CN115169434A - Method and system for extracting characteristic value of working condition of host based on K-means clustering algorithm - Google Patents
Method and system for extracting characteristic value of working condition of host based on K-means clustering algorithm Download PDFInfo
- Publication number
- CN115169434A CN115169434A CN202210665119.5A CN202210665119A CN115169434A CN 115169434 A CN115169434 A CN 115169434A CN 202210665119 A CN202210665119 A CN 202210665119A CN 115169434 A CN115169434 A CN 115169434A
- Authority
- CN
- China
- Prior art keywords
- host
- working condition
- average value
- characteristic
- working
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a host working condition characteristic value extraction method and a host working condition characteristic value extraction system based on a K-means clustering algorithm.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for extracting a characteristic value of a working condition of a host based on a K-means clustering algorithm.
Background
The daily operation of a ship is very costly and the effective operating time determines the profitability level of the owner. The main engine of the ship is a power device at the core of the ship, faults inevitably occur in the using process of the main engine, the faults seriously affect the normal operation of the ship, not only affect the normal operation of equipment, but also cause accidents in serious conditions, and even endanger the personal safety.
The performance of the ship main engine is an important index of the ship navigation state. In the field of intelligent ship big data mining operation, effective quantitative data classification is lacked when the performance of a host machine in ship navigation is analyzed at the present stage, modeling and optimization are usually performed on the host machine, but under different working conditions, the performance standards of the host machine are different, so that the division of the working conditions of the host machine has important significance for the research on the performance of the host machine. The existing working condition division method is single, multiple working conditions are based on single-level single-stage division, and certain limitation exists in practical application, particularly in analysis of massive real ship operation data.
The main engine working condition division is the main basis for realizing the main engine efficiency, the fault prediction and the operation analysis in the follow-up process. According to ship equipment information and navigation information acquired by a real ship and a physical prototype of the operation of a host, the working conditions of the host are reasonably divided, and a plurality of equipment parameters including parameters of a supercharger, parameters of cooling water and other complex mechanisms need to be considered.
In practical engineering applications, many equipment parameters are difficult to obtain and sometimes data loss occurs. The change of the working condition of the main engine is also influenced by temperature and machine aging, for example, the working conditions of the ship during the operation are different from the working conditions of the ship after the ship has been operated for many years, so that the reasonable operation working condition of the main engine of the ship divided according to the real ship data can lay a foundation for determining the pollutant emission of the ship, estimating the fuel consumption, estimating the performance evaluation of the main engine, diagnosing and predicting the faults of key equipment of the main engine and the like, and provides a reference basis for the management and maintenance of the equipment of the ship.
The working condition operation of the main engine is a coupled process, all main equipment can influence each other to cause the working condition to change, but the actual ship is difficult to comprehensively output parameters required by the physical model of the main engine operation, so that the working condition division has certain difficulty according to the existing method.
Disclosure of Invention
In order to solve the problems that the dividing method is single in the existing host working condition dividing process, and the limitation is large in practical application and massive real ship operation data analysis, the invention provides a host working condition characteristic value extracting method based on a K-means clustering algorithm. The invention also relates to a system for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm.
The technical scheme of the invention is as follows:
a host working condition characteristic value extraction method based on a K-means clustering algorithm is characterized by comprising the following steps:
data acquisition and processing steps: acquiring ship data, preprocessing the ship data, and selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters comprise host power, seawater temperature and host scavenging box temperature; calculating to obtain average values of all characteristic parameters in unit time, including a host power average value, a sea water temperature average value and a host scavenging box temperature average value;
a first working condition dividing step: extracting a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method to serve as a related characteristic parameter average value, and performing first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K mean clustering algorithm to obtain a plurality of host working conditions;
a second working condition division step: calculating a corresponding profile coefficient under each host working condition, continuously performing second-stage working condition division on the host working condition with the lowest profile coefficient by adopting a K-means clustering algorithm and combining a seawater temperature average value and a host scavenging air box temperature average value to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained in the second-stage working condition division step is the same as or different from the number of the host working conditions obtained in the first-stage working condition division step;
and (3) characteristic value extraction: and respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition dividing step and the second working condition dividing step, and integrating the calculation results to analyze the working performance of the hosts.
Preferably, in the second working condition division step, when the working condition division is performed at the second stage, an optimal host working condition number is calculated by using an elbow method, and the optimal host working condition number is used as the finally obtained host working condition number; and the characteristic value extraction step calculates the optimized characteristic value of each host working condition.
Preferably, in the data acquisition and processing step, the preprocessing includes deleting abnormal data in the ship data, and removing noise and standardizing data.
Preferably, in the data collecting and processing step, the characteristic parameters further include a host rotation speed, a ship speed, a host cylinder exhaust temperature and a host cylinder cooling water temperature.
Preferably, in the characteristic value extraction step, the characteristic values of the respective host machine operating conditions include an average value and a standard deviation of host machine power, an average value and a standard deviation of host machine rotating speed, an average value and a standard deviation of ship speed, an average value and a standard deviation of seawater temperature, an average value and a standard deviation of host machine cylinder exhaust temperature, an average value and a standard deviation of host machine cylinder cooling water temperature, and an average value and a standard deviation of host machine scavenging box temperature, which are calculated under the respective host machine operating conditions.
A host working condition characteristic value extraction system based on a K-means clustering algorithm is characterized by comprising a data acquisition processing module, a first working condition division module, a second working condition division module and a characteristic value extraction module which are connected in sequence,
the data acquisition and processing module: the method comprises the steps of collecting ship data, preprocessing the ship data, and selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters comprise host power, seawater temperature and host scavenging box temperature; calculating to obtain average values of all characteristic parameters in unit time, including a host power average value, a sea water temperature average value and a host scavenging air box temperature average value;
the first working condition division module: extracting a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method to serve as a related characteristic parameter average value, and performing first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K mean clustering algorithm to obtain a plurality of host working conditions;
the second working condition division module: calculating a corresponding profile coefficient under each host working condition, and continuously performing second-stage working condition division on the host working condition with the lowest profile coefficient by adopting a K-means clustering algorithm and combining a seawater temperature average value and a host scavenging box temperature average value to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained by the second-stage working condition division is the same as or different from the number of the host working conditions obtained by the first-stage working condition division;
the characteristic value extraction module: and respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition division module and the second working condition division module, and integrating the calculation results to analyze the working performance of the hosts.
Preferably, in the second working condition division module, when the second stage working condition division is performed, an optimal host working condition number is calculated by using an elbow method, and the optimal host working condition number is used as the finally obtained host working condition number; the characteristic value extraction module calculates the optimized characteristic values of the working conditions of each host.
Preferably, the preprocessing includes deleting abnormal data in the ship data, and removing noise and data normalization.
Preferably, the characteristic parameters further include a host rotation speed, a ship speed, a host cylinder exhaust temperature and a host cylinder cooling water temperature.
Preferably, the characteristic values of the various main engine working conditions comprise the average value and standard deviation of the main engine power, the average value and standard deviation of the main engine rotating speed, the average value and standard deviation of the ship speed, the average value and standard deviation of the seawater temperature, the average value and standard deviation of the main engine cylinder exhaust temperature, the average value and standard deviation of the main engine cylinder cooling water temperature and the average value and standard deviation of the main engine scavenging box temperature which are calculated under the various main engine working conditions.
The beneficial effects of the invention are as follows:
the invention provides a host working condition characteristic value extraction method based on a K-means clustering algorithm (K-means clustering algorithm for short), which is characterized in that correlation analysis is carried out on an average value of each characteristic parameter in ship data and a host power average value based on an F test method (or called as an F-test method), the host power and the characteristic parameter with the highest correlation are subjected to first-stage working condition division by adopting the K-means clustering algorithm to divide a plurality of host working conditions, then the profile coefficient of the host working conditions is calculated, and the host working conditions with the lowest profile coefficient are subjected to second-stage working condition division, namely secondary division, so that working condition identification and the availability of actual engineering can be effectively improved, and the characteristic value of each working condition is calculated. The method is easy to realize by adopting a K-means clustering algorithm, an F inspection method and the like, and in real-ship application, the ship host operation working condition can be really and effectively divided by adopting two-stage division on the host working condition, the accuracy of division of the host working condition is improved, and a foundation can be provided for further analyzing and optimizing the working performance of the ship and the host.
The invention also relates to a host working condition characteristic value extraction system based on the K-means clustering algorithm (K-means clustering algorithm for short), which corresponds to the host working condition characteristic value extraction method based on the K-means clustering algorithm and can be understood as a system for realizing the host working condition characteristic value extraction method based on the K-means clustering algorithm.
Drawings
FIG. 1 is a flow chart of the method for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm.
FIG. 2 is a preferred flow chart of the host working condition characteristic value extraction method based on the K-means clustering algorithm.
Detailed Description
The present invention will be described with reference to the accompanying drawings.
The invention relates to a host working condition characteristic value extraction method based on a K-means clustering algorithm (K-means clustering algorithm for short), a flow chart of the method is shown in figure 1, and the method sequentially comprises the following steps:
the method comprises the steps of data acquisition and processing, or further referred to as data acquisition and ship data preprocessing, firstly acquiring ship data, preprocessing the ship data, cleaning abnormal data in the ship data (data are lost and singular data are generated in the data acquisition process, and the data are removed), removing noise and standardizing the data, and then selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters preferably comprise host power, seawater temperature, host scavenging box temperature, host rotating speed, ship speed, host cylinder exhaust temperature, host cylinder cooling water temperature and the like; calculating to obtain the average value of each characteristic parameter in unit time (for example, ten minutes), such as the average value of the power of the main engine, the average value of the temperature of the seawater, the average value of the temperature of the scavenging air box of the main engine, the average value of the rotating speed of the main engine, the average value of the navigational speed of the ship, the average value of the exhaust temperature of the cylinder of the main engine, the average value of the cooling water temperature of the cylinder of the main engine, and the like.
Then, the working conditions of the ship main engine are divided into two stages based on a K-means clustering algorithm. A first working condition division step, namely a first-stage working condition division, extracting a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method (F-test method for short) as a related characteristic parameter average value, and performing the first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K-means clustering algorithm to obtain a plurality of host working conditions;
specifically, as shown in the preferred flowchart of fig. 2, the F-test method is first adopted to extract the average value of the characteristic parameter having the maximum correlation with the average value of the host power from the plurality of characteristic parameters, and the F-test method is calculated according to the following formula:
in the above formula, F is a calculated result score value, x 1 Is any characteristic parameter average value, x, other than the host power average value 2 Is the average value of the host power, n 1 Representing the mean value x of the characteristic parameter 1 Number of (2), x i1 Represents x 1 Ith value, n 2 Represents the average value x of the host power 2 Number of (2), x i2 Represents x 2 The ith value, fraction value F, being calculated from the mean value x of any characteristic parameter other than the mean value of the host power 1 Is calculated to obtain a result value S 1 And the host power x 2 Is calculated to obtain a result value S 2 And (4) comparing to obtain.
Substituting the average value of the power of the main engine, the average value of the temperature of seawater, the average value of the temperature of a scavenging box of the main engine, the average value of the rotating speed of the main engine, the average value of the navigational speed of a ship, the average value of the exhaust temperature of an air cylinder of the main engine and the average value of the cooling water temperature of a cooling water temperature of the air cylinder of the main engine into the formula in sequence for calculation to obtain a characteristic parameter A with the highest score value F as the average value of related characteristic parameters, and performing first-stage working condition division on the average value of the power of the main engine and the average value of the related characteristic parameters by adopting a K-means clustering algorithm to divide a plurality of working conditions of the main engine; the number of the main engine working conditions is preferably four, that is, it is determined that the number of the main engine working condition data obtained by dividing the first-stage working conditions is four, for example, the characteristic parameter a is divided into a high value and a low value, and the main engine power average value is also divided into a high value and a low value, so that there are four combinations, that is, four main engine working conditions.
And a second working condition division step, namely second-stage working condition division, calculating the corresponding profile coefficient under each host working condition, and continuously carrying out second-stage working condition division on the host working condition with the lowest profile coefficient by adopting a K-means clustering algorithm and combining the average value of the seawater temperature and the average value of the temperature of the host scavenging air box to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained in the second-stage working condition division step is the same as or different from that obtained in the first-stage working condition division step.
Specifically, according to the four host working conditions divided in the first working condition dividing step, the profile coefficient SC of the corresponding data cluster under each host working condition is calculated, and the profile coefficient SC is calculated according to the following formula:
in the above formula, the data point I belongs to the data cluster I (i.e. corresponding working condition), a (I) represents the average value of the distances from the data point I to other data points, C I Indicates that the data cluster I has C I A data point j represents the jth data point in the data cluster I, and d (I, j) represents the distance between I and j
In the above formula, b (i) represents the minimum value of the average of the distances from the data point i to other data points, C J Indicates that data cluster J has C J Data point J represents the jth data point in data cluster J, and d (i, J) represents the distance between i and J.
In the above equation, S (i) represents a calculation coefficient of the data point i.
In the above equation, SC represents a contour coefficient of the data cluster I.
After the corresponding profile coefficient SC under each host working condition is calculated, a K-means clustering algorithm is adopted, the average value of the sea water temperature and the average value of the temperature of the host scavenging box are used as input parameters of the K-means clustering algorithm, second-stage working condition division is continuously carried out on the host working condition with the lowest profile coefficient to obtain K host working conditions, an elbow method is adopted to calculate the optimal host working condition number n, the optimal host working condition number n is used as the finally obtained host working condition number (K = n), wherein K belongs to 1,2,3,4, n, m is sequentially introduced into an elbow method calculation formula to calculate the optimal host working condition number n, the host working condition number finally obtained by second-stage working condition division optimization is preferably four (n = 4), and the host working condition with the lowest profile coefficient is divided again to improve the identification of the host working condition and the availability of actual engineering. The elbow method has the following calculation formula:
in the above formula, C i Denotes the center of each data cluster, p is C i The data point of the data cluster formed by the center is, and n represents n data clusters. The most appropriate number of working conditions selected by the elbow method can reduce the blindness of secondary division working conditions, and the reliability of the working conditions is improved.
And (3) characteristic value extraction: and respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition dividing step and the second working condition dividing step, and integrating the calculation results to analyze the working performance of the hosts. Preferably, the characteristic value comprises a series of average values and standard deviations calculated under each host operating condition: the average value and standard deviation of the power of the main engine, the average value and standard deviation of the rotating speed of the main engine, the average value and standard deviation of the ship speed, the average value and standard deviation of the sea water temperature, the average value and standard deviation of the exhaust temperature of the cylinder of the main engine, the average value and standard deviation of the cooling water temperature of the cylinder of the main engine and the average value and standard deviation of the temperature of the scavenging air box of the main engine.
It should be noted that the average value of the main engine power, the average value of the main engine rotation speed, the average value of the ship speed, the average value of the sea water temperature, the average value of the main engine cylinder exhaust temperature, the average value of the main engine cylinder cooling water temperature and the average value of the main engine scavenging box temperature in the characteristic values of the working conditions of each main engine are all average values calculated by the average values of the characteristic parameters in the data acquisition processing step.
When four main machine working conditions are divided in the first working condition dividing step, dividing one main machine working condition secondary working condition with the lowest profile coefficient into n, so that the total number of the main machine working conditions obtained in the first working condition dividing step and the second working condition dividing step is 3+n, when n =4, namely the total number of the main machine working conditions obtained by two-stage division is 7, calculating the average value and the standard deviation of main machine power, the average value and the standard deviation of main machine rotating speed, the average value and the standard deviation of ship speed, the average value and the standard deviation of sea water temperature, the average value and the standard deviation of main machine cylinder exhaust temperature, the average value and the standard deviation of main machine cylinder cooling water temperature and the average value and the standard deviation of main machine scavenging box temperature under 3+n (for example 7) working conditions, integrating the calculation results to perform subsequent main machine performance analysis, and further analyzing the specific conditions of each main machine working condition. For example: the method comprises the steps that under the working condition of each host, parameters such as host power, host rotating speed, ship speed, seawater temperature, host cylinder exhaust temperature, host cylinder cooling water temperature and host scavenging box temperature are available, after the average value and standard deviation of each parameter are calculated, the maximum value and the minimum value of the average value and the standard deviation of each parameter can be obtained, the working condition of the current host can be analyzed according to the maximum value and the minimum value of the average value and the standard deviation of each parameter, and therefore the difference between the current host running parameter and the historical characteristic value under the working condition is compared, and whether the current host breaks down or has reduced performance is judged.
The invention also relates to a system for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm, which corresponds to the method for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm and can be understood as a system for realizing the method, the system comprises a data acquisition processing module, a first working condition division module, a second working condition division module and a characteristic value extraction module which are connected in sequence, and particularly,
the data acquisition and processing module is used for acquiring ship data, preprocessing the ship data and selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters comprise host power, seawater temperature and host scavenging box temperature; calculating to obtain average values of all characteristic parameters in unit time, including a host power average value, a sea water temperature average value and a host scavenging box temperature average value;
the first working condition division module extracts a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method to serve as a related characteristic parameter average value, and performs first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K mean value clustering algorithm to obtain a plurality of host working conditions;
the second working condition division module is used for calculating the corresponding profile coefficient under each host working condition, then adopting a K-means clustering algorithm and combining the average value of the seawater temperature and the average value of the temperature of the host scavenging air box to continuously carry out second-stage working condition division on the host working condition with the lowest profile coefficient to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained by the second-stage working condition division is the same as or different from the number of the host working conditions obtained by the first-stage working condition division;
and the characteristic value extraction module is used for respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition division module and the second working condition division module and integrating the calculation results to analyze the working performance of the hosts.
Preferably, in the second working condition division module, when the working condition division is performed at the second stage, the optimal host working condition number is calculated by adopting an elbow method, and the optimal host working condition number is taken as the finally obtained host working condition number; the characteristic value extraction module calculates the optimized characteristic values of the working conditions of each host.
Preferably, the preprocessing includes deleting abnormal data in the ship data, and removing noise and data normalization.
Preferably, the characteristic parameters further include a host rotation speed, a ship speed, a host cylinder exhaust temperature and a host cylinder cooling water temperature.
Preferably, the characteristic values of the working conditions of the main engine comprise the average value and the standard deviation of the power of the main engine, the average value and the standard deviation of the rotating speed of the main engine, the average value and the standard deviation of the navigational speed of the ship, the average value and the standard deviation of the seawater temperature, the average value and the standard deviation of the exhaust temperature of the main engine cylinder, the average value and the standard deviation of the cooling water temperature of the main engine cylinder and the average value and the standard deviation of the temperature of the scavenging air box of the main engine, which are calculated under the working conditions of the main engine.
The invention provides an objective and scientific host working condition characteristic value extraction method and system based on a K-means clustering algorithm, wherein correlation analysis is carried out based on an F-test inspection method, working condition division is carried out by adopting the K-means clustering algorithm, a profile coefficient is calculated by adopting a specific calculation method, working condition division is continuously carried out on the host working condition with the lowest profile coefficient, working condition identification and availability of actual engineering can be effectively improved, the running working condition of a ship host can be effectively divided by adopting two-stage division on the host working condition, the working condition division accuracy of the host can be improved, and a foundation can be provided for further analyzing and optimizing the working performance of a ship and the host.
It should be noted that the above-mentioned embodiments enable a person skilled in the art to more fully understand the invention, without restricting it in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A host working condition characteristic value extraction method based on a K-means clustering algorithm is characterized by comprising the following steps:
data acquisition and processing steps: the method comprises the steps of collecting ship data, preprocessing the ship data, and selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters comprise host power, seawater temperature and host scavenging box temperature; calculating to obtain average values of all characteristic parameters in unit time, including a host power average value, a sea water temperature average value and a host scavenging box temperature average value;
a first working condition dividing step: extracting a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method to serve as a related characteristic parameter average value, and performing first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K mean clustering algorithm to obtain a plurality of host working conditions;
a second working condition division step: calculating a corresponding profile coefficient under each host working condition, continuously performing second-stage working condition division on the host working condition with the lowest profile coefficient by adopting a K-means clustering algorithm and combining a seawater temperature average value and a host scavenging air box temperature average value to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained in the second-stage working condition division step is the same as or different from the number of the host working conditions obtained in the first-stage working condition division step;
and (3) characteristic value extraction: and respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition dividing step and the second working condition dividing step, and integrating the calculation results to analyze the working performance of the hosts.
2. The method for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm according to claim 1, wherein in the second working condition division step, when the working condition of the second stage is divided, an elbow method is adopted to calculate the optimal number of the working conditions of the host, and the optimal number of the working conditions of the host is used as the finally obtained number of the working conditions of the host; and the characteristic value extraction step calculates the optimized characteristic value of each host working condition.
3. The method for extracting the characteristic value of the working condition of the host computer based on the K-means clustering algorithm as claimed in claim 1, wherein in the step of data acquisition and processing, the preprocessing comprises deleting abnormal data in ship data, removing noise and standardizing data.
4. The method for extracting the characteristic value of the working condition of the host computer based on the K-means clustering algorithm as claimed in claim 1, wherein in the step of data acquisition and processing, the characteristic parameters further comprise the rotating speed of the host computer, the ship speed, the exhaust temperature of a cylinder of the host computer and the cooling water temperature of a cylinder of the host computer.
5. The method for extracting the characteristic value of the working condition of the host computer based on the K-means clustering algorithm as claimed in claim 4, wherein in the characteristic value extraction step, the characteristic value of each working condition of the host computer comprises the average value and the standard deviation of the power of the host computer, the average value and the standard deviation of the rotating speed of the host computer, the average value and the standard deviation of the navigational speed of the ship, the average value and the standard deviation of the temperature of seawater, the average value and the standard deviation of the exhaust temperature of the cylinder of the host computer, the average value and the standard deviation of the cooling water temperature of the cylinder of the host computer and the average value and the standard deviation of the temperature of the scavenging air box of the host computer, which are calculated under each working condition of the host computer.
6. A host working condition characteristic value extraction system based on a K-means clustering algorithm is characterized by comprising a data acquisition processing module, a first working condition division module, a second working condition division module and a characteristic value extraction module which are connected in sequence,
the data acquisition and processing module: acquiring ship data, preprocessing the ship data, and selecting a plurality of characteristic parameters from the preprocessed ship data, wherein the characteristic parameters comprise host power, seawater temperature and host scavenging box temperature; calculating to obtain average values of all characteristic parameters in unit time, including a host power average value, a sea water temperature average value and a host scavenging box temperature average value;
the first working condition division module: extracting a characteristic parameter average value with the maximum correlation with the host power average value by adopting an F test method to serve as a related characteristic parameter average value, and performing first-stage working condition division on the host power average value and the related characteristic parameter average value by adopting a K mean clustering algorithm to obtain a plurality of host working conditions;
the second working condition division module: calculating a corresponding profile coefficient under each host working condition, and continuously performing second-stage working condition division on the host working condition with the lowest profile coefficient by adopting a K-means clustering algorithm and combining a seawater temperature average value and a host scavenging box temperature average value to obtain a plurality of host working conditions, wherein the number of the host working conditions obtained by the second-stage working condition division is the same as or different from the number of the host working conditions obtained by the first-stage working condition division;
the characteristic value extraction module: and respectively calculating the characteristic values of the working conditions of the hosts obtained in the first working condition division module and the second working condition division module, and integrating the calculation results to analyze the working performance of the hosts.
7. The system for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm as claimed in claim 6, wherein in the second working condition division module, when the working condition of the second stage is divided, the optimal number of the working conditions of the host is further calculated by an elbow method, and the optimal number of the working conditions of the host is taken as the finally obtained number of the working conditions of the host; the characteristic value extraction module calculates the optimized characteristic values of the working conditions of each host.
8. The system for extracting the characteristic value of the working condition of the host computer based on the K-means clustering algorithm is characterized in that the preprocessing comprises deleting abnormal data in ship data, removing noise and standardizing data.
9. The system for extracting the characteristic value of the working condition of the host computer based on the K-means clustering algorithm is characterized in that the characteristic parameters further comprise the rotating speed of the host computer, the ship speed, the exhaust temperature of a cylinder of the host computer and the cooling water temperature of a cylinder of the host computer.
10. The system for extracting the characteristic value of the working condition of the host based on the K-means clustering algorithm according to claim 9, wherein the characteristic value of each working condition of the host comprises an average value and a standard deviation of power of the host, an average value and a standard deviation of rotating speed of the host, an average value and a standard deviation of navigational speed of a ship, an average value and a standard deviation of seawater temperature, an average value and a standard deviation of exhaust temperature of a cylinder of the host, an average value and a standard deviation of cooling water temperature of a cylinder of the host and an average value and a standard deviation of temperature of a scavenging air box of the host, which are calculated under each working condition of the host.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210665119.5A CN115169434B (en) | 2022-06-14 | 2022-06-14 | Host working condition characteristic value extraction method and system based on K-means clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210665119.5A CN115169434B (en) | 2022-06-14 | 2022-06-14 | Host working condition characteristic value extraction method and system based on K-means clustering algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115169434A true CN115169434A (en) | 2022-10-11 |
| CN115169434B CN115169434B (en) | 2023-09-19 |
Family
ID=83486289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210665119.5A Active CN115169434B (en) | 2022-06-14 | 2022-06-14 | Host working condition characteristic value extraction method and system based on K-means clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169434B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012089926A1 (en) * | 2010-12-31 | 2012-07-05 | Eniram Oy | A method for determining statistical distribution of characteristic parameters of a vessel |
| US20150286703A1 (en) * | 2014-04-08 | 2015-10-08 | International Business Machines Corporation | Adaptive variable selection for data clustering |
| CN105930629A (en) * | 2016-07-13 | 2016-09-07 | 大唐南京环保科技有限责任公司 | On-line fault diagnosis method based on massive amounts of operating data |
| CN106991524A (en) * | 2017-03-20 | 2017-07-28 | 国网江苏省电力公司常州供电公司 | A kind of platform area line loss per unit predictor method |
| CN108052707A (en) * | 2017-11-28 | 2018-05-18 | 中国船舶工业系统工程研究院 | A kind of ship's navigation operating mode division methods based on cluster analysis |
| CN112270312A (en) * | 2020-11-26 | 2021-01-26 | 中南林业科技大学 | Fan bearing fault diagnosis method and system, computer equipment and storage medium |
| CN112307688A (en) * | 2020-10-29 | 2021-02-02 | 中国舰船研究设计中心 | System and method for monitoring, managing and optimizing energy efficiency of electric propulsion ship |
| US20210065021A1 (en) * | 2018-12-17 | 2021-03-04 | Shenyang Institute Of Automation, Chinese Academy Of Sciences | Working condition state modeling and model correcting method |
| CN113128120A (en) * | 2021-04-22 | 2021-07-16 | 三一汽车起重机械有限公司 | Method for constructing typical running condition of automobile crane |
| CN113240201A (en) * | 2021-06-08 | 2021-08-10 | 兰州大学 | Method for predicting ship host power based on GMM-DNN hybrid model |
| CN113537386A (en) * | 2021-08-01 | 2021-10-22 | 大连海事大学 | Ship typical motion track self-adaptive mining method based on improved K-Medoids clustering |
| CN114254438A (en) * | 2021-12-23 | 2022-03-29 | 震兑工业智能科技有限公司 | Dynamic rotating speed fine adjustment method for optimizing ship speed |
-
2022
- 2022-06-14 CN CN202210665119.5A patent/CN115169434B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012089926A1 (en) * | 2010-12-31 | 2012-07-05 | Eniram Oy | A method for determining statistical distribution of characteristic parameters of a vessel |
| US20150286703A1 (en) * | 2014-04-08 | 2015-10-08 | International Business Machines Corporation | Adaptive variable selection for data clustering |
| CN105930629A (en) * | 2016-07-13 | 2016-09-07 | 大唐南京环保科技有限责任公司 | On-line fault diagnosis method based on massive amounts of operating data |
| CN106991524A (en) * | 2017-03-20 | 2017-07-28 | 国网江苏省电力公司常州供电公司 | A kind of platform area line loss per unit predictor method |
| CN108052707A (en) * | 2017-11-28 | 2018-05-18 | 中国船舶工业系统工程研究院 | A kind of ship's navigation operating mode division methods based on cluster analysis |
| US20210065021A1 (en) * | 2018-12-17 | 2021-03-04 | Shenyang Institute Of Automation, Chinese Academy Of Sciences | Working condition state modeling and model correcting method |
| CN112307688A (en) * | 2020-10-29 | 2021-02-02 | 中国舰船研究设计中心 | System and method for monitoring, managing and optimizing energy efficiency of electric propulsion ship |
| CN112270312A (en) * | 2020-11-26 | 2021-01-26 | 中南林业科技大学 | Fan bearing fault diagnosis method and system, computer equipment and storage medium |
| CN113128120A (en) * | 2021-04-22 | 2021-07-16 | 三一汽车起重机械有限公司 | Method for constructing typical running condition of automobile crane |
| CN113240201A (en) * | 2021-06-08 | 2021-08-10 | 兰州大学 | Method for predicting ship host power based on GMM-DNN hybrid model |
| CN113537386A (en) * | 2021-08-01 | 2021-10-22 | 大连海事大学 | Ship typical motion track self-adaptive mining method based on improved K-Medoids clustering |
| CN114254438A (en) * | 2021-12-23 | 2022-03-29 | 震兑工业智能科技有限公司 | Dynamic rotating speed fine adjustment method for optimizing ship speed |
Non-Patent Citations (4)
| Title |
|---|
| ALBERTO DIEZ-OLIVAN等: "Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score", 《NEUROCOMPUTING》, pages 97 - 107 * |
| YALING ZHANG, NA LIU, SHANGPING WANG: "A differential privacy protecting K-means clustering algorithm based on contour coefficients", 《 PLOS ONE》, pages 1 - 15 * |
| 沈泓;刘顺;: "基于K-means聚类算法的数据分析模型应用研究", 软件导刊, no. 03, pages 103 - 107 * |
| 高梓博;杜太利;张勇;黄连忠;: "聚类算法在船舶能效数据挖掘中的应用", 武汉理工大学学报(交通科学与工程版), no. 02, pages 286 - 290 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115169434B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113807570B (en) | XGBoost-based reservoir dam risk level assessment method and system | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN114282579A (en) | Aviation bearing fault diagnosis method based on variational modal decomposition and residual error network | |
| CN111190349A (en) | Method, system and medium for monitoring state and diagnosing fault of ship engine room equipment | |
| CN114676742A (en) | Power grid abnormal electricity utilization detection method based on attention mechanism and residual error network | |
| CN112685459A (en) | Attack source feature identification method based on K-means clustering algorithm | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN113076700A (en) | SVM-LDA rock burst machine learning prediction model method based on data analysis principle | |
| CN114386537A (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| CN113032912A (en) | Ship diesel engine fault detection method based on association rule | |
| CN115375026A (en) | Method for predicting service life of aircraft engine in multiple fault modes | |
| CN113918642A (en) | Data filtering, monitoring and early warning method based on power Internet of things equipment | |
| CN114878172A (en) | Method and system for extracting temperature signal characteristics of marine main engine cylinder | |
| CN116796271A (en) | Resident energy abnormality identification method | |
| CN114974306A (en) | Transformer abnormal voiceprint detection and identification method and device based on deep learning | |
| CN113469252A (en) | Extra-high voltage converter valve operation state evaluation method considering unbalanced samples | |
| CN113486698A (en) | Identification and prediction method, storage medium and system for hydrogen fuel cell operation | |
| CN115169434B (en) | Host working condition characteristic value extraction method and system based on K-means clustering algorithm | |
| CN116226693A (en) | Gaussian mixture model nuclear power operation condition division method based on density peak clustering | |
| CN115392710A (en) | Wind turbine generator operation decision method and system based on data filtering | |
| CN111210147B (en) | Sintering process operation performance evaluation method and system based on time sequence feature extraction | |
| CN114969638A (en) | Bridge performance abnormity early warning method based on modal equivalent standardization | |
| CN115310746A (en) | State evaluation method and system for main transmission system of wind generating set | |
| CN112883639A (en) | GIS equipment service life prediction device and method based on machine learning | |
| CN112990257A (en) | Reciprocating compressor fault diagnosis method based on principal component analysis and support vector machine |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |