CN108573285A - A kind of experimental parameter clustering method towards dredging energy consumption - Google Patents
A kind of experimental parameter clustering method towards dredging energy consumption Download PDFInfo
- Publication number
- CN108573285A CN108573285A CN201810376684.3A CN201810376684A CN108573285A CN 108573285 A CN108573285 A CN 108573285A CN 201810376684 A CN201810376684 A CN 201810376684A CN 108573285 A CN108573285 A CN 108573285A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- similarity
- experimental parameter
- attribute
- degree
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The invention discloses a kind of experimental parameter clustering methods towards dredging energy consumption, include the following steps：(1) data information of energy consumption and experimental parameter in dredging operation is collected, and establishes corresponding sample matrix；(2) parametric data in sample matrix is standardized；（3）Each experimental parameter is carried out with energy consumption to the calculating of similarity respectively；（4）The similarity result calculated is analyzed, determines the correlation between each experimental parameter and energy consumption.The attainable advantageous effect of institute of the invention：It determines the correlation between the experimental parameter in dredging operation and energy consumption, realizes the purpose of low energy consumption, be of great significance to the correlation research of energy consumption in dredging operation and experimental parameter.
Description
Technical field
The present invention relates to the applications that the dredging energy consumption based on clustering is determined with experimental parameter correlation, belong to dredger
Journey field.
Background technology
Dredging work is the big event of water conservancy marine traffic engineering, to progress of human society, enhancement of environment and economic development
Effect is very great.Modern dredging work relies primarily on dredger to carry out, and process control parameter is numerous, makees in dredging at this stage
In industry, mainly based on manual operation.Even veteran operating personnel lead to qualitative survey since influence factor is numerous
Relative difficulty is tried, dredging operation is constantly in high energy consumption, low yield state.Therefore, it searches and the relevant work of dredging operation energy consumption
Skill parameter is particularly important.High yield, the low energy consumption for realizing dredging operation, reduce Operating Complexity, improve dredging operation
The degree of automation seems particularly urgent in today.
Invention content
It is an object of the invention to overcome drawbacks described above, using clustering, a kind of technique towards dredging energy consumption is provided
Parameter clustering method, the correlation between the energy consumption and experimental parameter of dredging operation are determined, and screening influences dredging
An important factor for operation, realizes the purpose of low energy consumption, improves dredging operation the degree of automation.
To achieve the above object, the technical solution adopted in the present invention is：A kind of experimental parameter towards dredging energy consumption is poly-
Alanysis method, it is characterised in that include the following steps:
Step (1)：Collect dredging operation in energy consumption and experimental parameter data information, determine p situational variables, list because
Variable and independent variable sample matrix；Wherein, p is positive integer；
Step (2)：Associated parametric data is standardized；
Step (3)：Calculating to each experimental parameter and energy consumption progress similarity of selection；
Step (4)：The similarity result calculated is analyzed, is determined related between each experimental parameter and energy consumption
Property.
Sample matrix in above-mentioned steps (1) is as follows：
If to p independent variable x1,x2,…,xpWith 1 dependent variable y1It has gone n times observation, has remembered independent variable and dependent variable respectively
The data matrix of " sample point × variable " type be：
Remember that sample matrix is
Matrix standardization is as follows in above-mentioned steps (2)：
The matrix that sample matrix is standardized after transformation is as follows,
Wherein, r=1,2 ..., n
HereFor independent variable xpObservation minimum value,For independent variable xpThe pole of observation
Difference；For dependent variable y1Observation minimum value,For dependent variable y1Observation it is very poor.Through
After crossing very poor normalization transformation, matrix FREach element value between 0~1.
The calculating of similarity is as follows in above-mentioned steps (3)：
Any one independent variable after being standardized is chosen, such asIt is two n dimensions
Data object, then xjWith y1Between similarity calculating can divide three steps calculate：
The first step compares, and measures the phase between single attribute from degree.It can be calculated by following formula：
Wherein, RjIndicate the variance of j-th of attribute；
Second step, it is comprehensive, the measurement results between each attribute are integrated, are formed to whole measurement results.It can be under
Formula calculates：
Wherein,Indicate the weight of j-th of attribute.
Third walks, and result is mapped between [0,1] by conversion.F indicates transfer function, can be calculated by following formula：
The first step, which calculates single attributes similarity, is laid the groundwork for second step synthesis, from single attributes similarity it can be seen that every
The similitude of group data, and comprehensive function is the synthesis to overall data, cannot therefrom find out the similitude between single group data.
Similarity result is analyzed as follows in the step (4)：
In the present invention, single attributes similarity that step (3) is calculated is to weigh the phase of single attribute from degree.Work as calculating
Be mutually from degree when, single attributes similarity value range is entire set of real numbers, and two elements are more similar, then value is smaller.
It is similar with list attributes similarity since synthesized attribute is held to the comprehensive of each attribute, when single attributes similarity
Calculate be mutually from degree when, two elements are more similar, then value is smaller.
The similarity finally calculated is the mapping to synthesized attribute.The value range of similarity is [0,1], the size of value
Indicate the similarity degree between element.I.e. when two elements are similar samples, the result of calculation of similarity more levels off to 1；When
When two element dissmilarities, the result of calculation of similarity more tends to 0.
The beneficial effects of the invention are as follows：The invention discloses a kind of experimental parameter clustering sides towards dredging energy consumption
Method is defined using the similarity in clustering, the similarity between energy consumption and experimental parameter by calculating dredging operation, really
Surely consumption and the correlation between each experimental parameter.A kind of method can be provided for the optimizing research of dredging operation energy consumption, realized low
The purpose of energy consumption is of great significance to energy consumption in dredging operation and the correlation determination of experimental parameter.
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Specific implementation mode
The invention will be further described with example below in conjunction with the accompanying drawings.Following instance is only used for clearly illustrating this
The technical solution of invention, and not intended to limit the protection scope of the present invention.
A kind of experimental parameter clustering method towards dredging energy consumption, it is characterised in that include the following steps:
Step (1)：Collect dredging operation in energy consumption and experimental parameter data information, determine p situational variables, list because
Variable and independent variable sample matrix；Wherein, p is positive integer；
Step (2)：Associated parametric data is standardized；
Step (3)：Calculating to each experimental parameter and energy consumption progress similarity of selection；
Step (4)：The similarity result calculated is analyzed, is determined related between each experimental parameter and energy consumption
Property.
Sample matrix in above-mentioned steps (1) is as follows：
If to p independent variable x1,x2,…,xpWith 1 dependent variable y1It has gone n times observation, has remembered independent variable and dependent variable respectively
The data matrix of " sample point × variable " type be：
Remember that sample matrix is
Matrix standardization is as follows in above-mentioned steps (2)：
The matrix that sample matrix is standardized after transformation is as follows,
Wherein, r=1,2 ..., n
HereFor independent variable xpObservation minimum value,For independent variable xpThe pole of observation
Difference；For dependent variable y1Observation minimum value,For dependent variable y1Observation it is very poor.Through
After crossing very poor normalization transformation, matrix FREach element value between 0~1.
The calculating of similarity is as follows in above-mentioned steps (3)：
Any one independent variable after being standardized is chosen, such asIt is two n dimensions
Data object, then xjWith y1Between similarity calculating can divide three steps calculate：
The first step compares, and measures the phase between single attribute from degree.It can be calculated by following formula：
Wherein, RjIndicate the variance of j-th of attribute；
Second step, it is comprehensive, the measurement results between each attribute are integrated, are formed to whole measurement results.It can be under
Formula calculates：
Wherein,Indicate the weight of j-th of attribute.
Third walks, and result is mapped between [0,1] by conversion.F indicates transfer function, can be calculated by following formula：
The first step, which calculates single attributes similarity, is laid the groundwork for second step synthesis, from single attributes similarity it can be seen that every
The similitude of group data, and comprehensive function is the synthesis to overall data, cannot therefrom find out the similitude between single group data.
Similarity result is analyzed as follows in the step (4)：
In the present invention, single attributes similarity that step (3) is calculated is to weigh the phase of single attribute from degree.Work as calculating
Be mutually from degree when, single attributes similarity value range is entire set of real numbers, and two elements are more similar, then value is smaller.
It is similar with list attributes similarity since synthesized attribute is held to the comprehensive of each attribute, when single attributes similarity
Calculate be mutually from degree when, two elements are more similar, then value is smaller.
The similarity finally calculated is the mapping to synthesized attribute.The value range of similarity is [0,1], the size of value
Indicate the similarity degree between element.I.e. when two elements are similar samples, the result of calculation of similarity more levels off to 1；When
When two element dissmilarities, the result of calculation of similarity more tends to 0.
The data acquired in real time using " day lion number " cutter suction dredger site operation below are illustrated as data source：
Step (1)：Collect the data information of energy consumption and experimental parameter in dredging operation, in this example, the technique of selection
Parameter has pipeline mean concentration, flow rate of pipelines, exit velocity, reamer to cut mud thickness, reamer forward travel distance, transverse moving speed, reamer
Depth, sludge pipe caliber totally 8 parameters.
Data source in this example collects in real time in " day lion number " cutter suction dredger site operation.
Array data is randomly selected from " day lion " number mass data collected, and establishes corresponding data matrix F, such as table
Shown in 1；
1 energy consumption of table and some processes parametric data
Step (2)：Sample matrix is standardized.
By step (2), the matrix in step (1) is standardized,
Matrix after transformation is as shown in table 2.
2 energy consumption of table and experimental parameter standardized data
Step (3)：Carry out the calculating of similarity with energy consumption respectively to the experimental parameter of selection.
The calculating that pipeline mean concentration (%) this experimental parameter carries out similarity with yield is chosen first.According to step
(3) formula provided is calculated, and show that the results are shown in Table 3：
The similarity of table 3 pipeline mean concentration and energy consumption
Similarly, the similarity between remaining each experimental parameter and energy consumption can be calculated, as shown in table 4：
Comprehensive similarity
Similarity between 4 experimental parameter of table and energy consumption
Step (4) analyzes the similarity result calculated, determines the correlation between each experimental parameter and energy consumption.
Can be obtained by table 2, the numerical value of each experimental parameter after standardization and energy consumption closer to when, single attribute is similar
Degree, comprehensive measurement result are all bigger, and similarity is then smaller.By 4 calculated result of table it is concluded that：It is choosing above
Experimental parameter in, the similitude highest of reamer forward travel distance and energy consumption, be followed successively by reamer cut mud thickness, sludge pipe caliber, twist
Knife depth, flow rate of pipelines, exit velocity, pipeline mean concentration, transverse moving speed.
The above is only a preferred embodiment of the present invention, it should be pointed out that：For the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvement and deformations are also answered
It is considered as protection scope of the present invention.
Claims (6)
1. a kind of experimental parameter clustering method towards dredging energy consumption, which is characterized in that include the following steps:
Step (1)：The data information for collecting energy consumption and experimental parameter in dredging operation, determines p situational variables, lists dependent variable
With independent variable sample matrix；Wherein, p is positive integer；
Step (2)：Related process parametric data is standardized；
Step (3)：Carry out the calculating of similarity with energy consumption respectively to the experimental parameter of selection；
Step (4)：The similarity result calculated is analyzed, determines the correlation between each experimental parameter and energy consumption.
2. a kind of experimental parameter clustering method towards dredging energy consumption according to claim 1, which is characterized in that institute
It states and lists dependent variable in step (1) and be specially with independent variable sample matrix：If to p independent variable x1,x2,…,xpWith 1 because becoming
Measure y1It has gone n times observation, has remembered that the data matrix of independent variable and " sample point × variable " type of dependent variable is as follows respectively：
Remember that sample matrix is
Wherein, aijFor xjIth measured value, br1For y1The r times measured value.
3. a kind of experimental parameter clustering method towards dredging energy consumption according to claim 2, which is characterized in that institute
It states in step (2) to being standardized specially to related process parametric data：
The step (2) is standardized specially associated parametric data：
Sample matrix in step (1) is standardized transformation, the matrix after transformation is as follows,
Wherein, For independent variable xpObservation minimum value,For independent variable xpObservation it is very poor；For
Dependent variable yqObservation minimum value,For dependent variable y1Observation it is very poor.
4. a kind of experimental parameter clustering method towards dredging energy consumption according to claim 3, which is characterized in that institute
Stating calculating of the experimental parameter in step (3) to selection respectively with energy consumption progress similarity is specially：Selection has been standardized
Treated any one independent variable,It is two n dimension data objects, calculates xjWith y1Between phase
Like degree.
5. a kind of experimental parameter clustering method towards dredging energy consumption according to claim 4, which is characterized in that institute
It states and calculates x in step (3)jWith y1Between similarity be divided into three steps, it is specific as follows：
The first step compares, and measures the phase between single attribute from degree, is calculated by formula (5)：
Wherein, RjIndicate the variance of j-th of attribute；For by xjWith y1Between phase from degree；
Second step, it is comprehensive, the measurement results between each attribute are integrated, are calculated by formula (6)：
Wherein,Indicate the weight of j-th of attribute, Mn(x) it is synthesis result
Third walks, conversion, and between synthesis result is mapped to [0,1], f indicates transfer function, is calculated by formula (8)：
6. a kind of experimental parameter clustering method towards dredging energy consumption according to claim 5, which is characterized in that institute
It states and the similarity result calculated is analyzed specially in step (4)：
In the step (3),
For similarity analysis between single attribute, it is to weigh the phase of single attribute from degree to measure single attributes similarity, works as calculating
Be mutually from degree when, single attributes similarity value range is entire set of real numbers, and two elements are got over mutually from then value is bigger；
Synthesis result is analyzed, since synthesized attribute is held to the comprehensive of each attribute, with list attributes similarity alanysis
Method is identical, when single attributes similarity calculate be separation degree when, two elements more detach, then value is bigger；
To synthesis result map analysis, the value range of similarity is [0,1], and the size of value indicates the similar journey between element
Degree, when two elements are similar samples, the result of calculation of similarity more levels off to 1；When two element dissmilarities, similarity
Result of calculation more tend to 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810376684.3A CN108573285A (en) | 2018-04-25 | 2018-04-25 | A kind of experimental parameter clustering method towards dredging energy consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810376684.3A CN108573285A (en) | 2018-04-25 | 2018-04-25 | A kind of experimental parameter clustering method towards dredging energy consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108573285A true CN108573285A (en) | 2018-09-25 |
Family
ID=63575226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810376684.3A Pending CN108573285A (en) | 2018-04-25 | 2018-04-25 | A kind of experimental parameter clustering method towards dredging energy consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108573285A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543144A (en) * | 2018-11-14 | 2019-03-29 | 河海大学常州校区 | Dredging yield or energy consumption experimental parameter screening technique based on main substrate analytic approach |
| CN110309966A (en) * | 2019-06-27 | 2019-10-08 | 河海大学常州校区 | Dredging energy consumption prediction technique based on Partial Least Squares |
| CN113221348A (en) * | 2021-05-08 | 2021-08-06 | 中交第三航务工程局有限公司 | Analysis method for operational environmental conditions of engineering ship |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995467A (en) * | 2014-05-26 | 2014-08-20 | 河海大学常州校区 | Method for extracting main components of dredging operation energy consumption influence factors based on partial least squares |
| CN104008647A (en) * | 2014-06-12 | 2014-08-27 | 北京航空航天大学 | Road traffic energy consumption quantization method based on motor vehicle running modes |
| CN105718426A (en) * | 2016-01-22 | 2016-06-29 | 河海大学常州校区 | Dredging output mathematical model building method based on multiple linear regression analysis |
| CN106709662A (en) * | 2016-12-30 | 2017-05-24 | 山东鲁能软件技术有限公司 | Electrical equipment operation condition classification method |
| CN107391939A (en) * | 2017-07-25 | 2017-11-24 | 河海大学 | A kind of basin similitude comprehensive evaluation index computational methods of quantization |
| CN107633274A (en) * | 2017-10-16 | 2018-01-26 | 湖南科技大学 | A kind of clustering method of rolling mill vibration operating mode division |
-
2018
- 2018-04-25 CN CN201810376684.3A patent/CN108573285A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103995467A (en) * | 2014-05-26 | 2014-08-20 | 河海大学常州校区 | Method for extracting main components of dredging operation energy consumption influence factors based on partial least squares |
| CN104008647A (en) * | 2014-06-12 | 2014-08-27 | 北京航空航天大学 | Road traffic energy consumption quantization method based on motor vehicle running modes |
| CN105718426A (en) * | 2016-01-22 | 2016-06-29 | 河海大学常州校区 | Dredging output mathematical model building method based on multiple linear regression analysis |
| CN106709662A (en) * | 2016-12-30 | 2017-05-24 | 山东鲁能软件技术有限公司 | Electrical equipment operation condition classification method |
| CN107391939A (en) * | 2017-07-25 | 2017-11-24 | 河海大学 | A kind of basin similitude comprehensive evaluation index computational methods of quantization |
| CN107633274A (en) * | 2017-10-16 | 2018-01-26 | 湖南科技大学 | A kind of clustering method of rolling mill vibration operating mode division |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543144A (en) * | 2018-11-14 | 2019-03-29 | 河海大学常州校区 | Dredging yield or energy consumption experimental parameter screening technique based on main substrate analytic approach |
| CN110309966A (en) * | 2019-06-27 | 2019-10-08 | 河海大学常州校区 | Dredging energy consumption prediction technique based on Partial Least Squares |
| CN110309966B (en) * | 2019-06-27 | 2022-08-02 | 河海大学常州校区 | Dredging energy consumption prediction method based on partial least square method |
| CN113221348A (en) * | 2021-05-08 | 2021-08-06 | 中交第三航务工程局有限公司 | Analysis method for operational environmental conditions of engineering ship |
| CN113221348B (en) * | 2021-05-08 | 2024-02-02 | 中交第三航务工程局有限公司 | Analysis method for engineering ship operable environmental conditions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104239970B (en) | A kind of conductor galloping method for prewarning risk based on Adaboost | |
| CN108573285A (en) | A kind of experimental parameter clustering method towards dredging energy consumption | |
| Dale et al. | Dinoflagellate cysts as environmental indicators in surface sediments from the Congo deep-sea fan and adjacent regions | |
| CN107341497A (en) | The unbalanced weighting data streams Ensemble classifier Forecasting Methodology of sampling is risen with reference to selectivity | |
| CN108985380B (en) | Point switch fault identification method based on cluster integration | |
| CN109784383B (en) | Rail crack identification method based on graph domain feature and DS evidence theory fusion | |
| CN104807589B (en) | A kind of ONLINE RECOGNITION method collecting flow pattern of gas-liquid two-phase flow in defeated-riser systems | |
| WO2011134881A1 (en) | Data processing method and system for checking pipeline leakage | |
| CN115081945B (en) | Damage monitoring and evaluating method and system for underground water environment monitoring well | |
| CN102313796A (en) | Soft measuring method of biochemical oxygen demand in sewage treatment | |
| CN109978039B (en) | Fan blade icing prediction method based on unbalanced data set | |
| CN103903441A (en) | Road traffic state distinguishing method based on semi-supervised learning | |
| CN110288196A (en) | Transmission line galloping grading forewarning system method and system | |
| CN103278616A (en) | Multi-factor method for rapidly evaluating soil corrosivity | |
| Khemiri et al. | The use of otolith shape to determine stock structure of Engraulis encrasicolus along the Tunisian coast | |
| CN113008806A (en) | Agricultural product production area heavy metal spatial distribution determination method | |
| CN113658640B (en) | Fresh water ecological system health evaluation method | |
| CN105425291A (en) | Advantageous phase method of palaeogeographic reconstruction | |
| DeForest et al. | Using fatty acids to fingerprint biofilm communities: a means to quickly and accurately assess stream quality | |
| CN108596489A (en) | A kind of experimental parameter clustering method towards dredging yield | |
| Kroeck et al. | Morphological variability of peteinoid acritarchs from the Middle Ordovician of Öland, Sweden, and implications for acritarch classification | |
| CN116205087A (en) | Rain and sewage drainage pipe network anomaly analysis method and device based on edge computing gateway | |
| CN104850910A (en) | Dredging technical parameter multi-attribute decision analysis method based on OWA | |
| CN104699977B (en) | Using the method for weight quantitative analysis of mineral material resource | |
| CN113076693A (en) | Road surface compaction quality evaluation method based on support vector machine and hidden horse model |
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: 20180925 |