CN118208374A - Working condition off-load loading integrated monitoring system and method for offshore wind power - Google Patents
Working condition off-load loading integrated monitoring system and method for offshore wind power Download PDFInfo
- Publication number
- CN118208374A CN118208374A CN202410473449.3A CN202410473449A CN118208374A CN 118208374 A CN118208374 A CN 118208374A CN 202410473449 A CN202410473449 A CN 202410473449A CN 118208374 A CN118208374 A CN 118208374A
- Authority
- CN
- China
- Prior art keywords
- data
- offshore wind
- load
- data analysis
- module
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000007405 data analysis Methods 0.000 claims abstract description 53
- 238000012423 maintenance Methods 0.000 claims abstract description 24
- 230000000007 visual effect Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 6
- 238000003745 diagnosis Methods 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000008054 signal transmission Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/007—Wind farm monitoring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/005—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/005—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks
- F03D17/0065—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks for diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
- F03D17/009—Monitoring or testing of wind motors, e.g. diagnostics characterised by the purpose
- F03D17/013—Monitoring or testing of wind motors, e.g. diagnostics characterised by the purpose for detecting abnormalities or damage
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Toxicology (AREA)
- Health & Medical Sciences (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a working condition external loading integrated monitoring system and method for offshore wind power, comprising the following steps: the data acquisition module is used for acquiring and processing the data of the offshore wind turbine in real time so as to ensure the accuracy and the integrity of the data; the data storage module is used for storing the data acquired by the sensor unit and providing rapid retrieval and query service for the data; the data analysis module is used for processing and analyzing the data acquired by the sensor unit and outputting a data analysis result so as to monitor and predict the working condition and the external load of the offshore wind turbine generator in real time; the alarm module is connected with the data analysis module and is used for receiving the data analysis result and triggering an alarm signal, monitoring and alarming abnormal conditions in real time and reminding operation and maintenance personnel to take corresponding measures in time; the visual interface module is connected with the data analysis module, receives the data analysis result and displays the data analysis result to the operation and maintenance personnel in a visual mode so as to facilitate the operation and maintenance personnel to perform data analysis and fault diagnosis.
Description
Technical Field
The invention relates to the technical field of offshore power generation and monitoring, in particular to a working condition external loading integrated monitoring system and method for offshore wind power.
Background
At present, the daily power generation operation of wind power equipment is monitored by a wind power equipment owner, the routing inspection work of the wind power equipment is carried out by a special wind power operation maintenance company, once equipment fails, the wind power equipment owner notifies the special wind power operation maintenance company to reach a specified failure equipment position for emergency repair, and as the routing inspection maintenance work is open sea operation, the wind power owner and the wind power operation maintenance company cannot realize quick coordination and timely information processing, all the work is relatively independent, so that the actual routing inspection maintenance work efficiency is lower.
In the existing offshore wind power integrated design technology, under the condition that a unit and a basic design belong to different main bodies, design interaction information is often transmitted through an interface load of a flange at the bottom of a tower, and the condition is easy to cause that the combination of working conditions of the two parties cannot be considered integrally, and a few simple numbers are extracted from complex working condition settings, so that the current working condition information can be lost; when different simulation environments are used by both the unit and the base design, the design calculation of the unit by the whole system is not limited to wind condition load, but comprehensive load results including wave load are generally adopted, but the interface load value cannot be decomposed, so that the interface load and the wave load can only be acted on the base design simultaneously in the design, the wave load is repeatedly considered, and the base cost is increased.
CN113125884a discloses an operation and maintenance monitoring system for offshore wind power equipment, which realizes the receiving processing and analysis of the working condition information of the wind power equipment through stable coordination of all module parts in the system and stable connection among the equipment terminal, the user monitoring platform and the operation and maintenance server, but the system does not consider the problems of repeated use of wave load and loss of working condition information, increases the basic cost, and meanwhile, cannot accurately analyze the operation and maintenance condition of the offshore wind power equipment.
CN216477689U discloses a multi-source data synchronous real-time monitoring system for offshore wind power structure, which performs data acquisition through a structural response monitoring system, an environment monitoring system, a working condition monitoring system, a distributed data acquisition instrument and a field main control device, and transmits the data to the field main control device for monitoring; however, the system does not consider the problems of repeated use of wave load and loss of working condition information, so that the foundation cost is increased, and the data analysis accuracy of the offshore wind power monitoring system is affected.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present invention has been made in view of the above-described problems occurring in the prior art.
Therefore, the technical problems solved by the invention are as follows: in the existing offshore wind power working condition external load integrated design, the problems that the numerical value of the interface load cannot be decomposed, so that the wave load is repeatedly considered to influence the basic cost and the monitoring analysis accuracy exist.
In order to solve the technical problems, the invention provides the following technical scheme: the data acquisition module is used for acquiring and processing the data of the offshore wind turbine in real time so as to ensure the accuracy and the integrity of the data, and comprises a sensor unit which is used for acquiring various working condition parameters and externally loaded data of the offshore wind turbine;
The data storage module is used for storing the data acquired by the sensor unit and providing rapid retrieval and query service for the data;
The data analysis module is used for processing and analyzing the data acquired by the sensor unit and outputting a data analysis result so as to monitor and predict the working condition and the external load of the offshore wind turbine generator in real time;
The alarm module is connected with the data analysis module and is used for receiving the data analysis result and triggering an alarm signal, monitoring and alarming abnormal conditions in real time and reminding operation and maintenance personnel to take corresponding measures in time;
The visual interface module is connected with the data analysis module, receives the data analysis result and displays the data analysis result to the operation and maintenance personnel in a visual mode so as to facilitate the operation and maintenance personnel to perform data analysis and fault diagnosis.
As a preferable scheme of the working condition external loading integrated monitoring system for offshore wind power, provided by the invention, the system comprises the following components: the sensor units are arranged on each key part of the offshore wind turbine so as to acquire data information of wind speed, wind direction, rotating speed, vibration and temperature.
As a preferable scheme of the working condition external loading integrated monitoring system for offshore wind power, provided by the invention, the system comprises the following components: the data acquisition module is connected with the sensor unit through a signal transmission line, and transmits acquired data to the data storage module and the data analysis module.
As a preferable scheme of the working condition external loading integrated monitoring system for offshore wind power, provided by the invention, the system comprises the following components: and the data storage module transmits the stored data to the data analysis module for analysis and processing, and the data analysis result is fed back to the alarm module and the visual interface module through signal transmission.
As a preferable scheme of the working condition external loading integrated monitoring system for offshore wind power, provided by the invention, the system comprises the following components: the visual interface module displays the data analysis result in a chart form or a graph form.
As a preferable scheme of the working condition external load integrated monitoring method for offshore wind power, provided by the invention, the method comprises the following steps: acquiring historical working condition parameters and historical external loading data of the offshore wind turbine based on the SCADA system, and preprocessing the historical working condition parameters and the historical external loading data to obtain a sample set;
the sample set is imported into a network model constructed based on a deep convolutional neural network for learning training, and an optimization model is generated;
Setting the optimization model in an operation program of the monitoring system, and optimally processing real-time working condition parameters and real-time external loading data acquired by each sensor:
if the optimization result is more than 0 and less than or equal to 1, eliminating repeated wave load, optimizing successfully, and transmitting optimized data to a visual interface module for display;
if the optimization result is less than or equal to-1 and less than 0, no repeated wave load exists in the acquired real-time data, and the acquired data is directly transmitted to the visual interface module for display.
As a preferable scheme of the working condition external load integrated monitoring method for offshore wind power, provided by the invention, the method comprises the following steps: the optimization process includes:
detecting repeated wave load values of the acquired real-time data by using an anomaly detection algorithm, and eliminating the repeated wave load values if the repeated wave load values exist;
performing data dimensionless operation on the real-time data detected by the repeated wave load values to obtain data values of the same specification, and obtaining a set of unique dimensionless pure data values;
and the set performs data value optimization in the optimization model until a point with the gradient of 0 is found, the convergence is rapid, and an optimization result is output.
As a preferable scheme of the working condition external load integrated monitoring method for offshore wind power, provided by the invention, the method comprises the following steps: the repeated wave load value detection includes:
sorting the variables in the data according to the sequence from the small value to the large value;
calculating an average value, a standard deviation and a deviation value;
Determining a suspicious value, i.e. the value deviating from the average value to the maximum;
And calculating statistics of the suspicious values, comparing the statistics with a critical value given by a Grabbs table, and if the statistics are larger than the critical value, directly eliminating the suspicious values, namely the repeated wave load values.
As a preferable scheme of the working condition external load integrated monitoring method for offshore wind power, provided by the invention, the method comprises the following steps: constructing the optimization model, including:
Wherein H is a Hessian matrix, M is a target detection matrix, g is a gradient vector, τ is a parameter to be optimized currently, namely, the sample set is substituted, γ is a global learning rate, τ n+1 represents a parameter generated after optimization, and n is an nth element in the sample set.
As a preferable scheme of the working condition external load integrated monitoring method for offshore wind power, provided by the invention, the method comprises the following steps: the learning training includes:
initializing a word segmentation device and a network model;
Converting the sample set into a text sequence, and inputting the text sequence into the network model for iterative training;
After the iteration is performed for N times, training is stopped;
and storing the model after training is finished, and taking the model as an optimization model.
The invention has the beneficial effects that:
1. The invention can monitor the working condition and the external load loading condition of the offshore wind turbine in real time and master the running state in time;
2. The accuracy and the integrity of the acquired data are ensured through the data acquisition and processing module;
3. The data analysis and alarm module is used for realizing the functions of real-time monitoring and early warning of abnormal conditions, and measures are taken in advance to avoid faults;
4. the monitoring data are displayed in visual charts and graphic forms through the visual interface module, so that operation and maintenance personnel can conveniently conduct data analysis and fault diagnosis;
5. According to the invention, through accurate monitoring and early warning functions, the safety and stability of offshore wind power operation are improved.
6. According to the invention, the wave load in the working condition loading and unloading integration is identified through the optimization algorithm, so that the wave load is prevented from being repeatedly considered and used, the basic cost is reduced, and the accuracy of data analysis of the monitoring system is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a schematic flow chart of an off-load loading integrated monitoring method for offshore wind power in the working condition;
FIG. 2 is a schematic diagram of the module distribution of the on-load integrated monitoring system for offshore wind power.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings.
All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Example 1
Offshore wind power is becoming an important form of clean energy, and is becoming a hotspot in the energy industry, however, offshore wind turbines run in severe offshore environments and face complex working conditions and external loading changes, and conventional monitoring systems often cannot meet the requirements of real-time monitoring and analysis.
In the prior art, the integrated design is applied to the offshore wind power monitoring system, by taking a supporting structure, a foundation and external environmental conditions (especially wind conditions, sea conditions and seabed geological conditions) of the offshore wind turbine generator set as a unified overall dynamic system to perform simulation analysis and check, the stress condition of the offshore wind power equipment system is hoped to be more comprehensively estimated, and the design safety is improved, but the current integrated design cannot completely consider the influences generated by the integration of design standards, modeling integration, working condition setting and environmental condition loading and the overall extraction of dynamic loads, for example: wave loads are repeatedly considered, resulting in increased foundation costs.
Therefore, the purpose of the embodiment of the invention is to solve the problems existing in the off-load monitoring of the working condition of offshore wind power in the traditional monitoring system, and the embodiment provides the working condition off-load integrated monitoring system for offshore wind power.
Referring to fig. 2, an integrated monitoring system for off-load loading of a working condition for offshore wind power provided by an embodiment of the invention includes a data acquisition module, a data storage module, a data analysis module, an alarm module and a visual interface module. Wherein:
The data acquisition module is used for acquiring and processing the data of the offshore wind turbine in real time so as to ensure the accuracy and the integrity of the data, and comprises a sensor unit which is used for acquiring various working condition parameters and externally loaded data of the offshore wind turbine.
And the data storage module is used for storing the data acquired by the sensor unit and providing rapid retrieval and query service for the data.
The data analysis module is used for processing and analyzing the data acquired by the sensor unit and outputting a data analysis result so as to monitor and predict the working condition and the external load of the offshore wind turbine generator in real time.
The alarm module is connected with the data analysis module and is used for receiving the data analysis result and triggering an alarm signal, monitoring and alarming abnormal conditions in real time and reminding operation and maintenance personnel to take corresponding measures in time.
The visual interface module is connected with the data analysis module, receives the data analysis result and displays the data analysis result to the operation and maintenance personnel in a visual mode so as to facilitate the operation and maintenance personnel to perform data analysis and fault diagnosis.
In an alternative embodiment, the sensor units are arranged on each key part of the offshore wind turbine so as to acquire data information of wind speed, wind direction, rotating speed, vibration and temperature.
As an example, a wind speed sensor is installed at the top of a tower of an offshore wind turbine for monitoring wind speed in real time.
As an example, wind direction sensors are mounted on the blades for monitoring wind direction in real time.
As an example, a rotational speed sensor is mounted on the generator shaft for monitoring rotational speed in real time.
As an example, vibration sensors and temperature sensors are installed at key locations for monitoring vibration and temperature changes in real time.
Preferably, the data acquisition module performs data verification and filtering processing on the data acquired by the sensor unit in real time, so that the accuracy and stability of the data are ensured, and the processed data are transmitted to the data storage module and the data analysis module by the data acquisition module for subsequent analysis and processing.
In an alternative embodiment, the data acquisition module is connected with the sensor unit through a signal transmission line, and the acquired data is transmitted to the data storage module and the data analysis module.
As an example, the collected data may be stored in a data storage module, and a high-capacity and high-speed storage device is used to ensure the safety and reliability of the data.
By way of example, the data analysis module adopts a statistical or machine learning algorithm to realize real-time monitoring and prediction of the working condition and the off-load loading of the offshore wind turbine.
In an alternative embodiment, the data storage module transmits the stored data to the data analysis module for analysis, and the data analysis result is fed back to the alarm module and the visual interface module through signal transmission.
As an example, the alarm module monitors working conditions and external loading conditions of the offshore wind turbine in real time according to data analysis results, and when abnormal conditions are found, the alarm module triggers an alarm signal to prompt operation and maintenance personnel to take corresponding measures in time so as to avoid occurrence or expansion of faults.
In an alternative embodiment, the visual interface module presents the data analysis results in a graphical or graphical form.
The operation and maintenance personnel can analyze and diagnose the faults of the data through the visual interface, discover the problems in time and take corresponding maintenance and repair measures.
It should be noted that the monitoring system further includes one or more processors and a memory, where the memory is configured to store instructions that can be operated, where the instructions when executed by the one or more processors cause the one or more processors to perform operations including the flow of the method for off-load loading integrated monitoring of the working condition for offshore wind power according to the foregoing embodiment, and in particular, the flow of the method shown in fig. 1.
Still further aspects of the disclosure of embodiments of the present invention provide a computer-readable medium storing software comprising instructions executable by one or more computers, the instructions, when executed, cause the one or more computers to perform operations comprising the process of the method for off-load loading integrated monitoring of conditions for offshore wind power of the foregoing embodiments, and in particular, the process of the method shown in fig. 1.
According to an embodiment of the invention, in combination with the flowchart shown in fig. 1, a working condition external loading integrated monitoring method for offshore wind power specifically comprises the following steps:
S1: acquiring historical working condition parameters and historical external loading data of the offshore wind turbine based on an SCADA system (working condition monitoring system), and preprocessing the data to obtain a sample set; the step needs to be described as follows:
collecting historical working condition parameters and historical external loading data of a huge amount of offshore wind turbines by using an SCADA system;
calculating a hash value of each piece of data in the historical working condition parameters and the historical externally loaded data by combining a hash algorithm;
Storing the distribution of the hash value into a plurality of buckets according to the hash value;
and merging the multiple buckets and marking the repeated values, and sequencing the multiple buckets by a time queue to form a sample set.
In a preferred embodiment, the sample data in the sample set may be grouped by a natural language model, a character group corresponding to each sample data is adaptively generated in the form of time ip+word+kanji, and each sample data is marked by using the character group as a tag.
As an example, if the load value of the offshore wind turbine collected by 32 minutes at 10 am in 10 months of 2023 and 16 am is 3450.600KN, the corresponding character set is generated in the form of: 202310161032+Wind turbine load value+3450.600.
In an alternative embodiment, the historical operating condition parameters and the historical off-load loading data include meteorological data, power generation performance data, mechanical load data, and electrical parameter data.
By way of example, meteorological data includes wind speed, wind direction, air temperature, humidity, and barometric pressure.
As an example, the power generation performance data includes power generation amount, rotation speed, torque, and power factor.
As examples, the mechanical load data includes blade forces, tower vibrations, bearing temperatures, and gearbox loads.
As examples, the electrical parameter data includes voltage, current, frequency, active power, and reactive power.
Preferably, in this embodiment, through the label mark form of the application character group, unique identifiability is provided for sample data, and then the recognition accuracy under the multiple operating mode parameters is promoted, wave load is avoided being considered repeatedly, and the accuracy of the monitoring system is further improved.
S2: the sample set is imported into a network model constructed based on a deep convolutional neural network for learning and training, and an optimization model is generated; the step of obtaining the optimization model includes:
Establishing an input layer, a convolution layer, a pooling layer, a full connection layer and an output layer based on deep convolution learning;
selecting a cross entropy loss function as an objective function, and executing a monitoring task;
Selecting a random gradient descent algorithm to adjust network weights to minimize the cross entropy loss function;
and (5) adjusting a network structure and super parameters by using a grid search method, and outputting to obtain a network model.
Further, the learning training includes:
initializing a word segmentation device and a network model;
Converting the sample set into a text sequence, and inputting the text sequence into a network model for iterative training;
After the iteration is performed for N times, training is stopped;
and storing the model after training is finished, and taking the model as an optimization model.
Further, the mathematical expression formula of the optimization model is as follows:
Wherein H is a Hessian matrix, M is a target detection matrix, g is a gradient vector, τ is a parameter to be optimized currently, namely, the sample set is substituted, γ is a global learning rate, τ n+1 represents a parameter generated after optimization, and n is an nth element in the sample set.
It should be noted that, because of the complexity of the working condition of the offshore wind turbine, the identification of the working condition data is low, which poses a small challenge for the safety management of the monitoring system, in order to solve the problem, in the embodiment, in step S1, the character set is used as a tag to perform parameter marking, binding is performed by using the time IP, and when the monitoring system reads the parameters, the monitoring system can directly know whether the read parameters are the parameters repeatedly read, so as to avoid the situation that the parameter values are repeatedly considered.
Preferably, the embodiment of the invention combines the deep convolutional neural network to construct an optimization model, optimizes the acquired data, eliminates repeated parameters such as repeated wave load, is further efficiently and accurately applied to a monitoring system, and provides good service for safety management of the offshore wind turbine.
S3: setting an optimization model in an operation program of a monitoring system, and optimally processing real-time working condition parameters and real-time external loading data acquired by each sensor:
if the optimization result is more than 0 and less than or equal to 1, eliminating repeated wave load, optimizing successfully, and transmitting optimized data to a visual interface module for display;
if the optimization result is less than or equal to-1 and less than 0, no repeated wave load exists in the acquired real-time data, and the acquired data is directly transmitted to the visual interface module for display.
Specifically, the optimization process includes:
Detecting repeated wave load values of the acquired real-time data by using an anomaly detection algorithm, and eliminating the repeated wave load values if the repeated wave load values exist;
performing data dimensionless operation on the real-time data detected by the repeated wave load values to obtain data values of the same specification, and obtaining a set of unique dimensionless pure data values;
and (3) carrying out data value optimization on the set in the optimization model until a point with the gradient of 0 is found, quickly converging, and outputting an optimization result.
Further, the repeated wave load value detection includes:
sorting the variables in the data according to the sequence from the small value to the large value;
calculating an average value, a standard deviation and a deviation value;
determining a suspicious value, i.e. the value deviating from the average value to the greatest extent;
and calculating statistics of the suspicious values, comparing the statistics with a critical value given by a Grabbs table, and if the statistics are larger than the critical value, the suspicious values are repeated wave load values and are directly removed.
Preferably, the wave load in the working condition loading and external load integration is identified through the optimization algorithm, the wave load is prevented from being repeatedly considered and used, the basic cost is reduced, and meanwhile, the data analysis accuracy of the monitoring system is improved.
The hash calculation and duplicate value detection of the data vector may be performed by means of a method and a means in the prior art, which are not described in detail in this example.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. A operating mode off-load loading integration monitoring system for offshore wind power, which is characterized by comprising:
The data acquisition module is used for acquiring and processing the data of the offshore wind turbine in real time so as to ensure the accuracy and the integrity of the data, and comprises a sensor unit which is used for acquiring various working condition parameters and externally loaded data of the offshore wind turbine;
The data storage module is used for storing the data acquired by the sensor unit and providing rapid retrieval and query service for the data;
The data analysis module is used for processing and analyzing the data acquired by the sensor unit and outputting a data analysis result so as to monitor and predict the working condition and the external load of the offshore wind turbine generator in real time;
The alarm module is connected with the data analysis module and is used for receiving the data analysis result and triggering an alarm signal, monitoring and alarming abnormal conditions in real time and reminding operation and maintenance personnel to take corresponding measures in time;
The visual interface module is connected with the data analysis module, receives the data analysis result and displays the data analysis result to the operation and maintenance personnel in a visual mode so as to facilitate the operation and maintenance personnel to perform data analysis and fault diagnosis.
2. The on-load integrated monitoring system for the working conditions of offshore wind power according to claim 1, wherein the sensor units are arranged on key parts of the offshore wind turbine so as to collect data information of wind speed, wind direction, rotating speed, vibration and temperature.
3. The on-load integrated monitoring system for offshore wind power according to claim 1, wherein the data acquisition module is connected with the sensor unit through a signal transmission line, and transmits acquired data to the data storage module and the data analysis module.
4. The on-load integrated monitoring system for the working conditions of offshore wind power according to claim 1, wherein the data storage module transmits stored data to the data analysis module for analysis and processing, and the data analysis result is fed back to the alarm module and the visual interface module through signal transmission.
5. The on-load integrated monitoring system for offshore wind power according to claim 1, wherein the visual interface module displays the data analysis result in a graph form or a graph form.
6. The working condition external load and load integrated monitoring method applied to the working condition external load and load integrated monitoring system for offshore wind power according to any one of claims 1 to 5 is characterized by comprising the following steps:
Acquiring historical working condition parameters and historical external loading data of the offshore wind turbine based on the SCADA system, and preprocessing the historical working condition parameters and the historical external loading data to obtain a sample set;
the sample set is imported into a network model constructed based on a deep convolutional neural network for learning training, and an optimization model is generated;
Setting the optimization model in an operation program of the monitoring system, and optimally processing real-time working condition parameters and real-time external loading data acquired by each sensor:
if the optimization result is more than 0 and less than or equal to 1, eliminating repeated wave load, optimizing successfully, and transmitting optimized data to a visual interface module for display;
if the optimization result is less than or equal to-1 and less than 0, no repeated wave load exists in the acquired real-time data, and the acquired data is directly transmitted to the visual interface module for display.
7. The method for on-load and off-load integrated monitoring of offshore wind power according to claim 6, wherein the optimizing process comprises:
detecting repeated wave load values of the acquired real-time data by using an anomaly detection algorithm, and eliminating the repeated wave load values if the repeated wave load values exist;
performing data dimensionless operation on the real-time data detected by the repeated wave load values to obtain data values of the same specification, and obtaining a set of unique dimensionless pure data values;
and the set performs data value optimization in the optimization model until a point with the gradient of 0 is found, the convergence is rapid, and an optimization result is output.
8. The method for monitoring the off-load loading integration of the working condition of offshore wind power according to claim 7, wherein the method comprises the following steps of,
The repeated wave load value detection includes:
sorting the variables in the data according to the sequence from the small value to the large value;
calculating an average value, a standard deviation and a deviation value;
Determining a suspicious value, i.e. the value deviating from the average value to the maximum;
And calculating statistics of the suspicious values, comparing the statistics with a critical value given by a Grabbs table, and if the statistics are larger than the critical value, directly eliminating the suspicious values, namely the repeated wave load values.
9. The method for monitoring the off-load loading integration of the working condition of offshore wind power according to claim 6, wherein the method comprises the following steps of,
Constructing the optimization model, including:
Wherein H is a Hessian matrix, M is a target detection matrix, g is a gradient vector, τ is a parameter to be optimized currently, namely, the sample set is substituted, γ is a global learning rate, τ n+1 represents a parameter generated after optimization, and n is an nth element in the sample set.
10. The method for integrated off-load loading monitoring of offshore wind power according to claim 6, wherein the learning training comprises:
initializing a word segmentation device and a network model;
Converting the sample set into a text sequence, and inputting the text sequence into the network model for iterative training;
After the iteration is performed for N times, training is stopped;
and storing the model after training is finished, and taking the model as an optimization model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410473449.3A CN118208374B (en) | 2024-04-19 | 2024-04-19 | Working condition off-load loading integrated monitoring system and method for offshore wind power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410473449.3A CN118208374B (en) | 2024-04-19 | 2024-04-19 | Working condition off-load loading integrated monitoring system and method for offshore wind power |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118208374A true CN118208374A (en) | 2024-06-18 |
| CN118208374B CN118208374B (en) | 2024-09-06 |
Family
ID=91455366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410473449.3A Active CN118208374B (en) | 2024-04-19 | 2024-04-19 | Working condition off-load loading integrated monitoring system and method for offshore wind power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118208374B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107061183A (en) * | 2017-01-17 | 2017-08-18 | 中山大学 | A kind of automation method for diagnosing faults of offshore wind farm unit |
| CN109617234A (en) * | 2018-12-14 | 2019-04-12 | 吉林电力股份有限公司科技开发分公司 | A Wind Turbine Condition Monitoring System Based on Multidimensional Data |
| WO2023093774A1 (en) * | 2021-11-26 | 2023-06-01 | 中国华能集团清洁能源技术研究院有限公司 | Deep learning-based wind power cluster power prediction method |
| CN116906278A (en) * | 2023-07-06 | 2023-10-20 | 明阳智慧能源集团股份公司 | Double wind wheel floating type wind generating set monitoring control system and method |
| CN117627862A (en) * | 2023-11-28 | 2024-03-01 | 道莅智远科技(青岛)有限公司 | Marine wind turbine generator control system based on IEC61499 framework |
-
2024
- 2024-04-19 CN CN202410473449.3A patent/CN118208374B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107061183A (en) * | 2017-01-17 | 2017-08-18 | 中山大学 | A kind of automation method for diagnosing faults of offshore wind farm unit |
| CN109617234A (en) * | 2018-12-14 | 2019-04-12 | 吉林电力股份有限公司科技开发分公司 | A Wind Turbine Condition Monitoring System Based on Multidimensional Data |
| WO2023093774A1 (en) * | 2021-11-26 | 2023-06-01 | 中国华能集团清洁能源技术研究院有限公司 | Deep learning-based wind power cluster power prediction method |
| CN116906278A (en) * | 2023-07-06 | 2023-10-20 | 明阳智慧能源集团股份公司 | Double wind wheel floating type wind generating set monitoring control system and method |
| CN117627862A (en) * | 2023-11-28 | 2024-03-01 | 道莅智远科技(青岛)有限公司 | Marine wind turbine generator control system based on IEC61499 framework |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118208374B (en) | 2024-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103323772B (en) | Based on the running status of wind generator analytical approach of neural network model | |
| CN114444382B (en) | Wind turbine generator system gear box fault diagnosis and analysis method based on machine learning algorithm | |
| Zaher et al. | A multi-agent fault detection system for wind turbine defect recognition and diagnosis | |
| CN108376298A (en) | A kind of Wind turbines generator-temperature detection fault pre-alarming diagnostic method | |
| KR20160073945A (en) | System and method for managing wind plant | |
| Butler et al. | A feasibility study into prognostics for the main bearing of a wind turbine | |
| CN111582392A (en) | An on-line monitoring method for multi-condition health status of key components of wind turbines | |
| Wang et al. | Wind turbine fault detection and identification through self-attention-based mechanism embedded with a multivariable query pattern | |
| Mohammadi et al. | DeepWind: an accurate wind turbine condition monitoring framework via deep learning on embedded platforms | |
| CN116306139A (en) | Intelligent monitoring method and system for service life of wind turbine blade | |
| CN116085212A (en) | Method and system for monitoring running state of new energy wind turbine generator in real time | |
| CN111396266A (en) | GBRT-based wind turbine generator bearing fault early warning method | |
| Sethi et al. | Vibration signal-based diagnosis of wind turbine blade conditions for improving energy extraction using machine learning approach | |
| CN115906437A (en) | Fan state determination method, device, equipment and storage medium | |
| Dinh et al. | Implementation of digital twin-assisted condition monitoring and fault diagnosis for wind turbines | |
| Elijorde et al. | A wind turbine fault detection approach based on cluster analysis and frequent pattern mining | |
| Ahilan et al. | A self-improved optimizer-based CNN for wind turbine fault detection | |
| Tutiv'en et al. | Wind turbine main bearing condition monitoring via convolutional autoencoder neural networks | |
| CN118208374B (en) | Working condition off-load loading integrated monitoring system and method for offshore wind power | |
| CN115726935A (en) | An artificial intelligence-based abnormal state detection system and method for wind turbines | |
| CN113822344A (en) | Wind turbine generator front bearing state monitoring method based on data driving | |
| CN112202924A (en) | High-power wind turbine generator system bolt intellectual detection system that excels in based on thing networking | |
| Ristić et al. | A short overview on Industry 4.0 in maintenance of hydropower plants | |
| Randrianandraina et al. | Wind turbine generator bearing anomaly detection and explanation using rrcf approach | |
| CN116757681B (en) | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
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 |