CN109063910A - A kind of Pollution From Ships object discharge method of real-time based on big data - Google Patents
A kind of Pollution From Ships object discharge method of real-time based on big data Download PDFInfo
- Publication number
- CN109063910A CN109063910A CN201810871938.9A CN201810871938A CN109063910A CN 109063910 A CN109063910 A CN 109063910A CN 201810871938 A CN201810871938 A CN 201810871938A CN 109063910 A CN109063910 A CN 109063910A
- Authority
- CN
- China
- Prior art keywords
- data
- value
- real
- ship
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 91
- 231100000719 pollutant Toxicity 0.000 claims abstract description 91
- 230000002159 abnormal effect Effects 0.000 claims abstract description 42
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 230000003068 static effect Effects 0.000 claims abstract description 15
- 230000008676 import Effects 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000006467 substitution reaction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 9
- 238000003912 environmental pollution Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 239000007789 gas Substances 0.000 description 15
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000000446 fuel Substances 0.000 description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 description 3
- 239000001569 carbon dioxide Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 239000000295 fuel oil Substances 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000567 combustion gas Substances 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 239000002283 diesel fuel Substances 0.000 description 1
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及船舶监测技术领域，具体涉及一种基于大数据的船舶污染物排放实时监测方法，包括以下步骤：A）采集船舶若干个航行动态信息以及污染物排放速率；B）使用采集到的数据训练神经网络模型；C）应用时，采集船舶的航行动态信息，导入神经网络模型得出实时污染物排放速率预测，将实时污染物排放速率预测与实时污染物排放速率对比，若差值超过设定阈值，则判断船舶污染物排放异常。本发明的有益效果是：通过神经网络模型可以结合船舶静态参数和航行动态数据，预测污染物排放速率，并将其作为参考标准，实时判断船舶污染物排放是否异常，方便监管部门进行监管，发现并淘汰污染物排放偏高的船舶，减少环境污染。
The present invention relates to the technical field of ship monitoring, in particular to a method for real-time monitoring of ship pollutant discharge based on big data, comprising the following steps: A) collecting a number of ship navigation dynamic information and pollutant discharge rate; B) using the collected data Train the neural network model; C) When applying, collect the dynamic information of the ship's navigation, import the neural network model to obtain the real-time pollutant discharge rate prediction, compare the real-time pollutant discharge rate prediction with the real-time pollutant discharge rate, if the difference exceeds the set If the threshold is set, it is judged that the discharge of pollutants from ships is abnormal. The beneficial effects of the present invention are: the neural network model can be combined with the ship's static parameters and navigation dynamic data to predict the pollutant discharge rate, and use it as a reference standard to judge whether the ship's pollutant discharge is abnormal in real time, which is convenient for the supervision department to supervise and find And eliminate ships with high pollutant emissions to reduce environmental pollution.
Description
Technical field
The present invention relates to ship monitoring technical fields, and in particular to a kind of Pollution From Ships object discharge based on big data is real-time
Monitoring method.
Background technique
The content of pollutant is easy monitoring in marine exhaust, however only the content of monitoring pollution object has been unable to meet at present
Demand.It also needs to monitor exhaust gas total amount.Marine exhaust pollutant load standard is easy to formulate, however exhaust gas total emission volumn is by ship
Discharge capacity, new and old, course line, sea wind wind direction and wind-force etc. influence, it is difficult to formulate standard.But the reason of causing global warming is greenhouse gas
A large amount of discharges of body have exceeded the amount of Natural Circulation consumption.Transportation as first three industry of oil gas energy consumption ranking,
The highest attention for also having caused various circles of society is polluted caused by it.Prevailing traffic side of the Shipping as global trade
Formula, accounting of the carbon dioxide and other total amount of pollutant that Shipping discharges in the process in whole total carbon emissions are more next
It is higher.In today that control carbon emission is increasingly urgent, national governments launch respectively the Control Policy in relation to the discharge of Pollution From Ships object.
However ship pollutant emission how is monitored, and how to formulate the standard for judging pollutant emission reference whether up to standard, become
Urgent problem to be solved.
Chinese patent CN202013505U, publication date on October 19th, 2011, a kind of double fuel marine fuel consumption are long-range
Wireless supervisory control system, including Beidou satellite communication system, ship terminal applies system and monitoring center system, the ship terminal are answered
It include sequentially connected data collection station, data acquisition server and Beidou boat-carrying subscriber computer with system, data acquisition is eventually
End includes diesel flow sensor, gas flow sensor, liquid level sensor and pressure sensor, and the revolving speed of engine system passes
Sensor, water temperature sensor, exhaust gas temperature sensor and alarm sensor；The monitoring center system includes command type interconnected
Subscriber computer and data server；The Beidou boat-carrying subscriber computer between Beidou satellite communication system and command type subscriber computer by establishing
Wireless communication connection.Advantage is: utilizing big-dipper satellite long range radio transmissions technologies, record monitoring diesel oil and combustion gas disappear in real time
Situation is consumed, fuel oil substitution rate is calculated and is noted abnormalities in time, fuel consumption is reasonably controlled, reaches reduction fuel cost, is reduced
The purpose of disposal of pollutants.Although it can instruct the use of two kinds of fuel of reasonable disposition to match, disposal of pollutants is reduced, it cannot
The problem of realization is monitored pollutant discharge amount.
Summary of the invention
The technical problem to be solved by the present invention is at present due to lacking reference standard, and be difficult to exhaust gas in ship's navigation
And total amount of pollutant the technical issues of being monitored.Propose it is a kind of using big data can to judge that Pollution From Ships object discharges total
The whether normal reasonable Pollution From Ships object of amount discharges method of real-time.
In order to solve the above technical problems, the technical solution used in the present invention are as follows: a kind of Pollution From Ships based on big data
Object discharges method of real-time, comprising the following steps: A) contain in marine exhaust discharge outlet installation flow sensor and pollutant
Quantity sensor, several navigation multidate informations of acquisition ship and pollutant emission rate；B) using collected navigation dynamic
Information is used after pollutant emission rate stamps as effective sample data, and training neural network model；C) in application, acquisition vessel
The navigation multidate information of oceangoing ship, and import neural network model and obtain real-time pollutant emission rate prediction, real-time pollutant is arranged
Rate prediction and real-time pollutant emission rate comparison are put, if difference is more than given threshold, judges that the discharge of Pollution From Ships object is different
Often, on the contrary then repeat this step.By enough data samples training neural network model, enable neural network model root
According to the navigation multidate information of ship and the specifications parameter information of combination ship, the pollutant emission rate of ship is predicted, i.e., singly
The total emission volumn of pollutant in the time of position, the pollutant includes carbon dioxide isothermal chamber gas, is mounted on discharge outlet on ship
Sensor out can exhaust gas total emission volumn and pollutant load in the real-time detection unit time, and then calculate each pollution
The total emission volumn of object judges that the discharge of Pollution From Ships object is abnormal if exhaust emission content is exceeded, if pollution in the unit time
The result difference of object total emission volumn, i.e. pollutant emission rate and pollutant emission rate prediction is more than given threshold, then judges
The discharge of Pollution From Ships object is abnormal.In step, flow sensor can be arranged on the exhaust gas flow sensor of exhaust ports,
Flow velocity is multiplied with diameter of outlet and participates in calculating as exhaust gas total amount.Pollutant load sensor can use automobile-used or factory
With the detection sensor of exhaust emission content.The invention patent meaning pollutant can be Single Pollution object, be also possible to more
Kind pollutant, then needs to install if multiple pollutant multiple corresponding pollutant load detection sensors, with waste gas stream
Amount obtains pollutant emission rate after being multiplied, and establishes neural network model respectively to each pollutant, is monitored respectively.
Preferably, also acquiring the static parameter of ship in step, and data are carried out to the ship of multiple discharge capacities and are adopted
Collection forms the data group of multiple static parameters, navigation multidate information and pollutant emission rate, in step C, if application
Target ship discharge capacity is not acquire the discharge capacity of data, then by multiple static parameters of acquisition, navigation multidate information and pollution
Object rate of discharge data group carries out interpolation processing, obtains static parameter, navigation multidate information and dirt under target ship discharge capacity
Object rate of discharge interpolated data group is contaminated, and is then entered step using interpolated data group according to step B training neural network model
C.Ship static parameter includes the specifications parameter of ship, including captain, the beam and identification code (MMSI), and navigation multidate information includes
Speed on the ground, course over ground, steering angle and wind speed, wind direction, ocean current speed, ocean current to and wave heights.
Preferably, it is described acquisition ship several navigation multidate informations and pollutant emission rate method include with
Lower step: A1) it acquires and uploads navigation multidate information and pollutant emission rate；A2) respectively to each navigation multidate information
It is calculated with being associated property of pollutant emission rate；A3 the navigation multidate information that the degree of association is lower than setting value) is rejected, it will be remaining
Multidate information is navigated by water as subsequent navigation dynamic information collection project.Navigation multidate information includes speed on the ground, course over ground, turns
To angle and wind speed, wind direction, ocean current speed, ocean current to and wave heights picked to calculation of relationship degree is carried out after the acquisition of these data
It is subsequent no longer to acquire except the degree of association is lower than the parameter of setting value.
Preferably, it is described acquisition ship several navigation multidate informations and oil consumption method the following steps are included:
AA1 it) acquires and uploads navigation multidate information and pollutant emission rate；AA2) respectively to each navigation multidate information data
Rate of change and being associated property of pollutant emission rate rate of change calculate；AA3 the navigation that the degree of association is lower than setting value) is reduced
Multidate information project data frequency acquisition.Reduction need to handle data volume, reduce data and transmit pressure, while influencing on precision of prediction
Less.
Preferably, valid data sample is verified and repaired before training neural network model in stepb, it is described
The method of verification are as follows: successively judge whether each data are preset exception about definite value, if abnormal about definite value, then the number
According to abnormal data is verified as, conversely, being then verified as normal data；Then judge whether the data value is more than setting range, if super
Setting range is crossed, then the data check is abnormal data, conversely, being then verified as normal data；Then judge the data value with before
Whether the difference of one acquisition value is more than setting range, if being more than setting range, which is abnormal data, conversely,
Then it is verified as normal data.Abnormal data differentiate and reparation can be improved prediction accuracy.
Preferably, the method for the reparation are as follows: judge whether abnormal data adjacent data check results are normal data,
Subsequent calculating is participated in as normal data after abnormal data is replaced using the mean value of adjacent data if being, conversely, carrying out
Following steps: B1) data group that takes several continuous adjacents is normalized using one of data group as reference data set
Processing；B2) calculate normalization after each data with 1 difference absolute value, find out the maximum value K of differencemax；B3 it) calculates each
With abnormal data with the data x of projectiAssociation angle value δi,
Wherein, xiFor the value after the data normalization, ρ is the threshold of sensitivity, and the value of ρ is smaller, and the difference between data correlation degree is got over
Greatly；B4) with association angle value δiGreater than given threshold δ0Data xiConduct after the mean value substitution abnormal data of corresponding raw value
Normal data uses.
Substantial effect of the invention is: the data after being screened by the degree of association, can as neural metwork training data
It improves the efficiency of neural network model training and reduces data interference, ship static parameter can be combined by neural network model
With navigation dynamic data, pollutant emission rate is predicted, and as reference standard, the discharge of real-time judge Pollution From Ships object is
No exception, facilitates supervision department to be supervised, and finds and eliminates the higher ship of pollutant emission, reduce environmental pollution.
Detailed description of the invention
Fig. 1 is pollutant emission monitoring method flow diagram.
Fig. 2 is abnormal data restorative procedure flow diagram.
Specific embodiment
Below by specific embodiment, and in conjunction with attached drawing, a specific embodiment of the invention is further described in detail.
As shown in Figure 1, being pollutant emission monitoring method flow diagram, comprising the following steps: A) it is discharged in marine exhaust
Mouth installation flow sensor and pollutant load sensor, several navigation multidate informations of acquisition ship and pollutant emission
Rate；B it as effective sample data after) using collected navigation multidate information to use pollutant emission rate stamps, and trains
Neural network model；C it) in application, acquiring the navigation multidate information of ship, and imports neural network model and obtains real-time pollutant
Rate of discharge prediction, by real-time pollutant emission rate prediction and real-time pollutant emission rate comparison, if difference is more than setting
Threshold value then judges that the discharge of Pollution From Ships object is abnormal, on the contrary then repeat this step.Pass through enough data samples training neural network
Model enables neural network model according to the navigation multidate information of ship and the specifications parameter information of combination ship, prediction
The pollutant emission rate of ship out, i.e., the total emission volumn of pollutant in the unit time, pollutant includes carbon dioxide isothermal chamber
Gas, being mounted on sensor that discharge outlet on ship goes out being capable of exhaust gas total emission volumn and pollutant in the real-time detection unit time
Content, and then the total emission volumn of each pollutant is calculated, judge that Pollution From Ships object is arranged if exhaust emission content is exceeded
Exception is put, if gross contamination emission in the unit time, i.e. the result of pollutant emission rate and pollutant emission rate prediction
Difference is more than given threshold, then judges that the discharge of Pollution From Ships object is abnormal.In step, flow sensor can the row of being arranged on
Flow velocity is multiplied with diameter of outlet and participates in calculating as exhaust gas total amount by the exhaust gas flow sensor at port.Pollutant load
Sensor can use the detection sensor of automobile-used or factory exhaust emission content.The invention patent meaning pollutant can be with
It is Single Pollution object, is also possible to multiple pollutant, then needs to install multiple corresponding pollutants if multiple pollutant
Content detection sensor, obtains the pollutant emission rate after being multiplied with exhaust gas flow, establish nerve respectively to each pollutant
Network model is monitored respectively.
The static parameter of ship is also acquired in step, and data acquisition is carried out to the ship of multiple discharge capacities, is formed more
The data group of a static parameter, navigation multidate information and pollutant emission rate, in step C, if the target ship of application
Discharge capacity is not acquire the displacement type of data, then arranges multiple static parameters of acquisition, navigation multidate information and pollutant
It puts speed data group and carries out interpolation processing, obtain static parameter, navigation multidate information and the pollutant under target ship discharge capacity
Rate of discharge interpolated data group, and C is then entered step according to step B training neural network model using interpolated data group.Ship
Oceangoing ship static parameter includes the specifications parameter of ship, including captain, the beam and identification code (MMSI), and navigation multidate information includes over the ground
The speed of a ship or plane, course over ground, steering angle and wind speed, wind direction, ocean current speed, ocean current to and wave heights.
The method of several navigation multidate informations of acquisition ship and pollutant emission rate is the following steps are included: A1) it adopts
Collect and uploads navigation multidate information and pollutant emission rate；A2) respectively to each navigation multidate information and pollutant emission
Being associated property of rate calculates；A3 the navigation multidate information that the degree of association is lower than setting value) is rejected, by remaining navigation multidate information
As subsequent navigation dynamic information collection project.Navigating by water multidate information includes speed on the ground, course over ground, steering angle and wind
Speed, wind direction, ocean current speed, ocean current to and wave heights it is low to reject the degree of association to calculation of relationship degree is carried out after the acquisition of these data
It is subsequent no longer to acquire in the parameter of setting value.
Several navigation multidate informations of acquisition ship and the method for oil consumption are the following steps are included: AA1) it acquires and uploads boat
Mobile state information and pollutant emission rate；AA2) respectively to the rate of change and pollutant of each navigation multidate information data
Being associated property of rate of discharge rate of change calculates；AA3 the navigation multidate information project data that the degree of association is lower than setting value) is reduced
Frequency acquisition.Reduction need to handle data volume, reduce data and transmit pressure, while influencing on precision of prediction little.
Valid data sample is verified and repaired before training neural network model in stepb, the method for verification are as follows:
Successively judge whether each data are preset exception about definite value, if abnormal about definite value, then the data check is abnormal
Data, conversely, being then verified as normal data；Then judge whether the data value is more than setting range, if being more than setting range,
The data check is abnormal data, conversely, being then verified as normal data；Then judge the difference of the data value Yu a preceding collection value
Whether value is more than setting range, if being more than setting range, which is abnormal data, conversely, being then verified as normal number
According to.Abnormal data differentiate and reparation can be improved prediction accuracy.
As shown in Fig. 2, being abnormal data restorative procedure flow diagram, the method for reparation are as follows: judge abnormal data consecutive number
It whether is normal data according to check results, abnormal data is used as normal data after replacing using the mean value of adjacent data if being
Subsequent calculating is participated in, conversely, then following the steps below: B1) data group of several continuous adjacents is taken, with one of data group
For reference data set, it is normalized；B2) calculate normalization after each data with 1 difference absolute value, find out difference
Maximum value Kmax；B3) calculate each and abnormal data with project data xiAssociation angle value δi,
Wherein, xiFor the value after the data normalization, ρ is the threshold of sensitivity, and the value of ρ is smaller, and the difference between data correlation degree is got over
Greatly；B4) with association angle value δiGreater than given threshold δ0Data xiConduct after the mean value substitution abnormal data of corresponding raw value
Normal data uses.
Above-mentioned embodiment is only a preferred solution of the present invention, not the present invention is made in any form
Limitation, there are also other variations and modifications on the premise of not exceeding the technical scheme recorded in the claims.
Claims (9)
1. a kind of Pollution From Ships object based on big data discharges method of real-time, which is characterized in that
The following steps are included: A) in marine exhaust discharge outlet installation flow sensor and pollutant load sensor, acquisition vessel
Several navigation multidate informations of oceangoing ship and pollutant emission rate；
B as effective sample data after) using collected navigation multidate information to use pollutant emission rate stamps, and training is refreshing
Through network model；
C it) in application, acquiring the navigation multidate information of ship, and imports neural network model and obtains real-time pollutant emission rate
Prediction sentences real-time pollutant emission rate prediction and real-time pollutant emission rate comparison if difference is more than given threshold
Disconnected Pollution From Ships object discharge is abnormal, on the contrary then repeat this step.
2. a kind of Pollution From Ships object based on big data according to claim 1 discharges method of real-time, feature exists
In, in step also acquire ship static parameter, and to the ship of multiple discharge capacities carry out data acquisition, formed it is multiple quiet
The data group of state parameter, navigation multidate information and pollutant emission rate, in step C, if the target ship discharge capacity of application
For the discharge capacity for not acquiring data, then by multiple static parameters of acquisition, navigation multidate information and pollutant emission rate number
Interpolation processing is carried out according to group, obtains static parameter, navigation multidate information and pollutant emission rate under target ship discharge capacity
Interpolated data group, and C is then entered step according to step B training neural network model using interpolated data group.
3. a kind of Pollution From Ships object based on big data according to claim 1 or 2 discharges method of real-time, feature
Be, it is described acquisition ship several navigation multidate informations and pollutant emission rate method the following steps are included:
A1 it) acquires and uploads navigation multidate information and pollutant emission rate；
A2) each navigation multidate information and being associated property of pollutant emission rate are calculated respectively；
A3 the navigation multidate information that the degree of association is lower than setting value) is rejected, remaining navigation multidate information is dynamic as subsequent navigation
State information collection project.
4. a kind of Pollution From Ships object based on big data according to claim 1 or 2 discharges method of real-time, feature
Be, it is described acquisition ship several navigation multidate informations and oil consumption method the following steps are included:
AA1 it) acquires and uploads navigation multidate information and pollutant emission rate；
AA2) rate of change of each navigation multidate information data is associated with pollutant emission rate rate of change respectively
Property calculate；
AA3 the navigation multidate information project data frequency acquisition that the degree of association is lower than setting value) is reduced.
5. a kind of Pollution From Ships object based on big data according to claim 3 discharges method of real-time, feature exists
In, it is described acquisition ship several navigation multidate informations and oil consumption method the following steps are included:
AA1 it) acquires and uploads navigation multidate information and pollutant emission rate；
AA2) rate of change of each navigation multidate information data is associated with pollutant emission rate rate of change respectively
Property calculate；
AA3 the navigation multidate information project data frequency acquisition that the degree of association is lower than setting value) is reduced.
6. a kind of Pollution From Ships object based on big data according to claim 1 or 2 discharges method of real-time, feature
It is, valid data sample is verified and repaired before training neural network model in stepb, the method for the verification
Are as follows: successively judge whether each data are preset exception about definite value, if abnormal about definite value, then the data check is different
Regular data, conversely, being then verified as normal data；Then judge whether the data value is more than setting range, if being more than setting range,
Then the data check is abnormal data, conversely, being then verified as normal data；Then judge the data value and a preceding collection value
Whether difference is more than setting range, if being more than setting range, which is abnormal data, conversely, being then verified as normal
Data.
7. a kind of Pollution From Ships object based on big data according to claim 3 discharges method of real-time, feature exists
In, valid data sample is verified and repaired before training neural network model in stepb, the method for the verification are as follows:
Successively judge whether each data are preset exception about definite value, if abnormal about definite value, then the data check is abnormal
Data, conversely, being then verified as normal data；Then judge whether the data value is more than setting range, if being more than setting range,
The data check is abnormal data, conversely, being then verified as normal data；Then judge the difference of the data value Yu a preceding collection value
Whether value is more than setting range, if being more than setting range, which is abnormal data, conversely, being then verified as normal number
According to.
8. a kind of Pollution From Ships object based on big data according to claim 6 discharges method of real-time, feature exists
In the method for the reparation are as follows: judge whether abnormal data adjacent data check results are normal data, the abnormal number if being
Subsequent calculating is participated in as normal data after replacing according to the mean value using adjacent data, conversely, then following the steps below:
B1 the data group for) taking several continuous adjacents is normalized using one of data group as reference data set；
B2) calculate normalization after each data with 1 difference absolute value, find out the maximum value K of differencemax；
B3) calculate each and abnormal data with project data xiAssociation angle value δi,
Wherein, xiFor the value after the data normalization, ρ is the threshold of sensitivity, and the value of ρ is smaller, and the difference between data correlation degree is got over
Greatly；
B4) with association angle value δiGreater than given threshold δ0Data xiMake after the mean value substitution abnormal data of corresponding raw value
For normal data use.
9. a kind of Pollution From Ships object based on big data according to claim 7 discharges method of real-time, feature exists
In the method for the reparation are as follows: judge whether abnormal data adjacent data check results are normal data, the abnormal number if being
Subsequent calculating is participated in as normal data after replacing according to the mean value using adjacent data, conversely, then following the steps below:
B1 the data group for) taking several continuous adjacents is normalized using one of data group as reference data set；
B2) calculate normalization after each data with 1 difference absolute value, find out the maximum value K of differencemax；
B3) calculate each and abnormal data with project data xiAssociation angle value δi,
Wherein, xiFor the value after the data normalization, ρ is the threshold of sensitivity, and the value of ρ is smaller, and the difference between data correlation degree is got over
Greatly；
B4) with association angle value δiGreater than given threshold δ0Data xiMake after the mean value substitution abnormal data of corresponding raw value
For normal data use.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810871938.9A CN109063910A (en) | 2018-08-02 | 2018-08-02 | A kind of Pollution From Ships object discharge method of real-time based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810871938.9A CN109063910A (en) | 2018-08-02 | 2018-08-02 | A kind of Pollution From Ships object discharge method of real-time based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063910A true CN109063910A (en) | 2018-12-21 |
Family
ID=64832803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810871938.9A Pending CN109063910A (en) | 2018-08-02 | 2018-08-02 | A kind of Pollution From Ships object discharge method of real-time based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063910A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109855688A (en) * | 2019-02-28 | 2019-06-07 | 武汉理工大学 | A kind of inland harbour marine exhaust discharge Measurement Method |
| CN110244016A (en) * | 2019-07-16 | 2019-09-17 | 中国矿业大学(北京) | The measuring method and equipment of organic pollutant degradation rate |
| CN110705797A (en) * | 2019-10-09 | 2020-01-17 | 浙江海洋大学 | A method for predicting ship fuel consumption data based on ship sensor network |
| CN111008735A (en) * | 2019-11-27 | 2020-04-14 | 巴斯夫新材料有限公司 | Predictive Emissions Management System and Method |
| CN111046491A (en) * | 2019-11-28 | 2020-04-21 | 中国船舶工业系统工程研究院 | Method and device for estimating oil consumption of large ship diesel engine |
| CN111289690A (en) * | 2019-08-19 | 2020-06-16 | 浙江海洋大学 | AIS-based regional ship carbon emission monitoring method |
| CN111476699A (en) * | 2020-04-26 | 2020-07-31 | 浙江蓝景科技有限公司 | Ship pollutant supervision method and device |
| CN111811572A (en) * | 2020-06-12 | 2020-10-23 | 江苏奥畋工程科技有限公司 | Ship exhaust emission real-time monitoring method based on big data |
| CN111858140A (en) * | 2020-07-10 | 2020-10-30 | 江苏神彩科技股份有限公司 | Method, device, server and medium for checking pollutant monitoring data |
| CN112132541A (en) * | 2020-09-21 | 2020-12-25 | 中华人民共和国崇明海事局 | Method for rapidly judging illegal ship pollution discharge |
| CN113011811A (en) * | 2021-02-09 | 2021-06-22 | 浙江蓝景科技有限公司 | Ship water pollutant collecting and transferring system and method |
| CN113051963A (en) * | 2019-12-26 | 2021-06-29 | 中移(上海)信息通信科技有限公司 | Garbage detection method and device, electronic equipment and computer storage medium |
| CN113112389A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Pollutant emission data monitoring method and system |
| CN114218231A (en) * | 2022-02-21 | 2022-03-22 | 杭州春来科技有限公司 | Ship tail gas monitoring data processing method and system and computer readable storage medium |
| CN114757296A (en) * | 2022-04-29 | 2022-07-15 | 广东技术师范大学 | A method and device for pollutant analysis based on collaborative data |
| CN115063427A (en) * | 2022-08-18 | 2022-09-16 | 中海油天津化工研究设计院有限公司 | Pollutant discharge monitoring image processing method for novel ship |
| CN119065312A (en) * | 2024-11-05 | 2024-12-03 | 江苏汉盛海洋装备技术有限公司 | An intelligent marine sewage discharge monitoring method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106053306A (en) * | 2016-05-31 | 2016-10-26 | 北京理工大学 | Large pollution source exhaust emission test system |
| CN106855559A (en) * | 2016-12-28 | 2017-06-16 | 浙江海洋大学 | Ship carbon emission monitoring method based on AIS systems |
-
2018
- 2018-08-02 CN CN201810871938.9A patent/CN109063910A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106053306A (en) * | 2016-05-31 | 2016-10-26 | 北京理工大学 | Large pollution source exhaust emission test system |
| CN106855559A (en) * | 2016-12-28 | 2017-06-16 | 浙江海洋大学 | Ship carbon emission monitoring method based on AIS systems |
Non-Patent Citations (1)
| Title |
|---|
| 董珂辰: "基于物联网的船舶油耗监测系统的设计", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109855688A (en) * | 2019-02-28 | 2019-06-07 | 武汉理工大学 | A kind of inland harbour marine exhaust discharge Measurement Method |
| CN110244016A (en) * | 2019-07-16 | 2019-09-17 | 中国矿业大学(北京) | The measuring method and equipment of organic pollutant degradation rate |
| CN110244016B (en) * | 2019-07-16 | 2020-06-05 | 中国矿业大学(北京) | Method and device for measuring degradation rate of organic pollutants |
| CN111289690A (en) * | 2019-08-19 | 2020-06-16 | 浙江海洋大学 | AIS-based regional ship carbon emission monitoring method |
| CN110705797A (en) * | 2019-10-09 | 2020-01-17 | 浙江海洋大学 | A method for predicting ship fuel consumption data based on ship sensor network |
| CN110705797B (en) * | 2019-10-09 | 2023-09-22 | 浙江海洋大学 | Ship fuel consumption data prediction method based on ship sensing network |
| CN111008735A (en) * | 2019-11-27 | 2020-04-14 | 巴斯夫新材料有限公司 | Predictive Emissions Management System and Method |
| CN111008735B (en) * | 2019-11-27 | 2023-06-02 | 巴斯夫新材料有限公司 | Predictive emissions management system and method |
| CN111046491A (en) * | 2019-11-28 | 2020-04-21 | 中国船舶工业系统工程研究院 | Method and device for estimating oil consumption of large ship diesel engine |
| CN113051963A (en) * | 2019-12-26 | 2021-06-29 | 中移(上海)信息通信科技有限公司 | Garbage detection method and device, electronic equipment and computer storage medium |
| WO2021218032A1 (en) * | 2020-04-26 | 2021-11-04 | 浙江蓝景科技有限公司 | Ship water pollutant supervision method and apparatus |
| CN111476699A (en) * | 2020-04-26 | 2020-07-31 | 浙江蓝景科技有限公司 | Ship pollutant supervision method and device |
| CN111811572A (en) * | 2020-06-12 | 2020-10-23 | 江苏奥畋工程科技有限公司 | Ship exhaust emission real-time monitoring method based on big data |
| CN111858140A (en) * | 2020-07-10 | 2020-10-30 | 江苏神彩科技股份有限公司 | Method, device, server and medium for checking pollutant monitoring data |
| CN111858140B (en) * | 2020-07-10 | 2021-08-27 | 神彩科技股份有限公司 | Method, device, server and medium for checking pollutant monitoring data |
| CN112132541A (en) * | 2020-09-21 | 2020-12-25 | 中华人民共和国崇明海事局 | Method for rapidly judging illegal ship pollution discharge |
| CN112132541B (en) * | 2020-09-21 | 2024-03-29 | 中华人民共和国崇明海事局 | Method for rapidly judging illegal sewage disposal of ship |
| CN113011811A (en) * | 2021-02-09 | 2021-06-22 | 浙江蓝景科技有限公司 | Ship water pollutant collecting and transferring system and method |
| CN113112389A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Pollutant emission data monitoring method and system |
| CN114218231A (en) * | 2022-02-21 | 2022-03-22 | 杭州春来科技有限公司 | Ship tail gas monitoring data processing method and system and computer readable storage medium |
| CN114757296A (en) * | 2022-04-29 | 2022-07-15 | 广东技术师范大学 | A method and device for pollutant analysis based on collaborative data |
| CN115063427B (en) * | 2022-08-18 | 2022-11-15 | 中海油天津化工研究设计院有限公司 | Pollutant discharge monitoring image processing method for novel ship |
| CN115063427A (en) * | 2022-08-18 | 2022-09-16 | 中海油天津化工研究设计院有限公司 | Pollutant discharge monitoring image processing method for novel ship |
| CN119065312A (en) * | 2024-11-05 | 2024-12-03 | 江苏汉盛海洋装备技术有限公司 | An intelligent marine sewage discharge monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063910A (en) | A kind of Pollution From Ships object discharge method of real-time based on big data | |
| CN106335601A (en) | Ship energy saving method based on big data collection and analysis | |
| CN109270237B (en) | Water quality monitoring analysis system based on big data | |
| CN109060014A (en) | A kind of marine exhaust discharge compliance determines and violation ship identification method and system | |
| CN104090595B (en) | Ship navigational speed optimizing device and method based on main engine energy efficiency and navigation environment | |
| CN107589100A (en) | A kind of bunker oil sulfur content sniff estimation algorithm | |
| CN111811572A (en) | Ship exhaust emission real-time monitoring method based on big data | |
| CN107563576A (en) | A kind of ship intelligence energy efficiency management system | |
| Perera et al. | Machine intelligence for energy efficient ships: A big data solution | |
| CN104199406B (en) | System and method for evidence obtaining in water body pollution-discharge cruise monitoring | |
| CN113187638B (en) | Method for diagnosing high sulfur content in fuel oil | |
| CN112650110B (en) | A comprehensive intelligent monitoring system and monitoring method for ship pollutant discharge | |
| CN103466041A (en) | Real-time optimizing energy-saving ship speed intelligent-analysis system | |
| CN113640490B (en) | River and lake water ecological environment monitoring device, system and method based on Internet of things | |
| CN113902288A (en) | Management system and method for water resource regulation and control and operation | |
| CN106292596A (en) | A kind of sewage treatment plant intelligent management expert diagnostic system | |
| CN112036076A (en) | A method and system for predicting fuel consumption of ships in inland waterways in the Yangtze River in complex operating conditions | |
| CN115017684A (en) | Intelligent energy efficiency management system for ship | |
| CN107589220B (en) | A kind of ship tail gas monitoring station site selecting method suitable for long and narrow navigation channel | |
| CN113052042B (en) | Pollutant emission source monitoring device and method | |
| CN102661881B (en) | Intelligent supervision system and method for emission of fuel exhaust gas and fine particles of motor vehicles and ships | |
| CN106855559A (en) | Ship carbon emission monitoring method based on AIS systems | |
| CN116007685B (en) | Intelligent recognition method and recognition system for sediment point positions of sewage pipe network | |
| CN208847544U (en) | A kind of intelligent device of tracing to the source of marine exhaust discharge | |
| Zeng et al. | A novel big data collection system for ship energy efficiency monitoring and analysis based on BeiDou system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |