CN115130790A - Ship electric energy quality detection method and device - Google Patents
Ship electric energy quality detection method and device Download PDFInfo
- Publication number
- CN115130790A CN115130790A CN202211050954.4A CN202211050954A CN115130790A CN 115130790 A CN115130790 A CN 115130790A CN 202211050954 A CN202211050954 A CN 202211050954A CN 115130790 A CN115130790 A CN 115130790A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- predicted
- working condition
- ship
- index
- 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
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (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)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of power quality detection, in particular to a method and a device for detecting the power quality of a ship. The method comprises the following steps: the method comprises the steps that through obtaining electric energy quality indexes of different working conditions of a ship in each navigation, a predicted electric energy index vector of the corresponding working condition of the ship in the next navigation is predicted; obtaining predicted power quality indexes according to the predicted power index vectors and corresponding weights, and obtaining difference degrees under different working conditions based on the predicted power quality indexes so as to divide the working conditions into a plurality of groups; obtaining a predicted power quality score of the group according to the confidence coefficient of each working condition in the group and the predicted power quality index; and then, a comprehensive predicted electric energy quality score is obtained according to the predicted electric energy consumption index and the predicted electric energy quality score of the ship under each working condition, so that the electric energy quality of the next navigation of the ship is judged more timely, and the accuracy of the electric energy quality evaluation of the ship is improved.
Description
Technical Field
The invention relates to the technical field of power quality detection, in particular to a method and a device for detecting the power quality of a ship.
Background
The quality of the electric energy refers to the quality of the electric energy in the electric power system, and the problem of the quality of the electric energy of the ship is increasingly prominent along with the wide application of power electronic devices on the ship and the continuous increase of the capacity of the electric power system of the ship; the reduction of the power quality not only affects the normal operation of the electrical equipment for the ship, but also may affect the failure of the electrical equipment and seriously harm the safety of the ship.
The traditional detection method for the ship power quality generally detects the power data indexes of the ship, but ignores the running condition of the ship, so that the traditional detection method for the power quality has poor adaptability; the electric energy quality of the ship is possibly reduced continuously in the continuous running process, early warning maintenance is required to be carried out in time, but the phenomenon that the electric energy quality of the ship does not reach the standard possibly occurs in the next navigation of the ship can only be analyzed through human experience by the conventional manual detection method, and the judgment accuracy is low.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a method and a device for detecting ship power quality, wherein the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for detecting ship power quality, including the following steps:
acquiring electric energy indexes of a ship under each working condition in one sailing, forming an electric energy index vector according to the electric energy indexes corresponding to each working condition, and distributing weight to each electric energy index in the electric energy index vector;
acquiring an electric energy index vector of each working condition of the ship in multi-navigation, inputting the electric energy index vector of the working condition in multi-navigation into a time convolution network, and outputting a predicted electric energy index vector of a corresponding working condition of the ship in next navigation; acquiring a predicted electric energy quality index of the working condition according to the predicted electric energy index vector and the weight of the corresponding electric energy index;
acquiring the difference degrees under different working conditions according to the predicted electric energy index vector and the predicted electric energy quality index under each working condition, and dividing the working conditions into a plurality of groups according to the difference degrees under different working conditions; obtaining the confidence coefficient of each working condition in the group, and obtaining the predicted electric energy quality score of the group according to the predicted electric energy quality index and the confidence coefficient of each working condition in the group;
and acquiring a predicted electric energy consumption index corresponding to each working condition of the ship in the next navigation, obtaining a comprehensive predicted electric energy quality score according to the predicted electric energy consumption index and the predicted electric energy quality score of each working condition in the group, and judging the electric energy quality of the ship in the next navigation according to the comprehensive predicted electric energy quality score.
Preferably, the step of obtaining the predicted power quality indicator of the operating condition according to the predicted power indicator vector and the weight of the corresponding power indicator includes:
and acquiring the product of each electric energy index and the corresponding weight in the predicted electric energy index vector, wherein the sum of the products of all the electric energy indexes and the corresponding weights is the predicted electric energy quality index of the current working condition.
Preferably, the loss function of the time convolution network is:
wherein, the first and the second end of the pipe are connected with each other,
is shown as
Predicting the mean square error of the data and the target data by the sub-time convolution network;
is shown as
And the weight corresponding to each electric energy index vector.
Preferably, the step of obtaining the difference degrees under different working conditions according to the predicted power index vector and the predicted power quality index under each working condition includes:
and acquiring a difference value of the predicted electric energy quality indexes between every two working conditions and the similarity between the predicted electric energy index vectors between the two working conditions, wherein the ratio of the difference value to the similarity is the difference degree.
Preferably, the step of obtaining the confidence level of each of the operating conditions in the group includes:
the electric energy consumption of each working condition in actual operation comprises active power and reactive power;
and acquiring a reactive power distribution coefficient of each working condition in operation, and acquiring the confidence coefficient of the working condition according to the reactive power distribution coefficient.
Preferably, the step of obtaining the confidence level of the working condition according to the reactive power distribution coefficient includes:
acquiring a reactive power sequence corresponding to the ship in navigation under any working condition, wherein the reactive power sequence is acquired by a reactive power distribution coefficient in the navigation; and calculating the variance of the reactive power sequence, wherein the confidence coefficient of each working condition is in a negative correlation relation with the variance.
Preferably, the step of obtaining the predicted power quality score of the group according to the predicted power quality index and the confidence thereof of each working condition in the group includes:
and acquiring the product of the predicted power quality index and the confidence coefficient of each working condition in the group, wherein the sum of the products of the predicted power quality indexes and the confidence coefficients of all the working conditions in the group is the predicted power quality score of the group.
Preferably, the comprehensive predicted power quality score has a positive correlation with the predicted power quality score and the power consumption index.
In a second aspect, another embodiment of the present invention provides a ship power quality detection apparatus, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, can implement the steps of the above method.
The invention has the following beneficial effects: in the embodiment of the invention, the electric energy index vector of each working condition of the ship in multi-time sailing is obtained and input into a network to obtain the predicted electric energy index vector corresponding to each working condition of the ship in the next sailing, the self data of the ship is predicted, the prediction accuracy can be improved, the method has strong adaptability, the predicted electric energy quality index is further obtained according to the predicted electric energy index vector and the weight corresponding to each electric energy index, the difference degree between every two working conditions is obtained according to the predicted electric energy quality index corresponding to each working condition, so that different working conditions are divided into different groups according to the difference degree, the confidence coefficient corresponding to each working condition in each group is obtained, the predicted electric energy quality score of the group is obtained according to the confidence coefficient of each working condition and the corresponding predicted electric energy quality index, and the predicted electric energy consumption index corresponding to each group is further predicted, and obtaining a comprehensive predicted power quality score corresponding to the next navigation of the ship according to the predicted power consumption index and the predicted power quality score, so that the power quality of the ship in the next navigation is judged, the accuracy of the power quality evaluation of the ship is improved, and the electrical equipment of the ship can be protected in time according to the predicted power quality result.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for detecting ship power quality according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, the structure, the characteristics and the effects of the method and the device for detecting the electric energy quality of the ship according to the present invention are provided with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment of the invention is mainly suitable for detecting the electric energy quality of the ship, and aims to solve the problems that the traditional detection method has poor adaptability and can not accurately predict the electric energy quality of subsequent sailing of the ship, the embodiment of the invention predicts the predicted electric energy index vector corresponding to each working condition when the ship sails next time by acquiring the electric energy index vector of each working condition in multiple sailing of the ship, further obtains the predicted electric energy quality index, dividing different working conditions into different groups according to the predicted power quality index corresponding to each working condition to obtain each group of predicted power quality scores, obtaining a comprehensive predicted electric energy quality score corresponding to the next navigation of the ship according to the predicted electric energy consumption index and the predicted electric energy quality score, therefore, the electric energy quality of the ship in the next navigation is judged, the accuracy of the electric energy quality evaluation of the ship is improved, and meanwhile, the electric equipment of the ship is protected in time according to the predicted electric energy quality.
The following describes a specific scheme of the method and device for detecting the ship electric energy quality in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting ship power quality according to an embodiment of the present invention is shown, where the method includes the following steps:
and S100, acquiring an electric energy index of the ship under each working condition in one-time navigation, forming an electric energy index vector according to the electric energy index corresponding to each working condition, and distributing weight to each electric energy index in the electric energy index vector.
The quality of the ship electric energy is a group of parameters representing the electric energy generated, distributed and used by the ship under various working conditions; the electric energy quality of the ship can affect the continuity, reliability and stability of a ship electric power system, and is an important guarantee for normal work of power propulsion, deck machinery, control and communication equipment and the like.
In the practical evaluation of the ship power quality, relevant indexes of safe operation of a ship system are considered, the selected indexes can definitely indicate the state of a ship power system, and 6 indexes such as voltage deviation, voltage fluctuation, frequency deviation, frequency fluctuation, harmonic waves, three-phase unbalance degree and the like in the ship operation are selected as power indexes for the ship power quality evaluation.
In the embodiment of the invention, the working conditions in the ship navigation are divided into a navigation working condition, an entry working condition, an exit working condition, a loading working condition, an unloading working condition, a berthing working condition and an emergency working condition.
In order to improve the efficiency of subsequent calculation, in the embodiment of the invention, the standard of China Classification is taken as a basis, each electric energy index is divided into five evaluation grades according to the actual situation, and the higher the grade is, the better the quality of the electric energy index at the moment is, namely, the value range of elements in the electric energy index vector corresponding to each working condition is 1-5.
Furthermore, an analytic hierarchy process is adopted to respectively distribute weights to six electric energy indexes according to the importance degree, namely the importance degree of each electric energy index, an evaluation matrix between every two electric energy indexes is established, the evaluation matrix represents the relative importance between every two indexes, and an importance ratio scale description is usually carried out by adopting a 1-9 scale method; in the embodiment of the invention, the evaluation matrix is determined by experts, so that the corresponding weight obtained according to the importance degree of each electric energy index is obtained.
Step S200, acquiring an electric energy index vector of each working condition of the ship in multi-navigation, inputting the electric energy index vector of the working condition in the multi-navigation into a time convolution network, and outputting a predicted electric energy index vector of a corresponding working condition of the ship in the next navigation; and obtaining the predicted electric energy quality index of the working condition according to the predicted electric energy index vector and the weight corresponding to the electric energy index.
In the step S100, the electric energy index vector of the ship under the current working condition is obtained, the electric energy index vector corresponding to each working condition of the ship during multiple sailing processes is obtained, and the variation trend of the electric energy index vector of the ship during the next sailing is predicted according to the obtained historical electric energy index vector data.
(1) The input of the time convolution network is a historical electric energy index vector;
(2) distributing the occupied proportion for each historical electric energy index vector, wherein the proportion of the latest electric energy index vector is the largest, and by analogy, dynamically adjusting the proportions of the rest historical electric energy index vectors;
(3) the loss function adopts a mean square error loss function;
(4) and the output of the time convolution network is a predicted electric energy index vector.
The iteration loss function is specifically as follows:
wherein the content of the first and second substances,
is shown as
Predicting the mean square error of the data and the target data by the sub-time convolution network;
is shown as
And the weight corresponding to each electric energy index vector.
And by analogy, acquiring an electric energy index vector corresponding to each working condition when the ship sails next time.
Furthermore, the product of each electric energy index in the predicted electric energy index vector and the corresponding weight of the electric energy index is obtained, and the sum of the products of all the electric energy indexes and the corresponding weights of the electric energy indexes is the predicted electric energy quality index of the current working condition. The electric energy quality index of the ship under each working condition is in positive correlation with the evaluation grade of the electric energy index and the weight of the electric energy index, the product of each electric energy index under the current working condition and the corresponding weight of the electric energy index is obtained, the sum of the products of all the electric energy indexes and the corresponding weights of the electric energy indexes is the electric energy quality index under the current working condition, and then the electric energy quality index is as follows:
wherein the content of the first and second substances,
to indicate the ship
The electric energy quality index of each working condition;
denotes the first
The weight of each power indicator;
is shown as
The evaluation grade corresponding to each electric energy index;
indicating the number of electric energy indicators, in an embodiment of the invention
。
Based on the method for calculating the same electric energy quality index, the predicted electric energy quality index corresponding to each working condition of the ship in the next navigation is obtained according to the predicted electric energy index vector corresponding to each working condition of the ship in the next navigation.
Step S300, acquiring difference degrees under different working conditions according to the predicted electric energy index vector and the predicted electric energy quality index under each working condition, and dividing the working conditions into a plurality of groups according to the difference degrees under the different working conditions; and obtaining the confidence coefficient of each working condition in the group, and obtaining the predicted electric energy quality score of the group according to the predicted electric energy quality index and the confidence coefficient of each working condition in the group.
In step S200, the predicted electric energy index vector and the predicted electric energy quality index corresponding to each working condition of the ship in the next sailing are obtained, the electric energy quality of the ship is further specifically evaluated, the difference degree of each two different working conditions is obtained, and the different working conditions are divided into a plurality of groups according to the difference degree.
And acquiring a difference value of the predicted electric energy quality indexes between every two working conditions and the similarity between the predicted electric energy index vectors between the two working conditions, wherein the ratio of the difference value to the similarity is the difference degree. Specifically, the difference degree under every two different working conditions is obtained as follows:
wherein the content of the first and second substances,
is shown as
An operating condition and
the degree of difference between the individual operating conditions;
is shown as
Predicted electric energy index vector and the second of each working condition
Similarity among predicted electric energy index vectors of the working conditions;
is shown as
Predicting the power quality index of each working condition;
denotes the first
The predicted power quality index of each working condition.
Preferably, in the embodiment of the present invention, the second step is calculated by a cosine similarity method
Predicted electric energy index vector and the second of each working condition
The similarity between the predicted power indicator vectors of the respective operating conditions may be determined by using common means such as euclidean distance or pearson correlation method in other embodiments.
By analogy, the difference degree between any two working conditions of the ship in the next navigation is obtained, the working conditions with smaller difference degree are divided into a group for analysis, and the subsequent calculated amount is effectively reduced. In the embodiment of the invention, all working conditions are grouped by adopting a k-means mean clustering algorithm, and the electric energy quality indexes of the working conditions in each group are similar.
Further, the electric energy consumption of each working condition in actual operation is divided into active power and reactive power; acquiring a reactive power distribution coefficient of each working condition in operation, and acquiring a corresponding reactive power sequence of a ship in navigation under any working condition, wherein the reactive power sequence is acquired by the reactive power distribution coefficient in navigation; and calculating the variance of the reactive power sequence, wherein the confidence coefficient of each working condition is in a negative correlation relation with the variance.
Specifically, the consumption of the electric energy power of the ship in the normal sailing process can be divided into two categories of active power and reactive power, and the reactive power can greatly affect the electric energy quality when being larger, so that the reactive power distribution coefficients of the ship sailing under different working conditions are acquired.
In the embodiment of the invention, a variable frequency power meter is arranged in a ship power supply allocation center, the total power and reactive power of electrical equipment in operation are obtained, and the reactive power distribution coefficient under each working condition is obtained; in the embodiment of the invention, the reactive power sequence of each working condition of the ship is acquired at the frequency of updating once every 5 seconds.
Calculating the variance of the reactive power sequence corresponding to each working condition, and acquiring the confidence corresponding to each working condition in the group according to the variance as follows:
wherein the content of the first and second substances,
is shown as
The confidence corresponding to each working condition;
is shown as
And the variance of the reactive power sequence corresponding to each working condition.
Further, the product of the predicted power quality index and the confidence coefficient of each working condition in the group is obtained, and the sum of the products of the predicted power quality indexes and the confidence coefficients of all the working conditions in the group is the predicted power quality score of the group; the method for obtaining the predicted power quality score of the group according to the predicted power quality index and the confidence corresponding to each working condition in the group comprises the following steps:
wherein, the first and the second end of the pipe are connected with each other,
is shown as
A predicted power quality score corresponding to the group;
is shown as
In a group
Predicting power quality indexes corresponding to the working conditions;
is shown as
In a group
And the confidence corresponding to each working condition.
And S400, acquiring a predicted electric energy consumption index corresponding to each working condition of the ship in the next navigation, obtaining a comprehensive predicted electric energy quality score according to the predicted electric energy consumption index and the predicted electric energy quality score of each group of working conditions, and judging the electric energy quality of the ship in the next navigation according to the comprehensive predicted electric energy quality score.
The corresponding power consumption of the ship is different when the ship navigates under different working conditions, so that the power consumption index of the storage battery under each working condition of the ship in historical navigation is obtained, and the predicted power consumption index corresponding to each working condition of the ship in the next navigation process is obtained based on the method for obtaining the same predicted power quality index in the step S200; based on the grouping of different working conditions in the step S300, the proportion of the predicted electric energy consumption index corresponding to all the working conditions in each group to the total predicted electric energy consumption index of the working conditions in all the groups is used as the weight of the group, the comprehensive predicted electric energy quality score is in positive correlation with the predicted electric energy quality score and the electric energy consumption index, and then the comprehensive predicted electric energy quality score of the ship in the next navigation is calculated as:
wherein the content of the first and second substances,
representing a comprehensive predicted power quality score of the ship at the next voyage;
is shown as
The predicted power quality scores corresponding to the groups are scored;
is shown as
The predicted power consumption index corresponding to each group accounts for the total predicted power consumption index of all the working conditions in the group, i.e. the first
And the corresponding weights are grouped.
And manually setting an electric energy quality risk early warning value, and timely protecting the electrical equipment supplied by the storage battery in the next navigation when the obtained comprehensive prediction electric energy quality score is lower than the electric energy quality risk early warning value.
In summary, in the embodiment of the present invention, an electric energy index vector of each working condition of a ship in multiple sailing is obtained, a plurality of electric energy index vectors are input into a time convolution network to obtain a predicted electric energy index vector corresponding to each working condition of the ship in the next sailing, a predicted electric energy quality index is further obtained according to the predicted electric energy index vector and a weight corresponding to each electric energy index, a difference degree between each two working conditions is obtained according to the predicted electric energy quality index corresponding to each working condition, thereby dividing different working conditions into different groups according to the difference degree, obtaining a confidence degree of each working condition in each group, obtaining a predicted electric energy quality score of the group according to the confidence degree of each working condition and the corresponding predicted electric energy quality index, further predicting a predicted electric energy consumption index corresponding to each group, and obtaining a comprehensive predicted electric energy quality score corresponding to the next sailing of the ship according to the predicted electric energy consumption index and the predicted electric energy quality score, therefore, the electric energy quality of the ship during the next navigation is judged, the accuracy of the electric energy quality evaluation of the ship is improved, the prediction is carried out according to the data of the ship, the adaptability is strong, and meanwhile, the electric equipment of the ship is protected in time according to the predicted electric energy quality.
Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides a ship electric energy quality detection device, which comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor, when executing the computer program, implements the steps in one embodiment of the ship power quality detection method, such as the steps shown in fig. 1. The method for detecting the power quality of the ship has been described in detail in the above embodiments, and is not described again.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
Claims (9)
1. A ship electric energy quality detection method is characterized by comprising the following steps:
acquiring electric energy indexes of a ship under each working condition in one sailing, forming an electric energy index vector according to the electric energy indexes corresponding to each working condition, and distributing weight to each electric energy index in the electric energy index vector;
acquiring an electric energy index vector of each working condition of the ship in multi-navigation, inputting the electric energy index vector of the working condition in multi-navigation into a time convolution network, and outputting a predicted electric energy index vector of the corresponding working condition of the ship in next navigation; acquiring a predicted electric energy quality index of the working condition according to the predicted electric energy index vector and the weight of the corresponding electric energy index;
acquiring the difference degrees under different working conditions according to the predicted electric energy index vector and the predicted electric energy quality index under each working condition, and dividing the working conditions into a plurality of groups according to the difference degrees under different working conditions; obtaining the confidence coefficient of each working condition in the group, and obtaining the predicted electric energy quality score of the group according to the predicted electric energy quality index and the confidence coefficient of each working condition in the group;
and acquiring a predicted electric energy consumption index corresponding to each working condition of the ship in the next navigation, obtaining a comprehensive predicted electric energy quality score according to the predicted electric energy consumption index and the predicted electric energy quality score of each working condition in the group, and judging the electric energy quality of the ship in the next navigation according to the comprehensive predicted electric energy quality score.
2. The method of claim 1, wherein the step of obtaining the predicted power quality indicator for the operating condition based on the predicted power indicator vector and the weight corresponding to the power indicator comprises:
and acquiring the product of each electric energy index and the corresponding weight in the predicted electric energy index vector, wherein the sum of the products of all the electric energy indexes and the corresponding weights is the predicted electric energy quality index of the current working condition.
3. The method of claim 1, wherein the loss function of the time convolutional network is:
wherein the content of the first and second substances,
denotes the first
Predicting the mean square error of the data and the target data by using a secondary time convolution network;
denotes the first
And the weight corresponding to each electric energy index vector.
4. The method according to claim 1, wherein the step of obtaining the difference degree under different working conditions according to the predicted power index vector and the predicted power quality index under each working condition comprises:
and acquiring a difference value of predicted electric energy quality indexes between every two working conditions and the similarity between predicted electric energy index vectors between the two working conditions, wherein the ratio of the difference value to the similarity is the difference degree.
5. The method of claim 1, wherein said step of obtaining a confidence level for each of said operating conditions in said group comprises:
the electric energy consumption of each working condition in actual operation comprises active power and reactive power;
and acquiring a reactive power distribution coefficient of each working condition in operation, and acquiring the confidence coefficient of the working condition according to the reactive power distribution coefficient.
6. The method of claim 5, wherein the step of obtaining the confidence level of the operating condition based on the reactive power distribution coefficient comprises:
acquiring a reactive power sequence corresponding to the ship in navigation under any working condition, wherein the reactive power sequence is acquired by a reactive power distribution coefficient in the navigation; and calculating the variance of the reactive power sequence, wherein the confidence coefficient of each working condition is in a negative correlation relation with the variance.
7. The method of claim 1, wherein the step of obtaining the predicted power quality score of the group according to the predicted power quality indicator and the confidence level thereof for each operating condition in the group comprises:
and acquiring the product of the predicted power quality index and the confidence coefficient of each working condition in the group, wherein the sum of the products of the predicted power quality indexes and the confidence coefficients of all the working conditions in the group is the predicted power quality score of the group.
8. The method of claim 1, wherein the aggregate predicted power quality score is positively correlated to the predicted power quality score and the power consumption indicator.
9. A ship power quality detection apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of claim 1 when executing the computer program
8 the steps of any one of the methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211050954.4A CN115130790B (en) | 2022-08-30 | 2022-08-30 | Ship electric energy quality detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211050954.4A CN115130790B (en) | 2022-08-30 | 2022-08-30 | Ship electric energy quality detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115130790A true CN115130790A (en) | 2022-09-30 |
| CN115130790B CN115130790B (en) | 2022-11-25 |
Family
ID=83387806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211050954.4A Active CN115130790B (en) | 2022-08-30 | 2022-08-30 | Ship electric energy quality detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115130790B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565574A (en) * | 2011-12-06 | 2012-07-11 | 中国人民解放军海军工程大学 | Ship electric energy quality monitoring system |
| CN110930049A (en) * | 2019-11-29 | 2020-03-27 | 西安交通大学 | Method for comprehensively evaluating electric energy quality of regional power distribution network |
| CN111177650A (en) * | 2019-12-18 | 2020-05-19 | 国网浙江省电力有限公司绍兴供电公司 | Power quality monitoring and comprehensive evaluation system and method for power distribution network |
| CN112614020A (en) * | 2021-03-03 | 2021-04-06 | 天津中海油能源发展油田设施管理有限公司 | Electric propulsion state evaluation system based on electric energy quality |
| CN113240261A (en) * | 2021-05-07 | 2021-08-10 | 杭州巨奥能源科技有限公司 | Regional power quality monitoring and analyzing system |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
-
2022
- 2022-08-30 CN CN202211050954.4A patent/CN115130790B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565574A (en) * | 2011-12-06 | 2012-07-11 | 中国人民解放军海军工程大学 | Ship electric energy quality monitoring system |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
| CN110930049A (en) * | 2019-11-29 | 2020-03-27 | 西安交通大学 | Method for comprehensively evaluating electric energy quality of regional power distribution network |
| CN111177650A (en) * | 2019-12-18 | 2020-05-19 | 国网浙江省电力有限公司绍兴供电公司 | Power quality monitoring and comprehensive evaluation system and method for power distribution network |
| CN112614020A (en) * | 2021-03-03 | 2021-04-06 | 天津中海油能源发展油田设施管理有限公司 | Electric propulsion state evaluation system based on electric energy quality |
| CN113240261A (en) * | 2021-05-07 | 2021-08-10 | 杭州巨奥能源科技有限公司 | Regional power quality monitoring and analyzing system |
Non-Patent Citations (1)
| Title |
|---|
| 张文保等: "基于层次分析―模糊综合评估法的电力推进船舶电能质量实时评估系统", 《中国舰船研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115130790B (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110516821B (en) | Ship maintenance resource allocation optimization method and device | |
| CN102170131B (en) | Limit power calculating method of associated electricity transmission cross-section based on parallel calculating model | |
| CN115130790B (en) | Ship electric energy quality detection method and device | |
| CN113459867A (en) | Electric vehicle charging process fault early warning method based on adaptive deep confidence network | |
| CN112069727A (en) | Intelligent transient stability evaluation system and method with high reliability for power system | |
| CN115308465A (en) | Power supply potential safety hazard intelligent diagnosis system and method based on BP-SOM combined neural network | |
| CN116467667A (en) | Power failure monitoring and early warning method and system based on data fusion | |
| CN112541634B (en) | Method and device for predicting top-layer oil temperature and discriminating false alarm and storage medium | |
| CN113139639A (en) | MOMBI-based smart city application-oriented multi-target calculation migration method and device | |
| CN114970856A (en) | Model pruning method, device, equipment and storage medium based on hardware characteristics | |
| CN112636380B (en) | Alternating current and direct current power distribution system characteristic value analysis method based on Gehr circle theory | |
| CN115204698A (en) | Real-time analysis method for power supply stability of low-voltage transformer area | |
| CN113723705A (en) | Ship speed prediction and safe speed control method based on big data mining | |
| CN111814394A (en) | Power system safety assessment method based on correlation and redundancy detection | |
| CN116388296B (en) | Power angle stable control method and system based on sensitivity mapping | |
| CN113609756B (en) | Island distribution line drainage line operation failure evaluation method | |
| CN112598292A (en) | Comprehensive evaluation method and device for low-voltage treatment scheme | |
| CN113765153B (en) | New energy source limit access capability calculation method and system based on risk assessment | |
| CN117118085B (en) | Voltage load monitoring method based on intelligent operation and maintenance of distribution network | |
| CN117973859A (en) | Risk prevention and control method, device, equipment and medium for main distribution network | |
| Zhong et al. | Study on Improvement of Receiving Grid DC transmission feeding location Selection Method Using Principal Component Analysis | |
| Lo et al. | Using adaptive fuzzy inference system for voltage ranking | |
| CN116703001A (en) | Oil consumption prediction method and system of intelligent ship, intelligent ship and medium | |
| CN117973973A (en) | Special ship loading method and system for multi-target hybrid algorithm | |
| CN115796612A (en) | Charging pile health state detection method and device |
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 |