degree, which is characterized in that including walking as follows
Suddenly：
Select input data of the steady working condition data in history health sample as off-line training, the master in input data
Machine rotating speed builds host economic evaluation baseline with fuel consumption rate measured value, according to engine speed and economy associated member shape
State parameter builds economy associated member health baseline using SOM methods；
Data monitoring is carried out using multi-parameter monitoring system, monitoring data are carried out using the host economic evaluation baseline of structure
Host economy state analysis when economy state is normal, terminates；When economy abnormal state, abnormal alarm is sent, and
Carry out the analysis of host associated member health status；The host associated member health status analysis, including：It is associated using economy
Component health baseline analyzes monitoring data, obtains the decline of host economy associated member and declines to the economic sexual abnormality of host
Move back contribution degree；
Above-mentioned decline contribution degree is ranked up, the forward positioning parts that will sort are exceptional part, and carry out corresponding component
Repair investigation.
2. according to the method described in claim 1, it is characterized in that, the economy associated member includes cylinder system, cooling
System and supercharger systems.
3. according to the method described in claim 2, it is characterized in that, the monitoring data are the input data class with off-line training
The consistent data of type, including engine speed, fuel consumption, cylinder system state parameter, cooling system state parameter and supercharging
The state parameter of device system.
4. according to the method described in claim 3, it is characterized in that, structure economy associated member health baseline includes following steps
Suddenly：
Selection and the relevant each associated member system status parameters of economy, the economy associated member for building n-th of sample are seen
Direction finding amountInput vector of the complete or collected works as networkIts
In,The even running process sampling timeframe for being ship in boatIn be used for SOM network trainings sampling instant collection
Close, s (n) be rotating speed, x1(n),x2(n),…,xm(n) the state ginseng of m and the relevant each associated member system of economy is represented
Number；
According to j-th of weight vectors W of input vectorj(n) complete or collected works' weight vectors W is obtainedj；Wherein,
K is the neuron number of SOM network trainings；
The Euclidean distance of input vector and weight vectors is calculated, the minimum point of distance is found, as best match node Wc；
UsingAdjust weight, complete or collected works' weight vectors after being adjusted；Its
In, t is iterative step, and α is learning rate,For with best match node WcCentered on winning neighborhood in j-th of neuron
With best match node WcBetween topology distance function；
The repetitive exercise of SOM networks is carried out, terminates to train when convergence, using trained SOM networks as economy association portion
Part health baseline.
5. according to the method described in claim 4, it is characterized in that, further include the step tested trained SOM networks
Suddenly, test is by the way that then re -training, is tested until passing through.
6. host Economic Analysis Method according to claim 5, which is characterized in that described to trained SOM networks
The step of being tested includes：
Using in even running process sampling timeframeIn be different fromSampling instant setAs test process
Time range, in the economy associated member observation vector of n-th of sampled point
The corresponding input for inputting trained SOM networks to
Measuring complete or collected works is
The estimate of SOM networks output is obtained by trained SOM networksIn the economy association portion of n-th of sampled point
Part estimate vector：
<mrow>
<msub>
<mover>
<mi>X</mi>
<mo>^</mo>
</mover>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mover>
<mi>s</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mo>...</mo>
<mo>,</mo>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>n</mi>
<mo>&Element;</mo>
<msub>
<mover>
<mi>T</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>t</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
<mo>;</mo>
</mrow>
Calculate the corresponding economy associated member health baseline offset vector of test data：
<mrow>
<msub>
<mi>&Delta;</mi>
<mi>t</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<mo>|</mo>
<mfrac>
<mrow>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mover>
<mi>s</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mover>
<mi>s</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>|</mo>
<mo>&times;</mo>
<mn>100</mn>
<mi>%</mi>
<mo>,</mo>
<mo>|</mo>
<mfrac>
<mrow>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>|</mo>
<mo>&times;</mo>
<mn>100</mn>
<mi>%</mi>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mo>|</mo>
<mfrac>
<mrow>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>|</mo>
<mo>&times;</mo>
<mn>100</mn>
<mi>%</mi>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>n</mi>
<mo>&Element;</mo>
<msub>
<mover>
<mi>T</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>t</mi>
<mi>e</mi>
<mi>s</mi>
<mi>t</mi>
</mrow>
</msub>
</mrow>
When economy associated member health baseline offset vector ΔtIn each parameter error average when being no more than threshold value, it is believed that it is logical
Cross test.
7. according to the method described in one of claim 1-6, which is characterized in that
Host economy state analysis is carried out to online monitoring data using the host economic evaluation baseline of structure, including following
Step：
According to the relevant two-dimensional observation vector of fuel economyFor identical rotating speed, fuel oil effect is calculated
The equal Valued Statistics of rate are derived from even running process sampling timeframeIt is interior, fuel efficiency statistics relevant with rotating speed
ValueWherein, nsFor the number of different rotating speeds value；
By observation vectorMiddle different tachometer value si, i=1 ..., nsInput the assessment of host fuel economy
Baseline obtains corresponding host fuel economy assessment baseline estimations value
Calculate the deviation of input data corresponding host fuel economy assessment baseline
If all deviations are respectively less than threshold value, economy state is normal, terminates；
If the arbitrary value in deviation is more than threshold value, economy abnormal state carries out the analysis of host associated member health status.
8. host Economic Analysis Method according to claim 7, which is characterized in that utilize economy associated member health
Baseline analyzes online monitoring data, obtains the decline tribute that host economy associated member fails to the economic sexual abnormality of host
Degree of offering comprises the following steps：
Select even running process sampling timeframeThe interior and relevant each associated member system status parameters of economy, composition
The economy associated member observation vector of l-th of sampled pointComplete or collected works
Economy associated member health baseline input vector as SOM net structures
Each parameter is inputted after SOM networks in calculating observation vector to nearest best match node WcThe distance between value, be denoted as
Minimum quantization difference MQE；The minimum quantization difference of the economy associated member of l-th of sampled point is：
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>M</mi>
<mi>Q</mi>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>MQE</mi>
<mi>s</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<mo>|</mo>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<mi>s</mi>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</mrow>
</msub>
<mo>|</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values,
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</mrow>
</msub>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
ByInterior average obtains the decline contribution degree of whole each component
9. a kind of marine main engine associated member condition monitoring system based on decline contribution degree, which is characterized in that including：
Data selecting module is configured execution and selects the steady working condition data in history health sample as the defeated of off-line training
Enter data；
Baseline builds module, is configured to perform structure host economic evaluation baseline and economy associated member health baseline；
Online data acquisition module is configured to perform online acquisition economy correlation monitoring data；
Economy state analyzing module is configured to perform the host economic evaluation baseline analysis host economy using structure
State；
Judge selecting module, be configured to perform when being judged as that economy state is normal, selection terminates；When being judged as economy
During abnormal state, the analysis of host associated member health status is carried out；
Host associated member health status analysis module is configured to perform based on the utilization of economy associated member health baseline
SOM methods obtain the decline contribution degree of host economy associated member；
Service sequence determining module is configured execution and above-mentioned decline contribution degree is ranked up, obtains the healthy shape of each component
State according to the result as a result, obtain the sequencing of each parts for maintenance investigation.
10. system according to claim 9, it is characterised in that：Host associated member health status analysis module, by with
It is set to and performs following specific steps：
Select even running process sampling timeframeThe interior and relevant each associated member system status parameters of economy, composition
The economy associated member observation vector of l-th of sampled pointEntirely
Collect the economy associated member health baseline input vector as SOM net structuresS represents rotating speed, x1,x2,…,xmRepresent m
A state parameter with the relevant each associated member system of economy；L represents sampled point；
Each parameter is inputted after SOM networks in calculating observation vector to nearest best match node WcThe distance between value, be denoted as
Minimum quantization difference MQE；The minimum quantization difference of the economy associated member of l-th of sampled point is：
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>M</mi>
<mi>Q</mi>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>MQE</mi>
<mi>s</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<mo>|</mo>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<mi>s</mi>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mo>|</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</mrow>
</msub>
<mo>|</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
Each component decline contribution degree C (l) in addition to rotating speed is obtained by MQE values,
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>C</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>MQE</mi>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mo>/</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>c</mi>
<mo>,</mo>
<msub>
<mi>x</mi>
<mi>m</mi>
</msub>
</mrow>
</msub>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>,</mo>
<mi>l</mi>
<mo>&Element;</mo>
<mover>
<mi>L</mi>
<mo>&OverBar;</mo>
</mover>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
ByInterior average obtains the decline contribution degree of whole each component
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711235510.7A CN108062586B (en) | 2017-11-30 | 2017-11-30 | Ship host machine associated component state monitoring method and system based on decline contribution degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711235510.7A CN108062586B (en) | 2017-11-30 | 2017-11-30 | Ship host machine associated component state monitoring method and system based on decline contribution degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108062586A true CN108062586A (en) | 2018-05-22 |
| CN108062586B CN108062586B (en) | 2020-03-27 |
Family
ID=62135911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711235510.7A Active CN108062586B (en) | 2017-11-30 | 2017-11-30 | Ship host machine associated component state monitoring method and system based on decline contribution degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108062586B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255201A (en) * | 2018-10-24 | 2019-01-22 | 哈工大机器人（山东）智能装备研究院 | A kind of ball screw assembly, health evaluating method based on SOM-MQE |
| CN110502390A (en) * | 2019-07-08 | 2019-11-26 | 中国地质大学（武汉） | A kind of colleges and universities' cloud computing center automation operation management system |
| CN110696990A (en) * | 2019-11-11 | 2020-01-17 | 中国船舶工业系统工程研究院 | Ship generator component influence identification method and system based on data driving |
| CN111190349A (en) * | 2019-12-30 | 2020-05-22 | 中国船舶重工集团公司第七一一研究所 | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment |
| CN112378651A (en) * | 2020-12-08 | 2021-02-19 | 中国船舶工业系统工程研究院 | Data-driven-based equipment dynamic reliability assessment method |
| CN113379223A (en) * | 2021-06-04 | 2021-09-10 | 江苏科技大学 | Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880170B (en) * | 2012-10-08 | 2015-03-25 | 南京航空航天大学 | System failure early warning method based on baseline model and Bayesian factor |
| CN105737922A (en) * | 2016-01-26 | 2016-07-06 | 中国船舶工业系统工程研究院 | Method and device for early warning on fuel consumption rate of low-speed diesel engine of ship |
| CN106368816A (en) * | 2016-10-27 | 2017-02-01 | 中国船舶工业系统工程研究院 | Method for online abnormity detection of low-speed diesel engine of ship based on baseline deviation |
| CN106777554A (en) * | 2016-11-29 | 2017-05-31 | 哈尔滨工业大学（威海） | Aerial engine air passage cell cube health status evaluation method based on state baseline |
-
2017
- 2017-11-30 CN CN201711235510.7A patent/CN108062586B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880170B (en) * | 2012-10-08 | 2015-03-25 | 南京航空航天大学 | System failure early warning method based on baseline model and Bayesian factor |
| CN105737922A (en) * | 2016-01-26 | 2016-07-06 | 中国船舶工业系统工程研究院 | Method and device for early warning on fuel consumption rate of low-speed diesel engine of ship |
| CN106368816A (en) * | 2016-10-27 | 2017-02-01 | 中国船舶工业系统工程研究院 | Method for online abnormity detection of low-speed diesel engine of ship based on baseline deviation |
| CN106777554A (en) * | 2016-11-29 | 2017-05-31 | 哈尔滨工业大学（威海） | Aerial engine air passage cell cube health status evaluation method based on state baseline |
Non-Patent Citations (2)
| Title |
|---|
| HOUMAN HANACHI等: "A Physics-Based Modeling Approach for Performance Monitoring in Gas Turbine Engines", 《IEEE TRANSACTIONS ON RELIABILITY》 * |
| 马剑等: "船舶主推进系统故障预测与健康管理设计", 《南京航空航天大学学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255201A (en) * | 2018-10-24 | 2019-01-22 | 哈工大机器人（山东）智能装备研究院 | A kind of ball screw assembly, health evaluating method based on SOM-MQE |
| CN109255201B (en) * | 2018-10-24 | 2023-07-14 | 哈工大机器人（山东）智能装备研究院 | SOM-MQE-based ball screw pair health assessment method |
| CN110502390A (en) * | 2019-07-08 | 2019-11-26 | 中国地质大学（武汉） | A kind of colleges and universities' cloud computing center automation operation management system |
| CN110502390B (en) * | 2019-07-08 | 2021-06-01 | 中国地质大学（武汉） | Automatic operation and maintenance management system of colleges and universities cloud computing center |
| CN110696990A (en) * | 2019-11-11 | 2020-01-17 | 中国船舶工业系统工程研究院 | Ship generator component influence identification method and system based on data driving |
| CN111190349A (en) * | 2019-12-30 | 2020-05-22 | 中国船舶重工集团公司第七一一研究所 | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment |
| CN112378651A (en) * | 2020-12-08 | 2021-02-19 | 中国船舶工业系统工程研究院 | Data-driven-based equipment dynamic reliability assessment method |
| CN113379223A (en) * | 2021-06-04 | 2021-09-10 | 江苏科技大学 | Ship-borne spare part multi-level configuration method for ship main engine based on fault correlation model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108062586B (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062586A (en) | Marine main engine associated member state monitoring method and system based on decline contribution degree | |
| Xu et al. | PHM-oriented integrated fusion prognostics for aircraft engines based on sensor data | |
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN108062618A (en) | Low-speed diesel engine Economic Analysis Method and system based on biradical line | |
| CN108563806B (en) | Engine air passage parameter long-range forecast method and system based on similitude | |
| CN107949812A (en) | For detecting the abnormal combined method in water distribution system | |
| Ellefsen et al. | Online fault detection in autonomous ferries: Using fault-type independent spectral anomaly detection | |
| CN106368816A (en) | Method for online abnormity detection of low-speed diesel engine of ship based on baseline deviation | |
| CN102175282A (en) | Method for diagnosing fault of centrifugal air compressor based on information fusion | |
| JPH08202444A (en) | Method and device for diagnosing abnormality of machine facility | |
| CN115187832A (en) | Energy system fault diagnosis method based on deep learning and gram angular field image | |
| KR20220139920A (en) | Create a representation of a process network comprising at least two interconnected chemical plants | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN113847950A (en) | Intelligent ship equipment state monitoring system based on cloud computing and information interaction method | |
| CN115659263A (en) | Ship control behavior risk assessment system and assessment method based on big data | |
| Li et al. | A CM&CP framework with a GIACC method and an ensemble model for remaining useful life prediction | |
| Vorkapić et al. | Machine learning methods in monitoring operating behaviour of marine two-stroke diesel engine | |
| Kaklis et al. | From STEAM to Machine: Emissions control in the shipping 4.0 era | |
| Gkerekos et al. | Ship machinery condition monitoring using vibration data through supervised learning | |
| Orhan et al. | A literature review and future research agenda on fault detection and diagnosis studies in marine machinery systems | |
| CN110826600B (en) | Engine surge prediction method based on adaptive resonance network online incremental learning | |
| CN110826587B (en) | Vortex shaft engine fault detection method based on improved weighted support vector machine | |
| Zeng et al. | Rail break prediction and cause analysis using imbalanced in-service train data | |
| Fan et al. | Comprehensive evaluation of machine learning models for predicting ship energy consumption based on onboard sensor data | |
| CN109342862A (en) | Based on Non-surveillance clustering with and svm classifier Diagnosis Method of Transformer Faults |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |