CN113757048A - Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system - Google Patents
Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system Download PDFInfo
- Publication number
- CN113757048A CN113757048A CN202110836447.2A CN202110836447A CN113757048A CN 113757048 A CN113757048 A CN 113757048A CN 202110836447 A CN202110836447 A CN 202110836447A CN 113757048 A CN113757048 A CN 113757048A
- Authority
- CN
- China
- Prior art keywords
- gearbox
- fault diagnosis
- module
- monitoring
- plc
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 72
- 238000012544 monitoring process Methods 0.000 title claims abstract description 62
- 238000005259 measurement Methods 0.000 claims abstract description 62
- 239000013307 optical fiber Substances 0.000 claims abstract description 18
- 230000001133 acceleration Effects 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 6
- 230000018109 developmental process Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000006641 stabilisation Effects 0.000 claims description 4
- 238000011105 stabilization Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000033228 biological regulation Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 230000008054 signal transmission Effects 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Wind Motors (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to an online monitoring and intelligent fault diagnosis system for a wind turbine gearbox, which comprises a piezoelectric acceleration sensor, a four-channel dynamic measurement module, a graphic terminal, a programmable automatic controller, an optical fiber transceiver, an optical fiber ring network switch, an optical fiber ring network, a database server and a client terminal, wherein the piezoelectric acceleration sensor is connected with the four-channel dynamic measurement module; the system is mainly composed of three major parts. The invention can monitor the running state of the gear box in real time, and can perform timely early warning and accurate diagnosis before the fault occurs.
Description
Technical Field
The invention relates to the field of monitoring and diagnosis of a gear box of a wind generating set, in particular to a remote online monitoring and intelligent fault diagnosis system for the gear box of the wind generating set.
Background
With the rapid development of wind power, the problem of operation faults of large-scale wind turbine generators is also highlighted day by day. Because the fan is generally installed at wind gaps in mountains, wastelands and the like and is impacted by random wind load and strong gust, the wind turbine generator system has endless fault layers due to the factors. The wind turbine generator set can influence normal power generation of a wind power plant when in failure, and the maintenance cost of wind power equipment can be greatly increased. The gear box is used as an important component of the mechanical transmission of the fan, and main mechanical elements comprise a transmission shaft, a gear, a bearing and the like. The faults of the gear box account for a great proportion of the faults of the traditional system of the wind turbine generator, and meanwhile, the wind turbine generator is located in a remote environment and is generally located in a narrow space of a high-altitude cabin and difficult to maintain, so that the online monitoring and fault diagnosis of the gear box of the wind turbine generator is very important. The main faults of the existing gearbox parts comprise the problems of abrasion pitting of gears, inner and outer ring faults of bearings and shaft misalignment, and the faults show obvious difference from normal operation in a vibration signal time-frequency domain. Therefore, the gearbox is subjected to vibration monitoring, fault symptoms can be captured at the early stage of the fault, early warning is generated, and potential safety hazards and economic losses caused by further development of the fault are avoided.
There are many cases to realize online vibration monitoring and diagnosis of gearboxes. However, the existing on-line monitoring system can not effectively eliminate the environmental interference, and brings huge resistance to signal processing and analysis; the existing fault diagnosis system adopts a traditional signal extraction and analysis method or a machine learning method, needs a large amount of experience knowledge and data samples, and is particularly difficult to process non-stable nonlinear multi-modulation signals. Therefore, it is necessary to develop a data-driven fault diagnosis and monitoring system which is resistant to external environment interference.
Disclosure of Invention
The invention aims to solve the technical problem of providing a remote online monitoring and fault diagnosis system for a gearbox of a wind generating set, aiming at the defects in the prior art. The system can realize all-weather on-line monitoring and diagnosis under the unattended condition.
Therefore, the invention adopts the following technical scheme:
a wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system comprises a cabin dynamic measurement module and an auxiliary circuit thereof, a tower bottom fault diagnosis PLC and an auxiliary circuit thereof, and a background computer of a centralized control room. The method is characterized in that:
cabin developments measurement module and auxiliary circuit thereof: the dynamic measurement module is used for completing measurement of vibration signals of the gearbox, providing time domain index values and frequency band information required by fault diagnosis, completing measurement processes of analog-to-digital conversion, filtering, FFT (fast Fourier transform) and characteristic values of acceleration signals of seven channels in the module through an embedded DSP (digital signal processor), and transmitting processed data to subsequent parts such as a PLC (programmable logic controller) through Ethernet communication;
the tower bottom fault diagnosis PLC and the auxiliary circuit thereof: the device is used for collecting and caching vibration time-frequency domain information of each position of the gearbox output by the measuring module and judging the vibration state of the gearbox based on a set time-frequency domain threshold value; further preliminarily diagnosing the specific fault category of the gearbox by utilizing an internal wavelet neural network; transmitting the vibration time-frequency domain information and the diagnosis result to a background through an optical fiber ring network;
and the background computer of the centralized control room is used for acquiring and displaying real-time vibration time-frequency domain information of the gear box and a fault state diagnosed by the PLC, or further calling an original vibration signal of the gear box to perform off-line analysis and diagnosis, so as to acquire more accurate fault information. The data transmitted by the front end is stored in the database for inquiry and calling.
In the above wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system, the cabin dynamic measurement module and its auxiliary circuit include:
vibration signal measurement acquisition module and sensor: the system is used for completing the acquisition of vibration signals of the gearbox, adopting a five-path two-wire system general acceleration sensor and a two-path two-wire system low-frequency acceleration sensor according to the requirement of the vibration monitoring of the gearbox, and directly inputting seven acquired analog signals into a dynamic measurement module for preprocessing to obtain vibration trend information required by state monitoring and time-frequency domain characteristic information required by fault diagnosis;
a measuring module base: the terminal is used for defining a TCP/IP address required by the Ethernet communication of the module and providing 16 detachable wiring terminals for the dynamic measurement module; the measuring module base is arranged in the cabin mounting box through a DIN guide rail and is used for fixing the dynamic measuring module through threaded connection;
measuring a module switching power supply: the device is used for providing stable wide current range 24V direct current for the dynamic measurement module and the acceleration sensor. The switching power supply is connected to the measuring module through a power pin on the detachable wiring terminal of the base;
in the online monitoring and intelligent fault diagnosis system for the wind turbine gearbox, the tower bottom fault diagnosis PLC and the auxiliary circuit thereof comprise;
the PLC main controller caches and packs the measurement data output by the dynamic measurement module in real time and can receive an instruction sent by a remote monitoring center to perform centralized regulation and control on the operation parameters of the monitoring system;
the programmable graphic terminal is communicated with the PLC through a network port, receives PLC monitoring data, displays the PLC monitoring data in a map form, and can complete the field control and monitoring of the online measuring system through a touch screen;
the controller power supply module can simultaneously provide stable 24V direct current for the automatic controller and the graphic terminal through the wiring terminal;
the optical fiber ring network switch can communicate with the automatic controller by utilizing the Ethernet, converts the network signal into an optical fiber signal, is connected onto the optical fiber ring network by an optical cable in a lap joint mode, and communicates with the background computer by the optical fiber ring network.
In the online monitoring and intelligent fault diagnosis system for the wind turbine gearbox, the piezoelectric acceleration sensor respectively adopts low-frequency and universal sensors at the input end and the output end of the gearbox according to different rotating speeds, so that vibration information can be more accurately acquired; meanwhile, the shielding cable at the output end of the sensor signal wire is connected to the shielding terminal of the dynamic measurement module, so that external interference can be effectively isolated.
In the online monitoring and intelligent fault diagnosis system for the wind turbine gearbox, the dynamic measurement module selects dynamic measurement or static measurement according to the characteristics of the input signal, and a single measurement module supports the functions of four paths of 24-bit high-precision synchronous analog-to-digital conversion, adaptive filtering, provision of multiple frequency bands required by fault diagnosis and the like, and can be communicated with other dynamic measurement modules or expansion modules based on a local bus.
In the online monitoring and intelligent fault diagnosis system for the wind turbine gearbox, the dynamic measurement module is provided with 2 RJ45 interfaces and 4 paths of buffer outputs, and data can be transmitted in a serial port or network port mode according to actual application requirements.
In the wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system, the measurement module power supply is composed of the switching power supply, the voltage reduction module and the voltage stabilization module. Compared with the conventional linear power supply, the switching power supply is adopted to form the stabilized voltage power supply, so that the peripheral elements required by the stabilized voltage power supply are few, the power supply is small in size and low in power consumption, and the working efficiency is high.
In the online monitoring and intelligent fault diagnosis system for the wind turbine generator gearbox, the fault diagnosis PLC diagnoses the fault state of the gearbox by adopting the following steps:
step S1, dividing the frequency band number and the corresponding frequency range according to the distribution of the fan characteristic frequency, and writing the frequency band number and the corresponding frequency range into a dynamic measurement module;
step S2, determining a limit value of a trend value between normal/early warning, early warning/warning states according to the fan vibration monitoring standard;
step S3, determining the early warning and warning threshold value of each frequency band of each channel by combining the energy distribution characteristics of the signal spectrum signal of the gear box;
step S4, judging whether the voltage of each channel of the system is in a normal range, and determining whether the signal transmission link has a fault;
step S5, on the premise that the channels are normal, judging whether the time domain characteristics and the frequency domain characteristics of each channel exceed the standard by adopting a three-level alarm algorithm, and determining whether the gearbox has a fault;
and step S6, after the gear box is determined to have faults, the wavelet neural network is adopted to call the cache data to further judge the concrete faults of the gear box.
In the wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system, the PLC provides a data transparent transmission function and can also realize a data analysis and processing process. The controller supports linear, star and DLR equipment ring network topological structures, and can form more complex network structures based on other communication equipment.
In the wind turbine gearbox on-line monitoring and intelligent fault diagnosis system, the graphic terminal is allowed to be connected to 1 controller, up to 25 pictures and 200 alarms can be provided, and the controllers can be monitored and developed on site through the touch screen.
The invention can monitor the running state of the gear box in real time, and can perform timely early warning and accurate diagnosis before the fault occurs.
Drawings
FIG. 1 is an overall topological diagram of a remote online monitoring and intelligent fault diagnosis system for a gearbox of a wind generating set.
FIG. 2 is a schematic composition diagram of a wind generating set gearbox remote on-line monitoring and intelligent fault diagnosis system of the present invention.
FIG. 3 is a flow chart of fault analysis of the wind turbine generator system gearbox remote on-line monitoring and intelligent fault diagnosis system of the present invention.
FIG. 4 is a measuring point layout diagram of the wind generating set gearbox remote on-line monitoring and intelligent fault diagnosis system of the invention.
FIG. 5 is a flow chart of a wavelet neural network adopted by the wind generating set gearbox remote on-line monitoring and intelligent fault diagnosis system in a PLC.
Detailed Description
The invention is further described with reference to the drawings and the detailed description.
As shown in fig. 1, the wind turbine gearbox on-line monitoring and intelligent fault diagnosis system is composed of a cabin dynamic measurement module and an auxiliary circuit thereof, a tower bottom fault diagnosis PLC and an auxiliary circuit thereof, and a background computer of a centralized control room. The cabin dynamic measuring module and the auxiliary circuit thereof comprise a vibration signal measuring and collecting module, a sensor, a measuring module base and a measuring module switching power supply. The tower bottom fault diagnosis PLC and the auxiliary circuit thereof comprise a PLC main controller, a programmable graphic terminal, a controller power supply module and an optical fiber ring network switch. The monitoring center as a background is a networked high-performance industrial personal computer which mainly comprises a database server and a data display analysis client.
The wind turbine gearbox on-line monitoring and intelligent fault diagnosis system based on the hardware equipment has the specific fault analysis process shown in fig. 3. The method comprises the following steps that preprocessing processes such as analog-to-digital conversion and filtering are completed in a dynamic measurement module according to gearbox vibration data collected by a sensor, calculation of a trend value and characteristic quantity is completed in the module, and a PLC obtains signal characteristics calculated by the module and preliminarily determines the state of a gearbox by utilizing an internal three-level alarm program; after the fault state of the gearbox is detected, the signal characteristic value is input into a wavelet neural network to determine the specific fault type of the gearbox, the fault state and fault type information of the gearbox are transmitted to a background, the background further extracts an original vibration signal from a measuring module for detailed time-frequency domain analysis, and finally the specific fault information of the gearbox is determined to form a diagnosis report and a maintenance decision.
The piezoelectric acceleration sensor is used for collecting vibration signals of the gearbox, a five-path double-wire system general acceleration sensor and a two-path double-wire system low-frequency acceleration sensor are adopted according to the requirement of vibration monitoring of the gearbox, and seven collected channel analog signals are directly input into the dynamic measurement module for preprocessing. According to different rotating speeds, low-frequency and general sensors are respectively adopted at the input end and the output end of the gear box, so that vibration information can be acquired more accurately; meanwhile, the shielding cable at the output end of the sensor signal wire is connected to the shielding terminal of the dynamic measurement module, so that external interference can be effectively isolated.
The selection of the online monitoring measuring point position and the setting of the measuring point acquisition parameters are of great importance to the online monitoring effect. The arrangement and optimization of the measuring points of the gearbox sensor influence the detection and diagnosis of the system to be a very important factor. Although the existing knowledge-based or analytical model-based method can find the optimized measuring point, the accuracy of the optimized result without fault diagnosis is not obviously related. Therefore, the invention adopts the following scheme to arrange the sensor measuring points:
and step S1, determining the quantity of the sensors mounted at each part of the wind turbine according to the vibration monitoring standard VDI _3834 of the wind generating set. Arranging 2 sensors on a main shaft bearing and 5 sensors on a gear box according to a standard;
step S2, performing dynamic modeling on the gear box according to the structural parameters of the gear box, analyzing the vibration mode of the gear box to find a maximum value point of the vibration response of the gear box, and thus preliminarily determining the installation position of the sensor;
and step S3, taking the characteristic values of the test data of the multiple measuring points as input, taking the diagnosis error of fault diagnosis as an objective function, measuring the similarity degree between the measuring points according to the similarity degree between the vibration signal characteristics of the measuring points, and establishing a BP neural network model for measuring point optimization under different fault states on the basis of a measuring point rough determination scheme, thereby further determining the most sensitive part to fault information and finding the final installation position of the sensor. According to the principle, the measuring point arrangement scheme is determined as shown in FIG. 4.
TABLE 1 measurement Point and corresponding position sensor parameter selection
The dynamic measurement module is used for completing measurement of vibration signals of the gearbox, dynamic measurement or static measurement can be selected according to characteristics of input signals, time domain index values and frequency band information required by fault diagnosis are provided, four paths of acceleration signals complete analog-to-digital conversion, filtering, FFT and characteristic value measurement processes in the module, the module is provided with 2 RJ45 interfaces and 4 paths of buffer output, and processed data can be transmitted to subsequent parts such as a PLC (programmable logic controller) and the like in a serial port or network port mode according to actual application requirements. A single measurement module supports functions of 4-path 24-bit high-precision synchronous analog-digital conversion, adaptive filtering, provision of multiple frequency bands required by fault diagnosis and the like, and can also communicate with other dynamic measurement modules or expansion modules based on a local bus.
The measurement module base provides a fixture for the dynamic measurement module by a threaded connection and may be mounted into the nacelle mounting box via a DIN rail. The measurement module base may be used to define the TCP/IP address required for modular ethernet communications while providing 16 removable terminals for the dynamic measurement module.
The measuring module power supply provides direct current power supply for the dynamic measuring module and the acceleration sensor through the detachable wiring terminal of the base, and the power supply is composed of a switching power supply, a voltage reduction module and a voltage stabilization module. Compared with the conventional linear power supply, the switching power supply is adopted to form the stabilized voltage power supply, so that the peripheral elements required by the stabilized voltage power supply are few, and the protection circuit for overcurrent, overheat and adjusting tubes is arranged in the circuit. The switch power supply is stabilized by the duty ratio of the switch, the power supply is small in size, low in power consumption and high in working efficiency. The voltage reduction module and the voltage stabilization module are matched to use, so that wide-range voltage output under actual working conditions can be realized.
The PLC main controller caches and packs the measurement data output by the dynamic measurement module in real time, and can receive an instruction sent by a remote monitoring center to perform centralized regulation and control on the operation parameters of the monitoring system. The PLC controller not only provides the function of data transmission, but also can utilize an internally loaded program to realize the data analysis and processing process. The controller supports linear, star and DLR equipment ring network topological structures, and can form more complex network structures based on other communication equipment.
The traditional fault diagnosis system is carried out on a MATlab platform based on a PC or a C language platform. The PLC transmits the process data to the background PC to carry out neural network training and classification, modifies the control parameters or the control quantity according to the classification result, and then transmits the result back to the PLC to carry out control decision. Although this method has great flexibility, it has many disadvantages: firstly, data and transmission result information need to be acquired from a PLC system and transmitted to the PLC system repeatedly, and are constrained by a communication network and a PC platform; the uncertainty of the calculation time of the neural network does not meet the real-time certainty requirement pursued by the industrial process control; thirdly, the high requirement of the industrial environment poses a challenge to the running environment of the PC platform, and the pressure of data transmission and background processing is increased.
At present, fault diagnosis systems based on PLC platforms mainly comprise data analysis processing and pattern recognition. The PLC diagnosis method based on the expert system is applied to a large number of actual fields, however, the expert system has no self-learning capability and cannot adjust rules automatically, so that the PLC fault diagnosis expert system has great limitation in the application process.
In view of the above reasons, the invention is based on the neural network principle and the PLC programming method, realizes the diagnosis of the wavelet neural network on the fault on the PLC platform, and obtains good effect. After the neural network is trained off line, the field monitoring data is input in an on-line state, and then a fault classification result can be obtained. The results can provide reference for background analysis and maintenance decisions.
The programmable graphic terminal is communicated with the PLC through the internet access, receives PLC monitoring data and displays the data in a map form, is allowed to be connected to 1 controller, can provide up to 25 pictures and 200 alarms, and can complete field-level monitoring and development on the controller through the touch screen.
The controller power supply module can simultaneously provide stable 24V direct current for the automatic controller and the graphic terminal through the wiring terminal;
the optical fiber ring network switch can communicate with the automatic controller by utilizing Ethernet, converts a network signal into an optical fiber signal, is connected to the optical fiber ring network in a lap joint mode through an optical cable, and communicates with the background computer through the optical fiber ring network.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited thereto, and any other modifications or equivalent substitutions made by the technical solution of the present invention by those skilled in the art can be covered within the scope of the claims of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system comprises a cabin dynamic measurement module and an auxiliary circuit thereof, a tower bottom fault diagnosis PLC and an auxiliary circuit thereof, and a background computer of a centralized control room; the method is characterized in that:
cabin developments measurement module and auxiliary circuit thereof: the dynamic measurement module is used for completing measurement of vibration signals of the gearbox, providing time domain index values and frequency band information required by fault diagnosis, completing measurement processes of analog-to-digital conversion, filtering, FFT (fast Fourier transform) and characteristic values of acceleration signals of seven channels in the module through an embedded DSP (digital signal processor), and transmitting processed data to subsequent parts such as a PLC (programmable logic controller) through Ethernet communication;
the tower bottom fault diagnosis PLC and the auxiliary circuit thereof: the device is used for collecting and caching vibration time-frequency domain information of each position of the gearbox output by the measuring module and judging the vibration state of the gearbox based on a set time-frequency domain threshold value; further preliminarily diagnosing the specific fault category of the gearbox by utilizing an internal wavelet neural network; transmitting the vibration time-frequency domain information and the diagnosis result to a background through an optical fiber ring network;
the background computer of the centralized control room is used for acquiring and displaying real-time vibration time-frequency domain information of the gearbox and a fault state diagnosed by the PLC, or further calling an original vibration signal of the gearbox to perform off-line analysis and diagnosis to acquire more accurate fault information; the data transmitted by the front end is stored in the database for inquiry and calling.
2. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system according to claim 1, wherein the nacelle dynamic measurement module and its auxiliary circuits comprise:
vibration signal measurement acquisition module and sensor: the system is used for completing the acquisition of vibration signals of the gearbox, adopting a five-path two-wire system general acceleration sensor and a two-path two-wire system low-frequency acceleration sensor according to the requirement of the vibration monitoring of the gearbox, and directly inputting seven acquired analog signals into a dynamic measurement module for preprocessing to obtain vibration trend information required by state monitoring and time-frequency domain characteristic information required by fault diagnosis;
a measuring module base: the terminal is used for defining a TCP/IP address required by the Ethernet communication of the module and providing 16 detachable wiring terminals for the dynamic measurement module; the measuring module base is arranged in the cabin mounting box through a DIN guide rail and is used for fixing the dynamic measuring module through threaded connection;
measuring a module switching power supply: the device is used for providing stable wide current range 24V direct current for the dynamic measurement module and the acceleration sensor; the switch power supply is connected to the measuring module through a power pin on the detachable wiring terminal of the base.
3. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system according to claim 1, wherein the tower bottom fault diagnosis PLC and its auxiliary circuit comprise;
the PLC main controller caches and packs the measurement data output by the dynamic measurement module in real time and can receive an instruction sent by a remote monitoring center to perform centralized regulation and control on the operation parameters of the monitoring system;
the programmable graphic terminal is communicated with the PLC through a network port, receives PLC monitoring data, displays the PLC monitoring data in a map form, and can complete the field control and monitoring of the online measuring system through a touch screen;
the controller power supply module can simultaneously provide stable 24V direct current for the automatic controller and the graphic terminal through the wiring terminal;
the optical fiber ring network switch can communicate with the automatic controller by utilizing the Ethernet, converts the network signal into an optical fiber signal, is connected onto the optical fiber ring network by an optical cable in a lap joint mode, and communicates with the background computer by the optical fiber ring network.
4. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system as claimed in claim 2, wherein the piezoelectric acceleration sensor respectively adopts low-frequency and general sensors at the input end and the output end of the gearbox according to different rotating speeds, so that vibration information can be more accurately acquired; meanwhile, the shielding cable at the output end of the sensor signal wire is connected to the shielding terminal of the dynamic measurement module, so that external interference can be effectively isolated.
5. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system according to claim 2, wherein the dynamic measurement module selects dynamic measurement or static measurement according to the characteristics of input signals, and a single measurement module supports four paths of functions such as 24-bit high-precision synchronous analog-to-digital conversion, adaptive filtering, provision of multiple frequency bands required by fault diagnosis and the like, and can be communicated with other dynamic measurement modules or expansion modules based on a local bus.
6. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system as claimed in claim 2, wherein the dynamic measurement module is provided with 2 RJ45 interfaces and 4 paths of buffer outputs, and can transmit data in a serial port or network port mode according to actual application requirements.
7. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system as claimed in claim 2, wherein the measurement module power supply is composed of a switching power supply, a voltage reduction module and a voltage stabilization module; compared with the conventional linear power supply, the switching power supply is adopted to form the stabilized voltage power supply, so that the peripheral elements required by the stabilized voltage power supply are few, the power supply is small in size and low in power consumption, and the working efficiency is high.
8. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system of claim 3, wherein the fault diagnosis PLC diagnoses a gearbox fault state by adopting the following steps:
step S1, dividing the frequency band number and the corresponding frequency range according to the distribution of the fan characteristic frequency, and writing the frequency band number and the corresponding frequency range into a dynamic measurement module;
step S2, determining a limit value of a trend value between normal/early warning, early warning/warning states according to the fan vibration monitoring standard;
step S3, determining the early warning and warning threshold value of each frequency band of each channel by combining the energy distribution characteristics of the signal spectrum signal of the gear box;
step S4, judging whether the voltage of each channel of the system is in a normal range, and determining whether the signal transmission link has a fault;
step S5, on the premise that the channels are normal, judging whether the time domain characteristics and the frequency domain characteristics of each channel exceed the standard by adopting a three-level alarm algorithm, and determining whether the gearbox has a fault;
and step S6, after the gear box is determined to have faults, the wavelet neural network is adopted to call the cache data to further judge the concrete faults of the gear box.
9. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system as claimed in claim 3, wherein the PLC is further configured to implement a data analysis and processing process; the controller supports linear, star and DLR device-level ring network topological structures, and can form a complex network structure based on other communication devices.
10. The wind turbine generator gearbox on-line monitoring and intelligent fault diagnosis system as claimed in claim 3, wherein the graphic terminal allows connection to 1 controller, provides 25 pictures and 200 alarms, and can complete field level monitoring and development on the controller through a touch screen.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110836447.2A CN113757048B (en) | 2021-07-23 | 2021-07-23 | Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110836447.2A CN113757048B (en) | 2021-07-23 | 2021-07-23 | Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113757048A true CN113757048A (en) | 2021-12-07 |
CN113757048B CN113757048B (en) | 2024-07-16 |
Family
ID=78787881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110836447.2A Active CN113757048B (en) | 2021-07-23 | 2021-07-23 | Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113757048B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115728057A (en) * | 2022-11-03 | 2023-03-03 | 华能国际电力股份有限公司安徽风电分公司 | Vibration monitoring and fault diagnosis method for gearbox of wind generating set |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101858778A (en) * | 2010-05-28 | 2010-10-13 | 浙江大学 | Vibration monitoring-based wind generator set automatic fault diagnosis method |
US20120025526A1 (en) * | 2010-07-30 | 2012-02-02 | General Electric Company | System and method for monitoring wind turbine gearbox health and performance |
CN202735788U (en) * | 2012-03-31 | 2013-02-13 | 广东电网公司电力科学研究院 | Wind generating set running state remote-monitoring and fault diagnosis system |
CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
CN103529386A (en) * | 2013-10-12 | 2014-01-22 | 山西大学工程学院 | System and method for remote real-time state monitoring and intelligent failure diagnosis of wind turbine generators |
CN106092565A (en) * | 2016-06-08 | 2016-11-09 | 成都阜特科技股份有限公司 | A kind of Vibration Analysis method and system thereof |
US20190033169A1 (en) * | 2016-03-30 | 2019-01-31 | Ntn Corporation | State monitoring system of gear device and state monitoring method |
WO2019218408A1 (en) * | 2018-05-15 | 2019-11-21 | 江苏大学 | Internet of things-based device and method for monitoring typical health status of pump unit |
CN111461497A (en) * | 2020-03-12 | 2020-07-28 | 许昌许继风电科技有限公司 | Wind turbine generator early warning method and system with intelligent diagnosis function |
-
2021
- 2021-07-23 CN CN202110836447.2A patent/CN113757048B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101858778A (en) * | 2010-05-28 | 2010-10-13 | 浙江大学 | Vibration monitoring-based wind generator set automatic fault diagnosis method |
US20120025526A1 (en) * | 2010-07-30 | 2012-02-02 | General Electric Company | System and method for monitoring wind turbine gearbox health and performance |
CN202735788U (en) * | 2012-03-31 | 2013-02-13 | 广东电网公司电力科学研究院 | Wind generating set running state remote-monitoring and fault diagnosis system |
CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
CN103529386A (en) * | 2013-10-12 | 2014-01-22 | 山西大学工程学院 | System and method for remote real-time state monitoring and intelligent failure diagnosis of wind turbine generators |
US20190033169A1 (en) * | 2016-03-30 | 2019-01-31 | Ntn Corporation | State monitoring system of gear device and state monitoring method |
CN106092565A (en) * | 2016-06-08 | 2016-11-09 | 成都阜特科技股份有限公司 | A kind of Vibration Analysis method and system thereof |
WO2019218408A1 (en) * | 2018-05-15 | 2019-11-21 | 江苏大学 | Internet of things-based device and method for monitoring typical health status of pump unit |
CN111461497A (en) * | 2020-03-12 | 2020-07-28 | 许昌许继风电科技有限公司 | Wind turbine generator early warning method and system with intelligent diagnosis function |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115728057A (en) * | 2022-11-03 | 2023-03-03 | 华能国际电力股份有限公司安徽风电分公司 | Vibration monitoring and fault diagnosis method for gearbox of wind generating set |
Also Published As
Publication number | Publication date |
---|---|
CN113757048B (en) | 2024-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106525415B (en) | Health state evaluation system and method for transmission chain of wind turbine generator | |
CN103234585A (en) | Online monitoring and fault diagnosis system of large wind turbine units | |
EP3444944B1 (en) | Fault detection and positioning system for cell panel in large-scale photovoltaic array | |
CN103343728A (en) | Wind generating set remote on-line multi-mode health state monitoring and fault diagnosis system | |
CN110907170B (en) | Wind turbine generator gearbox bearing temperature state monitoring and fault diagnosis method | |
CN202326011U (en) | State-monitoring and fault-diagnosis system of wind-power set | |
CN102033200A (en) | On-line monitoring and diagnosis method of AC (alternating current) motor based on statistical model | |
CN111878322B (en) | Wind power generator device | |
CN113757048B (en) | Wind turbine generator system gear box on-line monitoring and intelligent fault diagnosis system | |
CN204591656U (en) | Based on thermal power plant turbine pumping unit fault pre-alarming and the optimized maintenance system of industry internet | |
TW202208746A (en) | Fault diagnosis system and method for wind turbine wherein the hidden faults in the operation process can be found in time through the real-time monitoring and trend prediction of the operating status of wind power generation equipment | |
CN108491622A (en) | A kind of fault diagnosis method and system of Wind turbines | |
CN116378910A (en) | Real-time monitoring and fault diagnosis system for gearbox of wind driven generator | |
CN112855462A (en) | Early warning method and system for fan equipment | |
CN116644672A (en) | Aeroengine rolling bearing fault diagnosis method based on residual error network | |
CN203333098U (en) | Dynamic load monitoring device of lifting bearing component of coal mine vertical shaft | |
CN113267711B (en) | On-line monitoring system and method for insulation state of high-voltage electrical equipment of transformer substation | |
Yuan et al. | The application analysis of fault diagnosis with artificial Intelligent for industrial equipment | |
CN218439629U (en) | Wind turbine generator system state monitoring system based on 5G + industrial internet | |
CN219888203U (en) | Real-time monitoring and fault diagnosis system for gearbox of wind driven generator | |
CN107544024A (en) | A kind of generator brush slip ring burn fault degree diagnostic method | |
CN219730398U (en) | Safety operation monitoring system of fixed winch hoist | |
CN218151256U (en) | Over-temperature monitoring system for gear box bearing of wind generating set | |
CN112628089B (en) | Abnormity monitoring method, system, platform, electronic equipment and storage medium | |
Yu et al. | Real-time intelligent monitoring system in manufacturing system |
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 |