CN117151684A - Wind power fan data analysis early warning method, system, device and readable storage medium - Google Patents
Wind power fan data analysis early warning method, system, device and readable storage medium Download PDFInfo
- Publication number
- CN117151684A CN117151684A CN202311060839.XA CN202311060839A CN117151684A CN 117151684 A CN117151684 A CN 117151684A CN 202311060839 A CN202311060839 A CN 202311060839A CN 117151684 A CN117151684 A CN 117151684A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- early warning
- analysis
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000007405 data analysis Methods 0.000 title claims abstract description 21
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000003745 diagnosis Methods 0.000 claims abstract description 47
- 238000003062 neural network model Methods 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 21
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000006698 induction Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013024 troubleshooting Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims 1
- 230000007774 longterm Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000011068 loading method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
Abstract
The application provides a wind power fan data analysis and early warning method, a system, a device and a readable storage medium, comprising the following steps: s1: acquiring data of wind power fan equipment to obtain original data; s2: SCADA state detection is carried out, S3 is carried out on state abnormal data, and S8 is carried out on state normal data; s3: triggering an alarm and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm; s4: extracting fault characteristics of potential fault risks; s5: diagnosing potential fault characteristics through a neural network model; s6: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy; s7: outputting the results of each step S2-S6 and storing data, and updating the data storage results to the SCADA state detection standard in S2; s8: and S1, continuing to operate, the application can rationalize overhaul and maintenance, comprehensively improve the utilization efficiency of the equipment, and simultaneously ensure long-term stable and healthy operation of the equipment.
Description
[ field of technology ]
The application relates to the technical field of wind turbines, in particular to a wind turbine data analysis and early warning method, a system and a device and a readable storage medium.
[ background Art ]
The wind power industry is an important component in the field of renewable energy sources, and along with the continuous increase of energy demand, the wind power industry is also continuously developed and increased. The wind turbine generator system has the advantages that the wind turbine generator system is used as a large country of wind power industry, but the wind turbine generator system has the advantages that the availability ratio is continuously reduced, the performance of equipment parts is reduced, the shutdown phenomenon caused by equipment faults is serious, the overhaul cost is gradually increased, particularly important machine parts such as a gear box, a sensor, a pitch, a cabin and the like, which are critical components in the wind turbine generator system, but in overhaul and maintenance, fault diagnosis is extremely difficult, and the overhaul work is often in a bottleneck to cause great loss, so the problems of difficult overhaul of the wind turbine generator system, high overhaul cost, large investigation limit of fault causes, incapability of timely finding potential hazards and the like are solved.
Accordingly, there is a need to develop a wind turbine data analysis and early warning method, system, apparatus, and readable storage medium to address the deficiencies of the prior art, to solve or mitigate one or more of the problems described above.
[ application ]
In view of the above, the application provides a wind turbine data analysis and early warning method, a system, a device and a readable storage medium, which aim to accurately and timely monitor various faults and risks of wind turbine equipment, and improve the predictive and predictive capabilities of equipment faults and alarms, so that reasonable overhaul and maintenance are performed, the utilization efficiency of the equipment is comprehensively improved, and meanwhile, the long-term stable and healthy operation of the equipment is ensured.
In one aspect, the application provides a wind power fan data analysis and early warning method, which comprises the following steps:
s1: acquiring data of wind power fan equipment to obtain original data;
s2: performing SCADA state detection on the original data, performing S3 on the state abnormal data, and performing S8 on the state normal data;
s3: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
s4: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
s5: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
s6: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
s7: outputting the results of each step S2-S6 and storing data, and updating the data storage results to the SCADA state detection standard in S2;
s8: the operation S1 is continued.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, wherein the raw data in S1 are data of an operation state, wear degree of vulnerable parts and a control system acquired by sensors on parts of the wind turbine equipment.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the fuzzy logic reasoning algorithm in S3 specifically describes a fuzzy relationship between a fault cause and a fault phenomenon by using fuzzy logic, and the relationship between the fault cause and the state identification is established through membership functions and a fuzzy relationship equation.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the fault extraction method in S4 includes:
threshold comparison method: through a preset interval of the telemetry value of the equipment, exceeding the upper limit and the lower limit of the interval is a risk sign;
trend analysis: identifying abnormal working conditions through the change of the trend of the telemetry point within a period of time;
equilibrium analysis: identifying abnormal working conditions through the balance relation among a plurality of remote points of the equipment;
proximity value mapping method: identifying abnormal indexes of the equipment by comparing the range interval of the real-time data of the remote measuring points of the fans with indexes of adjacent fans;
duration tracking method: and (3) counting the time length of the measuring point which is related to the fan control and reaches the target value, measuring the time length of the fan which is issued from the control instruction to the control in place, and reflecting the performance condition of the fan parts.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the neural network model diagnosis in S5 is specifically: and carrying out background training on the collected fault samples, carrying out normalization processing on the data, then learning the fault samples through a neural network training model, diagnosing the real-time data through a neural network monitoring model, obtaining a result, outputting an early warning threshold value, comparing the early warning threshold value with the data, if the data is smaller than the early warning threshold value, normally operating the unit, and if the data is larger than the early warning threshold value, sending out early warning, then triggering an alarm mechanism, and timely feeding back the early warning result.
The aspect and any possible implementation manner as described above further provide an implementation manner, where the retrieving the historical knowledge base in S6, and obtaining the diagnostic overhaul policy specifically is: and adopting multi-parameter and multi-dimensional feature vectors and fault matrixes to carry out induction, synthesis, comparison and classification on the historical knowledge base, obtaining a conclusion after system processing and arrangement, pushing an overhaul scheme and troubleshooting a fault reason.
In aspects and any one of the possible implementations described above, there is further provided an implementation, the components of the wind turbine device including a gearbox, a drive train, a sensor, and a pitch of the wind turbine.
Aspects and any possible implementation manner as described above, further provide a wind power fan data analysis and early warning system, the analysis and early warning system includes:
and a data acquisition module: acquiring data of wind power fan equipment to obtain original data;
the state monitoring module: performing SCADA state detection on the original data;
and a fuzzy logic reasoning algorithm module: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
the fault feature extraction module: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
neural network model diagnostic module: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
and a detection and diagnosis module: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
output and storage module: and outputting a result and storing data, wherein the data storage result is updated to the SCADA state detection standard.
The aspects and any possible implementation manner as described above further provide a wind power fan data analysis and early warning device, where the analysis and early warning device includes a processor and a memory connected with the processor; the memory is used for storing program data, and the processor is used for executing the program data to realize the data analysis early warning method according to any one of the above.
In aspects and any of the possible implementations described above, there is further provided a computer readable storage medium for storing program data for implementing the analytical pre-warning method of any of the claims when executed by a processor.
Compared with the prior art, the application can obtain the following technical effects:
1) The intelligent sensing and real-time reminding of the potential risks and abnormal conditions of the wind power equipment can be realized based on the fault mechanism and the fault feature extraction method, fault points can be timely and accurately positioned, early warning and processing can be timely carried out before serious faults occur on key components or when the potential risks exist, and the safe operation of the wind power equipment is ensured;
2) According to the method, the expert early warning is classified by utilizing a big data technology, the expert early warning is analyzed, the expert early warning frequency and the early warning duration are analyzed, and meanwhile, classification and single early warning ordering can be performed according to an analysis page so as to analyze the associated logic relationship among the early warnings;
3) The neural network model algorithm can find out and solve deep defect hidden dangers existing in the wind power plant through the application of the big data analysis functional module based on expert knowledge, and effectively avoid economic loss and unsafe events caused by equipment hidden danger deterioration;
4) The implementation and application of the research method provided by the application can reduce risks by early warning and online warning, greatly reduce manual inspection frequency, reduce casualties and save labor cost.
Of course, it is not necessary for any of the products embodying the application to achieve all of the technical effects described above at the same time.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a graph of correspondence between fault signatures and fault causes provided by one embodiment of the present application;
FIG. 2 is a flow chart of a fuzzy diagnostic method provided in one embodiment of the present application;
fig. 3 is a flowchart of an analysis and early warning method according to an embodiment of the present application.
[ detailed description ] of the application
For a better understanding of the technical solution of the present application, the following detailed description of the embodiments of the present application refers to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
As shown in fig. 3, the application provides a wind power fan data analysis and early warning method, which comprises the following steps:
s1: acquiring data of wind power fan equipment to obtain original data;
s2: performing SCADA state detection on the original data, performing S3 on the state abnormal data, and performing S8 on the state normal data;
s3: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
s4: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
s5: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
s6: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
s7: outputting the results of each step S2-S6 and storing data, and updating the data storage results to the SCADA state detection standard in S2;
s8: the operation S1 is continued.
The raw data in the S1 are data of an operation state, wearing degree of vulnerable parts and a control system acquired by sensors for the parts of the wind power fan equipment.
The fuzzy logic reasoning algorithm in the S3 specifically describes the fuzzy relation between the fault cause and the fault phenomenon by using fuzzy logic, and establishes the relation between the fault cause and the state identification by a membership function and a fuzzy relation equation.
The fault extraction method in the S4 comprises the following steps:
threshold comparison method: through a preset interval of the telemetry value of the equipment, exceeding the upper limit and the lower limit of the interval is a risk sign;
trend analysis: identifying abnormal working conditions through the change of the trend of the telemetry point within a period of time;
equilibrium analysis: identifying abnormal working conditions through the balance relation among a plurality of remote points of the equipment;
proximity value mapping method: identifying abnormal indexes of the equipment by comparing the range interval of the real-time data of the remote measuring points of the fans with indexes of adjacent fans;
duration tracking method: and (3) counting the time length of the measuring point which is related to the fan control and reaches the target value, measuring the time length of the fan which is issued from the control instruction to the control in place, and reflecting the performance condition of the fan parts.
The neural network model diagnosis in the step S5 is specifically as follows: and carrying out background training on the collected fault samples, carrying out normalization processing on the data, then learning the fault samples through a neural network training model, diagnosing the real-time data through a neural network monitoring model, obtaining a result, outputting an early warning threshold value, comparing the early warning threshold value with the data, if the data is smaller than the early warning threshold value, normally operating the unit, and if the data is larger than the early warning threshold value, sending out early warning, then triggering an alarm mechanism, and timely feeding back the early warning result. The step S6 of retrieving the historical knowledge base to obtain the diagnosis and maintenance strategy specifically comprises the following steps: and adopting multi-parameter and multi-dimensional feature vectors and fault matrixes to carry out induction, synthesis, comparison and classification on the historical knowledge base, obtaining a conclusion after system processing and arrangement, pushing an overhaul scheme and troubleshooting a fault reason. The components of the wind power fan equipment comprise a gear box, a transmission chain, a sensor and a variable pitch of the wind turbine.
The application also provides a wind power fan data analysis and early warning system, which comprises:
and a data acquisition module: acquiring data of wind power fan equipment to obtain original data;
the state monitoring module: performing SCADA state detection on the original data;
and a fuzzy logic reasoning algorithm module: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
the fault feature extraction module: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
neural network model diagnostic module: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
and a detection and diagnosis module: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
output and storage module: and outputting a result and storing data, wherein the data storage result is updated to the SCADA state detection standard.
The application also provides a wind power fan data analysis and early warning device, which comprises a processor and a memory connected with the processor; the memory is used for storing program data, and the processor is used for executing the program data to realize the data analysis early warning method according to any one of the above.
The present application also provides a computer readable storage medium for storing program data which, when executed by a processor, is for implementing the analytical pre-warning method of any one of the above.
According to the application, through the SCADA state detection and fault feature extraction method and the fuzzy logic reasoning algorithm, the vibration signals of the wind turbine generator are judged and processed by utilizing the mean value, the variance and the residual error of the time domain waveform (SCADA is a data acquisition and monitoring control system), and the fault components detected by the wind turbine generator are searched by combining with neural network model diagnosis and expert knowledge base establishment, so that fault reasons and solutions are provided, the hidden danger and risks of the wind turbine generator are pre-judged and intelligently monitored in real time, and early warning diagnosis reports are provided for the overall health condition of the wind turbine generator, so that the problems faced by efficient operation of a wind power plant are solved. The method comprises the steps of predicting hidden trouble faults of equipment such as a gearbox, a transmission chain, a sensor, a variable pitch and the like of the wind turbine, wherein the method for analyzing, early-warning and researching the fan data comprises the following steps: the SCADA state detection and data acquisition and preprocessing method is used for acquiring data and speed signals of wind turbine generator equipment in real time in the running process, a fault mechanism and fault feature extraction method and a fuzzy logic reasoning algorithm are adopted, an expert knowledge base is established in combination with neural network model diagnosis, research and analysis are carried out on fault prediction and hidden danger of the wind turbine generator equipment, normalization processing is carried out on the data to obtain a conclusion, fault components detected by the wind turbine generator equipment are searched, fault reasons and solutions are provided, and finally data extraction, conversion and loading are provided for a system through data storage, so that a user can conveniently trace and inquire the data.
The application relates to the field of wind power, in particular to a fan data analysis early warning system, which can intelligently identify risks and potential faults of wind turbine generator equipment in the production and operation process, adopts a fault mechanism and fault feature extraction method and a fuzzy logic reasoning algorithm by adopting a SCADA state detection and data acquisition and preprocessing method, combines neural network model diagnosis and establishment of an expert knowledge base, searches fault components detected by the wind turbine generator equipment, provides fault reasons and solutions, and finally provides data extraction, conversion and loading for the system by data storage, thereby facilitating the user to trace and inquire data.
According to the SCADA state detection method, data monitored by the system are analyzed and processed, abnormal data or data information with potential risks and faults are extracted, and equipment is subjected to investigation and maintenance by using an expert knowledge base and fault diagnosis, so that correct analysis and judgment are made, and the fault problem is solved.
According to the fault mechanism and fault feature extraction method, potential fault risks of the fan are predicted through analysis of the operation data of the fan, and corresponding early warning signals are provided, so that corresponding measures can be taken in time to avoid the occurrence of fan faults, and the efficiency and reliability of the fan are improved.
The fuzzy logic reasoning algorithm is used for reasoning and analyzing the running state of the fan by establishing a fault model so as to predict the fault occurrence time and maintenance requirement of the fan. Specifically, the fuzzy logic reasoning algorithm can identify potential fault risks by monitoring and analyzing parameters of the fan in the operation process of the fan, and timely give an alarm to a fan manager so that the manager can take corresponding measures to repair or replace.
The neural network model diagnosis is carried out, the transmission chain fault prediction and hidden danger are researched and analyzed based on the neural network model, the acquired fault sample is subjected to background training, the fault sample is learned through the neural network training model after the data are normalized, the neural network monitoring model is used for diagnosing real-time data to obtain a result, an early warning threshold value is output, the early warning threshold value is compared with the data, if the data are smaller than the early warning threshold value, the unit normally operates, early warning is sent out, an alarm mechanism is triggered later, and the early warning result is fed back in time.
The expert knowledge base adopts multi-parameter and multi-dimensional feature vectors and fault matrixes to carry out induction, synthesis, comparison, classification and the like on received data, and a conclusion is obtained after system processing and arrangement, and an overhaul scheme and fault reasons are intelligently pushed.
The data storage method provides data extraction, conversion and loading for the system, is convenient for users to trace back and inquire data, and can be used for classifying and storing according to early warning conditions, so that the data storage method can access and inquire in real time, and provides a data platform for data analysis and data mining.
The method can be used for early warning the risk and potential faults of the wind turbine generator running equipment in the production running process. The vibration signals of the wind turbine generator are judged and processed by means of the mean value, variance and residual error of the time domain waveform through the SCADA state detection and fault feature extraction method and the fuzzy logic reasoning algorithm, and the neural network model diagnosis and the expert knowledge base establishment are combined to search fault components detected by the wind turbine generator, so that fault reasons and solutions are provided, the hidden danger and risks of the wind turbine generator are pre-judged in advance and intelligently monitored in real time, early warning diagnosis reports are provided for the overall health condition of the wind turbine generator, and the problems faced by efficient operation of the wind power plant are solved. Aiming at various fault phenomena of the wind power generation system, the application performs intelligent early warning monitoring research by analyzing and researching different fault mechanisms and causes and fault characterization phenomena thereof and combining the front edge technologies such as modern advanced sensor technology, network communication technology machine learning and the like.
Example 1:
the application analyzes and pre-warns fan data in the wind power field based on the SCADA state detection and fault feature extraction method and the fuzzy logic reasoning algorithm, can intelligently identify risks and potential faults of wind turbine generator equipment in the production operation process, mainly comprises a SCADA state detection and data acquisition and preprocessing module, a fault mechanism and fault feature extraction module, a neural network model diagnosis module, an expert knowledge base module and the like, can effectively solve the problems, and comprises the following specific implementation steps:
step one, data acquisition, namely, acquiring data of key components of wind power equipment by using a sensor, and extracting fault characteristics of the acquired original signals by adopting various advanced signal processing methods and fusion modes of a plurality of characteristic extraction methods so as to eliminate noise interference and redundant information and improve fault diagnosis precision and effectiveness and availability of the fault characteristic information. And a proper classification algorithm is selected to identify and classify the fault state by utilizing a data depth mining technology, so that decision support is provided for maintenance of equipment.
Step two, SCADA state detection: based on the SCADA data acquisition and monitoring system, the operation state of the fan equipment, the wearing degree of vulnerable parts and the data of the control system are collected and analyzed, the system has ultrahigh data acquisition capacity, supports large-scale data processing and flexible and efficient data storage, and workers can timely know the operation condition of the fan equipment, and through the technical parameters stored by a computer and the SCADA, the database can realize full-automatic recording of the production operation process, so that the remote control operation on site is realized, the occurrence probability of artificial faults is reduced, a preventive maintenance plan is formulated, and a large amount of labor and material cost is saved.
And thirdly, extracting fault mechanism and fault characteristics, predicting potential fault risk of the fan through analysis of fan operation data, and providing corresponding early warning signals so as to take corresponding measures in time to avoid fan faults and improve efficiency and reliability of the fan.
Generally, the device will have some symptoms before failure, which is an initial manifestation of the failure. By knowing these symptoms, maintenance or repair actions are developed before the occurrence of the fault, and the occurrence of an emergency fault can be effectively prevented. As shown in fig. 1, for convenience of research, the present application combines fault symptoms and fault modes to discuss them together, collectively referred to as fault signatures, and fault mechanisms the present application is collectively referred to as fault causes. There is often a many-to-many relationship between fault characteristics and fault causes.
The fault feature extraction method is an important ring in fan equipment early warning. The method can help to predict the failure probability and failure time of the fan equipment, thereby improving the utilization rate and safety of the fan equipment. The following are some common fault signature extraction methods:
1) Threshold comparison method
The telemetering value of the equipment is usually in a reasonable interval, and the upper limit and the lower limit of the interval are usually risk symptoms, such as cabin vibration overrun, temperature overrun, generator rotating speed overrun and the like; conventionally, SCADA alarms are usually such alarms, but SCADA alarms are usually built-in and solidified in a fan main control system and are difficult to modify and configure, and SCADA alarms can be stopped after equipment fails, even parts are damaged, and economic losses are caused.
The early warning rule configuration tool provided by the patent allows a user to select the measuring points and set the threshold value, and besides, the early warning system can analyze the early warning event in a time domain and a frequency domain, so that the user can master the working condition of the equipment more comprehensively; for example, a single nacelle vibration overrun warning may be caused by a strong wind, but if a unit frequently experiences vibration overrun warning, or is of a longer duration, then attention needs to be paid and inspection is re-focused.
2) Trend analysis method
And identifying abnormal working conditions by changing the trend of the telemetry point within a period of time. For example, when the generator works, the bearing temperature curve usually shows a gentle rising, falling or fluctuation trend, and if the temperature rises rapidly in a short time or even exceeds a certain critical value, the generator is extremely likely to be burnt out, and measures need to be taken in time; the early warning system supports the temperature rise function, can monitor and identify abnormal temperature rise conditions in real time, and triggers early warning.
3) Balance analysis method
And identifying abnormal working conditions through the balance relation among a plurality of remote points of the equipment. For example, the impeller rotating speed and the generator rotating speed generally have a proportional relation of about one hundred times, and if the deviation between the impeller rotating speed and the generator rotating speed is larger than a set threshold value after multiplying the multiplying power, the condition that the working condition of the main shaft or the coupling is poor is indicated, and the main shaft is damaged or the coupling slips.
4) Proximity value matching method
And identifying abnormal indexes of the equipment by comparing the range interval of the real-time data of the remote measuring points of the fans with indexes of adjacent fans. For example, the wind speed and the power of a certain fan belong to the same interval with the average wind speed and the average power of a wind field, and the cabin temperature of the fan is obviously higher than the average cabin temperature of the whole field, so that the abnormal working condition can be considered, and attention needs to be paid.
5) Duration tracking method
And (3) counting the time length of the measuring point which is related to the fan control and reaches the target value, measuring the time length of the fan which is issued from the control instruction to the control in place, and reflecting the performance condition of the fan parts. For example: after stopping, the blade angle of the blade is tracked, and when the blade angle is greater than 88 degrees (configurable), the blade is regarded as the completion of the blade harvesting, and the timing is stopped. And the working condition of the fan variable pitch system is evaluated through tracking statistics of the fan pitch time.
And step four, a fuzzy logic reasoning algorithm is used for reasoning and analyzing the running state of the fan by establishing a fault model so as to predict the fault occurrence time and maintenance requirement of the fan. Specifically, the fuzzy logic reasoning algorithm can identify potential fault risks by monitoring and analyzing parameters of the fan in the operation process of the fan, and timely give an alarm to a fan manager so that the manager can take corresponding measures to repair or replace.
88 early warning models are established on an intelligent alarm related platform, second-level calculation is carried out by adopting a big data platform, the models are established by adopting a machine learning algorithm and expert knowledge, wherein characteristic parameters are extracted and threshold values are adjusted, and a data mining technology is adopted.
As shown in fig. 2, a failure phenomenon may be caused by multiple reasons, and a failure of one reason may generate multiple phenomena, so that the failure of the wind turbine has a certain ambiguity, which is specifically expressed as follows:
the same fault expression forms are diversified;
several faults occur simultaneously and are mutually induced;
the classification between faults has ambiguity, namely different faults have similar or similar characteristics;
the existence degree of the fault has ambiguity, and the fault cannot be absolutely identified as existence or nonexistence;
for the fuzzy phenomenon of wind turbine generator faults, quantitative diagnosis is often difficult by using a traditional mathematical tool, and the fuzzy mathematical method shows superiority. The fuzzy diagnosis method is an automatic diagnosis method based on knowledge, which uses fuzzy logic to describe the fuzzy relation between the fault cause and the fault phenomenon, and solves the problem of fault cause and state identification through membership functions and fuzzy relation equations.
And fifthly, diagnosing a neural network model, carrying out research analysis on the fault prediction and hidden danger of the transmission chain based on the neural network model, carrying out background training on the collected fault sample, carrying out normalization processing on the data, then carrying out learning on the fault sample through the neural network training model, diagnosing real-time data by a neural network monitoring model, obtaining a result, outputting an early warning threshold value, comparing the early warning threshold value with the data, if the data is smaller than the early warning threshold value, enabling the machine set to normally operate, and sending out early warning, then triggering an alarm mechanism, and timely feeding back the early warning result.
Neural networks are a computational model that simulates the human brain, which is capable of processing input data in a learning and adaptive manner, and then outputting corresponding results based on the characteristics of the input data. In the early warning of the fan equipment, the neural network model can predict possible faults of the fan by analyzing and learning the operation data of the fan, and provides corresponding early warning signals.
First, data acquisition is performed. Collecting operation data of a fan, including parameters such as wind speed, temperature, humidity, pressure and the like; and secondly, preprocessing data. And cleaning, normalizing, extracting features and the like are carried out on the acquired data so as to facilitate the learning and analysis of the neural network model. And thirdly, training a neural network model. And training a neural network model by using the processed data set, so that the model can learn the characteristics and rules of the fan operation data. And fourthly, performing model diagnosis. And analyzing and learning the data of the fresh air machine by using the trained neural network model, and then outputting corresponding fault prediction and early warning signals. And fifthly, fault diagnosis and early warning. And according to the fault prediction and early warning signals output by the neural network model, carrying out corresponding fault diagnosis and early warning on the fan so as to discover and repair faults in time, thereby reducing the fault rate of the fan and prolonging the service life of equipment.
The neural network model diagnosis can rapidly and accurately diagnose the faults of the fan in the fan equipment early warning and provide corresponding early warning signals, so that the fault rate of the fan can be effectively reduced and the service life of the equipment can be prolonged. Meanwhile, the neural network model diagnosis can also analyze and learn the operation data of the fan, so that more accurate and comprehensive fan operation state analysis and prediction can be provided, and the fan can be managed and controlled better.
And step six, an expert knowledge base adopts multi-parameter and multi-dimensional feature vectors and fault matrixes to carry out induction, synthesis, comparison, classification and the like on received data, and a conclusion is obtained after system processing and arrangement, so that an overhaul scheme and fault reasons are intelligently pushed.
The retrieved equipment fault information is uploaded to an expert knowledge base, the fault reasons are analyzed, equipment fault problems are solved in batches, meanwhile, the system can automatically identify the type of the faults, and reasonable guidance suggestions are provided for maintenance staff by combining knowledge of maintenance and inspection schemes, fault processing schemes, operation guidance and the like, so that maintenance operation is reasonable and reasonable, and hidden danger eliminating efficiency is improved.
The method, the system, the device and the readable storage medium for analyzing and early warning the wind power fan data provided by the embodiment of the application are described in detail. The above description of embodiments is only for aiding in the understanding of the method of the present application and its core ideas; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Certain terms are used throughout the description and claims to refer to particular components. Those of skill in the art will appreciate that a hardware manufacturer may refer to the same component by different names. The description and claims do not take the form of an element differentiated by name, but rather by functionality. As referred to throughout the specification and claims, the terms "comprising," including, "and" includes "are intended to be interpreted as" including/comprising, but not limited to. By "substantially" is meant that within an acceptable error range, a person skilled in the art is able to solve the technical problem within a certain error range, substantially achieving the technical effect. The description hereinafter sets forth a preferred embodiment for practicing the application, but is not intended to limit the scope of the application, as the description is given for the purpose of illustrating the general principles of the application. The scope of the application is defined by the appended claims.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or system comprising such elements.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
While the foregoing description illustrates and describes the preferred embodiments of the present application, it is to be understood that the application is not limited to the forms disclosed herein, but is not to be construed as limited to other embodiments, and is capable of numerous other combinations, modifications and environments and is capable of changes or modifications within the scope of the inventive concept as expressed herein, either as a result of the foregoing teachings or as a result of the knowledge or technology of the relevant art. And that modifications and variations which do not depart from the spirit and scope of the application are intended to be within the scope of the appended claims.
Claims (10)
1. The wind power fan data analysis and early warning method is characterized by comprising the following steps of:
s1: acquiring data of wind power fan equipment to obtain original data;
s2: performing SCADA state detection on the original data, performing S3 on the state abnormal data, and performing S8 on the state normal data;
s3: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
s4: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
s5: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
s6: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
s7: outputting the results of each step S2-S6 and storing data, and updating the data storage results to the SCADA state detection standard in S2;
s8: the operation S1 is continued.
2. The analysis and early warning method according to claim 1, wherein the raw data in S1 are data of an operation state, wear degree of vulnerable parts and a control system collected by a sensor for parts of wind power fan equipment.
3. The analysis and early warning method according to claim 1, wherein the fuzzy logic reasoning algorithm in S3 specifically describes a fuzzy relationship between a fault cause and a fault phenomenon by using fuzzy logic, and establishes a relationship between the fault cause and state recognition by using membership functions and a fuzzy relationship equation.
4. The analysis and early warning method according to claim 1, wherein the fault extraction method in S4 includes:
threshold comparison method: through a preset interval of the telemetry value of the equipment, exceeding the upper limit and the lower limit of the interval is a risk sign;
trend analysis: identifying abnormal working conditions through the change of the trend of the telemetry point within a period of time;
equilibrium analysis: identifying abnormal working conditions through the balance relation among a plurality of remote points of the equipment;
proximity value mapping method: identifying abnormal indexes of the equipment by comparing the range interval of the real-time data of the remote measuring points of the fans with indexes of adjacent fans;
duration tracking method: and (3) counting the time length of the measuring point which is related to the fan control and reaches the target value, measuring the time length of the fan which is issued from the control instruction to the control in place, and reflecting the performance condition of the fan parts.
5. The analysis and early warning method according to claim 1, wherein the neural network model diagnosis in S5 is specifically: and carrying out background training on the collected fault samples, carrying out normalization processing on the data, then learning the fault samples through a neural network training model, diagnosing the real-time data through a neural network monitoring model, obtaining a result, outputting an early warning threshold value, comparing the early warning threshold value with the data, if the data is smaller than the early warning threshold value, normally operating the unit, and if the data is larger than the early warning threshold value, sending out early warning, then triggering an alarm mechanism, and timely feeding back the early warning result.
6. The analysis and early warning method according to claim 5, wherein the step of retrieving the historical knowledge base in step S6, the step of obtaining the diagnosis and maintenance strategy specifically includes: and adopting multi-parameter and multi-dimensional feature vectors and fault matrixes to carry out induction, synthesis, comparison and classification on the historical knowledge base, obtaining a conclusion after system processing and arrangement, pushing an overhaul scheme and troubleshooting a fault reason.
7. The analytic early warning method of claim 2, wherein the components of the wind turbine equipment comprise a gearbox, a drive train, a sensor, and a pitch of the wind turbine.
8. The utility model provides a wind-powered electricity generation fan data analysis early warning system which characterized in that, analysis early warning system includes:
and a data acquisition module: acquiring data of wind power fan equipment to obtain original data;
the state monitoring module: performing SCADA state detection on the original data;
and a fuzzy logic reasoning algorithm module: triggering an alarm, and reasoning and analyzing the original data with abnormal states through a fuzzy logic reasoning algorithm to acquire potential fault risks;
the fault feature extraction module: extracting fault characteristics of the potential fault risks to obtain potential fault characteristics;
neural network model diagnostic module: diagnosing potential fault characteristics through a neural network model to obtain a fault diagnosis result;
and a detection and diagnosis module: carrying out historical knowledge base retrieval on fault diagnosis results to obtain a diagnosis maintenance strategy;
output and storage module: and outputting a result and storing data, wherein the data storage result is updated to the SCADA state detection standard.
9. The wind power fan data analysis and early warning device is characterized by comprising a processor and a memory connected with the processor; the memory is used for storing program data, and the processor is used for executing the program data to realize the data analysis early warning method according to any one of claims 1 to 7.
10. A computer readable storage medium for storing program data, which when executed by a processor is adapted to carry out the analytical pre-warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311060839.XA CN117151684A (en) | 2023-08-22 | 2023-08-22 | Wind power fan data analysis early warning method, system, device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311060839.XA CN117151684A (en) | 2023-08-22 | 2023-08-22 | Wind power fan data analysis early warning method, system, device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117151684A true CN117151684A (en) | 2023-12-01 |
Family
ID=88883504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311060839.XA Pending CN117151684A (en) | 2023-08-22 | 2023-08-22 | Wind power fan data analysis early warning method, system, device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117151684A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117967524A (en) * | 2024-01-29 | 2024-05-03 | 德州隆达空调设备集团有限公司 | Multi-data fusion fan health monitoring method based on Internet of things |
| CN117972547A (en) * | 2024-03-26 | 2024-05-03 | 华电电力科学研究院有限公司 | Fault early warning method, device and medium for key components of wind turbine generator |
| CN117967524B (en) * | 2024-01-29 | 2024-07-02 | 德州隆达空调设备集团有限公司 | Multi-data fusion fan health monitoring method based on Internet of things |
-
2023
- 2023-08-22 CN CN202311060839.XA patent/CN117151684A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117967524A (en) * | 2024-01-29 | 2024-05-03 | 德州隆达空调设备集团有限公司 | Multi-data fusion fan health monitoring method based on Internet of things |
| CN117967524B (en) * | 2024-01-29 | 2024-07-02 | 德州隆达空调设备集团有限公司 | Multi-data fusion fan health monitoring method based on Internet of things |
| CN117972547A (en) * | 2024-03-26 | 2024-05-03 | 华电电力科学研究院有限公司 | Fault early warning method, device and medium for key components of wind turbine generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsu et al. | Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning | |
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| CN109543210A (en) | A kind of Wind turbines failure prediction system based on machine learning algorithm platform | |
| Zeng et al. | Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation | |
| US11840998B2 (en) | Hydraulic turbine cavitation acoustic signal identification method based on big data machine learning | |
| CN111539553B (en) | Wind turbine generator fault early warning method based on SVR algorithm and off-peak degree | |
| US9483049B2 (en) | Anomaly detection and diagnosis/prognosis method, anomaly detection and diagnosis/prognosis system, and anomaly detection and diagnosis/prognosis program | |
| CN111582392B (en) | Multi-working-condition health state online monitoring method for key components of wind turbine generator | |
| US20130060524A1 (en) | Machine Anomaly Detection and Diagnosis Incorporating Operational Data | |
| CN106779200A (en) | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data | |
| CN114021932A (en) | Energy efficiency evaluation and diagnosis method, system and medium for wind turbine generator | |
| CN111209934A (en) | Fan fault prediction and alarm method and system | |
| CN117151684A (en) | Wind power fan data analysis early warning method, system, device and readable storage medium | |
| Yang et al. | Fault early warning of wind turbine gearbox based on multi‐input support vector regression and improved ant lion optimization | |
| Eickmeyer et al. | Data Driven Modeling for System-Level Condition Monitoring on Wind Power Plants. | |
| CN114841580A (en) | Generator fault detection method based on hybrid attention mechanism | |
| Zhang et al. | A novel fault diagnosis method for wind turbine based on adaptive multivariate time-series convolutional network using SCADA data | |
| CN116578908A (en) | Cross-domain fault diagnosis method, system, medium and equipment for wind power gear box | |
| CN116011982A (en) | Online monitoring method and system for breakage of grinding roller of coal mill | |
| Peng et al. | Semi-Supervised CNN-Based SVDD Anomaly Detection for Condition Monitoring of Wind Turbines | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| CN112202924A (en) | High-power wind turbine generator system bolt intellectual detection system that excels in based on thing networking | |
| Yang et al. | Condition Monitoring for Wind Turbine Pitch System Using Multi-parameter Health Indicator | |
| Ma et al. | Application of SCADA data in wind turbine fault detection–a review | |
| Zheng et al. | Spatio-Temporal Attention-based Neural Network for Wind Turbine Blade Cracking Fault Detection |
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 |