CN111472946A - Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set - Google Patents
Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set Download PDFInfo
- Publication number
- CN111472946A CN111472946A CN202010290769.7A CN202010290769A CN111472946A CN 111472946 A CN111472946 A CN 111472946A CN 202010290769 A CN202010290769 A CN 202010290769A CN 111472946 A CN111472946 A CN 111472946A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- maintenance
- storage unit
- intelligent
- 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
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
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
- F03D80/50—Maintenance or repair
-
- 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
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent auxiliary maintenance system of a wind generating set, which is characterized in that a maintenance site is in real-time butt joint with technical experts through a coordination processor, so that the experts can provide remote technical guidance for the maintenance site conveniently, meanwhile, an intelligent processing module of the system can store and manage related maintenance data in the system, future learning and experience accumulation are facilitated, a more convenient and efficient learning platform is provided for maintenance personnel, and meanwhile, the efficiency of maintenance work of the wind generating set is greatly improved. The invention also discloses an intelligent auxiliary maintenance method for the wind generating set, which applies the previously accumulated experience data to the fault processing work of the on-site wind generating set, and can more quickly and accurately locate the fault point by matching with the remote guidance of experts, thereby greatly improving the maintenance efficiency of the wind generating set, and meanwhile, the maintenance personnel can also improve the self ability and accumulate the experience through the continuously updated maintenance data.
Description
Technical Field
The invention relates to the technical field of intelligent maintenance of electromechanical equipment, in particular to an intelligent auxiliary maintenance system and an auxiliary maintenance method for a wind generating set.
Background
At present, the maintenance work of a wind generating set mostly depends on the actual operation experience judgment of operation and maintenance personnel, after a new fault occurs, the fault position can be searched and the fault cause can be analyzed only by looking up a fault processing manual and a wind generating set drawing, and finally a fault maintenance scheme is given.
Therefore, how to provide an intelligent auxiliary maintenance system for a wind generating set, which is intelligent, efficient and convenient for operation and maintenance personnel to improve the capability, is a problem that needs to be solved urgently by technical personnel in the field.
Disclosure of Invention
In view of the above, the invention provides an intelligent auxiliary maintenance system and an auxiliary maintenance method for a wind generating set, the system enables a field maintenance working end to be in butt joint with an expert client, an expert guides the system in real time, and meanwhile, maintenance data can be stored in the system in a classified mode, so that the problems that an existing wind generating set maintenance mode is time-consuming and labor-consuming, low in maintenance working efficiency and slow in maintenance personnel capacity improvement are solved.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides an intelligent auxiliary maintenance system for a wind generating set, comprising:
the working condition data interface is in communication connection with an external fan working condition data source and is used for reading external monitoring data;
the field maintenance working end is used for acquiring field maintenance information and performing virtual-real fusion processing;
the expert client is used for acquiring and inputting expert knowledge data and providing a self-learning processing model of related operation and maintenance affairs of the unit, spare part attribute information and unit mechanism model data;
the coordination processor is in communication connection with the working condition data interface, the field maintenance working end and the expert client, and is used for analyzing, processing and forwarding the received data; and
and the coordination processor is also in communication connection with the intelligent processing module, and the intelligent processing module is used for storing and managing system related data and executing an intelligent computing function.
The invention has the beneficial effects that: the system is used for carrying out real-time butt joint on a maintenance site and technical experts through the coordination processor, so that the experts can provide remote technical guidance for the maintenance site, meanwhile, an intelligent processing module of the system can store and manage related maintenance data in the system, future learning and experience accumulation are facilitated, a more convenient and efficient learning platform is provided for maintenance personnel, and meanwhile, the efficiency of maintenance work of the wind generating set is greatly improved.
On the basis of the above scheme, the scheme provided by the invention is further explained.
Further, the working condition data interface comprises a unit SCADA system interface and a unit operation log interface. The working condition data interface is a group of network interface hardware, supports wired, wireless and other industrial common buses or network forms, can receive the working condition data of the unit from a unit SCADA system interface and a unit operation log interface, and is used for assisting maintenance decisions.
Furthermore, the field maintenance working end comprises a maintenance data acquisition unit, a first data identification unit, a first virtual-real fusion unit and a first human-computer interaction unit, the maintenance data acquisition unit is connected with the first human-computer interaction unit sequentially through the first data identification unit and the first virtual-real fusion unit, and the first data identification unit, the first virtual-real fusion unit and the first human-computer interaction unit are respectively connected with the coordination processor;
the maintenance data acquisition unit is used for acquiring maintenance data of a user in the maintenance process of the wind generating set, the first data identification unit is used for extracting key information in the maintenance data acquired by the maintenance data acquisition unit, the first virtual-real fusion unit is used for fusing real graphs in the key information with virtual graphs stored in advance, and the first human-computer interaction unit is used for displaying the fused data.
Furthermore, the expert client comprises an expert data acquisition unit, a second data identification unit, a second virtual-real fusion unit and a second human-computer interaction unit, wherein the expert data acquisition unit is connected with the second human-computer interaction unit sequentially through the second data identification unit and the second virtual-real fusion unit, and the second data identification unit, the second virtual-real fusion unit and the second human-computer interaction unit are respectively connected with the coordination processor;
the expert data acquisition unit is used for acquiring input expert knowledge data, the second data identification unit is used for extracting key information in the expert knowledge data acquired by the expert data acquisition unit, the second virtual-real fusion unit is used for fusing real graphs in the key information with virtual graphs stored in the key information, and the second human-computer interaction unit is used for displaying the fused data.
Furthermore, the intelligent processing module comprises a storage unit and an intelligent processor, the storage unit is connected with the intelligent processor, the intelligent processor is in communication connection with the coordination processor, the intelligent processor is used for performing data interaction with the coordination processor and analyzing and processing the received data, and the storage unit is used for storing the data received and processed by the intelligent processor in real time.
Further, the storage unit comprises a self-learning model storage unit, an empirical knowledge data storage unit, a fact data storage unit, a spare part data storage unit, a unit structure data storage unit and a personal ability evaluation storage unit, and the self-learning model storage unit, the empirical knowledge data storage unit, the fact data storage unit, the spare part data storage unit, the unit structure data storage unit and the personal ability evaluation storage unit are respectively and electrically connected with the intelligent processor;
the self-learning model storage unit is used for storing and updating a unit related operation and maintenance affair self-learning processing model, the empirical knowledge data storage unit is used for storing knowledge data learned by the self-learning model, the fact data storage unit is used for storing expert knowledge data extracted by the expert client and animation demonstration data of related troubleshooting and troubleshooting generated by processing maintenance data extracted by the field maintenance working end through the intelligent processor, the spare part data storage unit is used for storing the number of spare parts, spare part attribute information and a three-dimensional model, the unit structure data storage unit is used for storing a unit structure, a part connection condition and the three-dimensional model of the unit, and the personal ability evaluation storage unit is used for storing evaluation data of a system on the ability of maintenance personnel.
On the other hand, the invention also provides an intelligent auxiliary maintenance method for the wind generating set, which comprises the following steps:
s1: the method comprises the steps of storing an operation and maintenance affair self-learning processing model related to the unit, animation demonstration data of fault processing steps, spare part attribute information and three-dimensional models thereof, unit structure and component connection conditions and three-dimensional models thereof in a classified manner in advance;
s2: collecting working condition historical data of the wind generating set, carrying out deep mining and fusion on the working condition historical data and the structure knowledge data according to a pre-stored self-learning model of related operation and maintenance affairs of the wind generating set and the structure knowledge data of the wind generating set to generate experience knowledge, and storing the experience data in real time;
s3: receiving a fault code when a fault occurs, positioning a maximum-possibility damaged component according to prestored empirical data, recommending the maximum-possibility damaged component to a field maintenance working end, and determining a target fault point by the field maintenance working end according to the received maximum-possibility damaged component;
s4: acquiring video data of a target fault point in real time, calling prestored animation demonstration data of the target fault point, fusing the animation demonstration data with the video data of the target fault point acquired in real time, and displaying the video data to field maintenance personnel;
s5: if the component can not be located to the maximum possibility to be damaged according to the prestored experience data, automatically connecting the field maintenance working end to the expert client, transmitting the fault code and the maintenance field video to the expert client in real time, and determining a fault point and providing a maintenance scheme by the real-time butt joint of the expert client and the field maintenance working end;
s6: and storing the final maintenance scheme in real time, and updating experience data.
Further, the step S3 specifically includes:
s301: determining the most probable damaged component according to the received fault code and by combining empirical data, and acquiring a picture of the most probable damaged component;
s302: the field maintenance working end collects the video data of the electric appliance cabinet where the most-possibly-damaged part is located in real time;
s303: respectively acquiring current frame data of the video data when suspected damaged parts appear each time, and extracting semantic features of each current frame data;
s304: and performing data fusion on semantic features of a plurality of current frame data in a stacking mode, and judging whether a suspected damaged part appearing in the video data is the most possibly damaged part or not according to the similarity.
According to the technical scheme, compared with the prior art, the intelligent auxiliary maintenance method for the wind generating set is disclosed, the previously accumulated experience data are applied to the fault handling work of the on-site wind generating set, and the fault point can be positioned more quickly and accurately by being matched with expert remote guidance, so that the maintenance efficiency of the wind generating set is greatly improved, and meanwhile, the self ability of maintenance personnel can be improved through continuously updated maintenance data, and the experience is accumulated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of an overall structure of an intelligent auxiliary maintenance system for a wind turbine generator system according to the present invention;
FIG. 2 is a schematic diagram illustrating an implementation principle of a self-learning model storage database, a spare part information database and a unit structure database in the embodiment of the invention;
FIG. 3 is a schematic diagram illustrating an implementation principle of an empirical knowledge database construction function according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a system failure point recommendation function implemented in an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating an implementation principle of a system-aided guidance function according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating an implementation principle of an expert online guidance function according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating an implementation principle of an online learning and training function according to an embodiment of the present invention;
FIG. 8 is a schematic view of an installation of an auxiliary maintenance system for a wind turbine generator system according to the present invention;
FIG. 9 is a schematic flow chart of an intelligent auxiliary maintenance method for a wind turbine generator system according to the present invention;
fig. 10 is a schematic diagram of a fault component locating process in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
On one hand, the embodiment of the invention discloses an intelligent auxiliary maintenance system of a wind generating set, which comprises the following components:
the working condition data interface 2 is in communication connection with an external fan working condition data source and is used for reading external monitoring data;
the field maintenance working end 3 is used for acquiring field maintenance information and performing virtual-real fusion processing;
the expert client 5 is used for acquiring and inputting expert knowledge data and providing a self-learning processing model of related operation and maintenance affairs of the unit, spare part attribute information and unit mechanism model data;
the coordination processor 1, the working condition data interface 2, the field maintenance working end 3 and the expert client 5 are all in communication connection with the coordination processor 1, and the coordination processor 1 is used for analyzing, processing and forwarding the received data; and
the intelligent processing module 4 and the coordination processor 1 are also in communication connection with the intelligent processing module 4, and the intelligent processing module 4 is used for storing and managing system-related data and executing intelligent computing functions.
In a specific embodiment, the operating condition data interface 2 comprises a unit SCADA system interface 21 and a unit operation log interface 22. The working condition data interface 2 is a group of network interface hardware, supports wired, wireless and other industrial common buses or network forms, can receive unit working condition data from a unit SCADA system interface 21 and a unit operation log interface 22, and is used for assisting maintenance decisions.
In a specific embodiment, the field maintenance work end 3 includes a maintenance data acquisition unit 31, a first data identification unit 32, a first virtual-real fusion unit 33 and a first human-machine interaction unit 34, the maintenance data acquisition unit 31 is connected with the first human-machine interaction unit 34 sequentially through the first data identification unit 32 and the first virtual-real fusion unit 33, and the first data identification unit 32, the first virtual-real fusion unit 33 and the first human-machine interaction unit 34 are respectively connected with the coordination processor 1;
the maintenance data acquisition unit 31 is used for acquiring maintenance data of a user in a maintenance process of the wind generating set, the first data identification unit 32 is used for extracting key information in the maintenance data acquired by the maintenance data acquisition unit 31, the first virtual-real fusion unit 33 is used for fusing a real graph in the key information with a virtual graph stored in advance, and the first human-computer interaction unit 34 is used for displaying the fused data.
In this embodiment, the field maintenance terminal 3 is a fixed terminal, a mobile terminal or a wearable device, the maintenance data acquisition unit 31 is a mobile phone, a camera of a tablet computer, a microphone or other movable cameras, a recording device, etc. carried by a maintenance person and used for acquiring a maintenance process of a unit or other information of a user, the first data identification unit 32 is a high-speed processor of a graph, an audio frequency, and a text installed on the wearable device carried by the maintenance person and used for extracting a useful part of video, an image, and text information acquired by the maintenance data acquisition unit 31, the first virtual-real fusion unit 33 is a data fusion processor on the wearable device carried by the maintenance person and used for properly fusing a virtual graph with a real graph, the first human-machine interaction unit 34 is a touch display screen installed on a control panel of a cabin of the unit and a mobile phone of the maintenance person, The tablet computer, the personal computer display device, the input device and the like are selected according to actual conditions and used for displaying the processing result of the first virtual-real fusion unit 33 and other information needing to be displayed.
In a specific embodiment, the expert client 5 includes an expert data acquisition unit 51, a second data identification unit 52, a second virtual-real fusion unit 53 and a second human-computer interaction unit 54, the expert data acquisition unit 51 is connected with the second human-computer interaction unit 54 sequentially through the second data identification unit 52 and the second virtual-real fusion unit 53, and the second data identification unit 52, the second virtual-real fusion unit 53 and the second human-computer interaction unit 54 are respectively connected with the coordination processor 1;
the expert data acquisition unit 51 is used for acquiring input expert knowledge data, the second data identification unit 52 is used for extracting key information in the expert knowledge data acquired by the expert data acquisition unit 51, the second virtual-real fusion unit 53 is used for fusing real graphs in the key information with virtual graphs stored in the key information, and the second human-computer interaction unit 54 is used for displaying the fused data.
In this embodiment, the expert client 5 solidifies the self-learning processing model, the spare part attribute information and the unit mechanism model of the operation and maintenance affairs related to the unit into the intelligent processing module 4 through the coordination processor 1, automatically generates knowledge data about the operation and maintenance affairs according to data input by the working condition data interface 2 and by combining the solidified model and information in the intelligent processing module 4, and stores the knowledge data into the intelligent processing module 4, and the field work terminal 3 performs data interaction through the coordination processor 1, the intelligent processing module 4 and the expert client 5 to provide support for the operation and maintenance related affairs.
Specifically, the expert client 5 is a fixed terminal, a mobile terminal or a wearable device, the expert data collecting unit 51 is a mobile phone carried by an expert, a camera of a tablet computer, a microphone or other movable cameras, a recording device or the like, for collecting input expert knowledge data, the second data recognition unit 52 is a graphic, audio, text high speed processor on an expert device, for extracting useful parts of the video, image, text information collected by the expert data collection unit 51, the second virtual-real fusion unit 53 is a data fusion processor on the expert device, for appropriately fusing the virtual graphics with the real graphics, the second human-computer interaction unit 54 is a mobile phone, a tablet computer, a personal computer display device, an earphone, a sound device, etc. carried by an expert, and the selection is performed according to actual conditions, and is used for displaying the processing result of the second virtual-real fusion unit 53 and other information required to be displayed.
In this embodiment, the coordination processor 1 is a computer system including an embedded processor, an industrial personal computer, and a server, and is selected according to the difference of system complexity.
In a specific embodiment, the intelligent processing module 4 includes a storage unit and an intelligent processor 47, the storage unit is connected to the intelligent processor 47, the intelligent processor 47 is further connected to the coordination processor 1 in a communication manner, the intelligent processor 47 is configured to perform data interaction with the coordination processor 1 and analyze and process the received data, and the storage unit is configured to store the data received and processed by the intelligent processor 47 in real time.
In a specific embodiment, the storage unit includes a self-learning model storage unit 41, an empirical knowledge data storage unit 42, a fact data storage unit 43, a spare part data storage unit 44, a unit structure data storage unit 45 and a personal ability evaluation storage unit 46, and the self-learning model storage unit 41, the empirical knowledge data storage unit 42, the fact data storage unit 43, the spare part data storage unit 44, the unit structure data storage unit 45 and the personal ability evaluation storage unit 46 are respectively electrically connected with an intelligent processor 47;
the self-learning model storage unit 41 is used for storing and updating the self-learning processing model of the related operation and maintenance affairs of the unit, the empirical knowledge data storage unit 42 is used for storing knowledge data learned by the self-learning model, the fact data storage unit 43 is used for storing expert knowledge data extracted by the expert client 5 and animation demonstration data of related troubleshooting and troubleshooting generated by processing maintenance data extracted by a field maintenance working end through the intelligent processor 47, the spare part data storage unit 44 is used for storing the number of spare parts, spare part attribute information and a three-dimensional model, the unit structure data storage unit 45 is used for storing the unit structure, the part connection condition and the three-dimensional model of the unit, and the personal ability evaluation storage unit 46 is used for storing evaluation data of the system on the ability of maintenance personnel.
In this embodiment, each of the storage units is a hardware medium having storage and fast read/write functions, so that a large-capacity data storage requirement can be met.
As shown in fig. 2, firstly, the second human-computer interaction unit 54 of the expert client 5 inputs the operation and maintenance affair self-learning processing model related to the unit into the self-learning model storage unit 41 through the coordination processor 1 and the intelligent processor 47, the animation demonstration of the fault processing step is input into the fact data storage unit 43, the spare part attribute information and the three-dimensional model thereof are stored into the spare part information storage unit 44, the unit structure, the component connection condition and the three-dimensional model are stored into the unit structure data storage unit 45, and the parameter initial setting is performed on the self-learning model storage unit 41, the fact data storage unit 43, the spare part information storage unit 44 and the unit structure data storage unit 45.
As shown in fig. 3, the intelligent processor 47 receives the operating condition history Data collected from the SCADA system interface 21(Supervisory Control And Data Acquisition, i.e., Data Acquisition And monitoring Control system) And the operation log interface 22 in the operating condition Data interface 2 through the coordination processor 1, performs deep mining And fusion on the history Data And the structure knowledge Data stored in the self-learning model storage unit 41 And the unit structure knowledge Data stored in the unit structure Data storage unit 45, generates the experience knowledge, stores the experience knowledge Data in the experience knowledge Data storage unit 42, And performs initial parameter setting on the experience knowledge Data storage unit 42.
As shown in fig. 4, when a fault occurs, the first human-machine interaction unit 34 in the field maintenance work terminal 3 receives the fault code received by the SCADA system interface 21 in the condition data interface 2 and the knowledge data in the experimental knowledge data storage unit 42 in the intelligent processing module 4 through the coordination processor 1, and recommends the most likely damaged component corresponding to the fault code for the worker, so as to help the maintenance worker to confirm the fault point most quickly.
As shown in fig. 5, during the fault handling process, animation demonstration data corresponding to the fault in the fact data storage unit 43 is received through the coordination processor 1 and the intelligent processor 47, and in combination with video data acquired and processed by the maintenance data acquisition unit 31 and the first data identification unit 32, the animation demonstration data and real video data are fused through the first virtual-real fusion unit 33 and transmitted to the first human-computer interaction unit 34, so as to provide real-time guidance for a serviceman, and then the handling record is stored in the personal ability assessment storage unit 46 as experience of the serviceman after being processed by the coordination processor 1 and the intelligent processor 47.
As shown in fig. 6, when the processed fault exceeds the original knowledge data of the system, the expert client 5 is used for help, the expert performs virtual maintenance demonstration on the virtual unit in the unit structure data storage unit 45 through the fault code and real-time real video data fed back by the field maintenance work terminal 3, the virtual maintenance demonstration is transmitted to the field maintenance work terminal 3 through the coordination processor 1, remote support is provided for the maintenance personnel, meanwhile, the virtual maintenance demonstration of the fault is generated into animation demonstration through the coordination processor 1 and the intelligent processor 47 and is stored in the fact data storage unit 43, and the processing record is processed by the coordination processor 1 and the intelligent processor 47 and then is stored in the personal capability evaluation storage unit 46 as the experience of the maintenance personnel.
As shown in fig. 7, the fault repair related knowledge data in the experience knowledge data storage unit 42, the fact data storage unit 43 and the unit structure storage unit 45 are automatically extracted by the intelligent processor 47, transmitted to the first human-machine interaction unit 34 in the field repair work terminal 3 via the coordination processor 1 for the maintenance personnel to perform virtual repair training, and the training records are stored as the experience of the maintenance personnel in the personal ability assessment storage unit 46 after being processed by the coordination processor 1 and the intelligent processor 47.
As shown in fig. 8, the intelligent auxiliary maintenance system for the wind generating set further comprises a cabinet above IP65 level; the coordination processor 1, the working condition data interface 2 and the intelligent processing module 5 are arranged in the cabinet, a memory and a communication line through hole are reserved on the cabinet, the communication interface and the power supply interface have a lightning protection function, the working condition data interface 2 is installed on the coordination processor 1 and is arranged in the cabinet together with the coordination processor 1, the cabinet is arranged in the main control room, a fixed terminal of the field maintenance working end 3 is arranged on a tower foundation and a cabin control cabinet or other positions where the fixed terminal is necessary to be arranged, the mobile terminal is carried by a maintenance worker, the wearable equipment is carried by the maintenance worker, the fixed terminal of the expert client 5 is arranged on the tower foundation control cabinet or the location of an expert office, the mobile terminal is carried by an expert, and the wearable equipment is carried by the expert.
On the other hand, referring to fig. 9, the invention further provides an intelligent auxiliary maintenance method for a wind generating set, which comprises the following steps:
s1: the method comprises the steps of storing an operation and maintenance affair self-learning processing model related to the unit, animation demonstration data of fault processing steps, spare part attribute information and three-dimensional models thereof, unit structure and component connection conditions and three-dimensional models thereof in a classified manner in advance;
s2: collecting working condition historical data of the wind generating set, carrying out deep mining and fusion on the working condition historical data and the structure knowledge data according to a pre-stored self-learning model of related operation and maintenance affairs of the wind generating set and the structure knowledge data of the wind generating set to generate experience knowledge, and storing the experience data in real time;
s3: receiving a fault code when a fault occurs, positioning a maximum-possibility damaged component according to prestored empirical data, recommending the maximum-possibility damaged component to a field maintenance working end, and determining a target fault point by the field maintenance working end according to the received maximum-possibility damaged component;
s4: acquiring video data of a target fault point in real time, calling prestored animation demonstration data of the target fault point, fusing the animation demonstration data with the video data of the target fault point acquired in real time, and displaying the video data to field maintenance personnel;
s5: if the component can not be located to the maximum possibility to be damaged according to the prestored experience data, automatically connecting the field maintenance working end to the expert client, transmitting the fault code and the maintenance field video to the expert client in real time, and determining a fault point and providing a maintenance scheme by the real-time butt joint of the expert client and the field maintenance working end;
s6: and storing the final maintenance scheme in real time, and updating experience data.
In the embodiment, in order to further improve the accuracy of target tracking, a method based on a dual-channel pseudo-twin network is provided. Semantic feature G of each frame of video extracted through CNNW(X), Conv L STM (Convolitional L STM) calculates image semantic information G by combining the current frame and historical information in the videoV(X), and then performing data fusion on the obtained features through stacking to obtain GWV(X), finally, judging whether the observed X is the target or not by calculating the similarity of the two vectorsAnd marking Z.
Referring to fig. 10, the specific fault location process is implemented by the following steps:
(1) firstly, reasoning out related components according to fault codes reported by an SCADA background, and then extracting related component photos Z;
(2) a fan operation and maintenance worker utilizes tools such as Google glasses to acquire the electric appliance cabinet where the part is located in real time;
(3) when the part appears in the collected video data for the first time, the frame is defined as X1, and the semantic features of the frame are extracted through CNN and Conv L STM, wherein GW(X) and GW(Z) share the same set of parameters, with independent parameters;
(4) the second frame and the later frames, the features extracted by the Conv L STM are fused with the historical information, so the extracted features are more comprehensive and detailed;
(5) data fusion is carried out on each characteristic in a stacking mode, and G is combined with the characteristicW(X) performing a comparison, wherein a loss function of the comparison is as follows:
wherein the content of the first and second substances,
the value of Y is 1 or 0, if the model prediction inputs are similar, then the value of Y is 0, otherwise Y is 1; max () represents 0 and m-DwA function of greater value in between, DwIndicating the residual, E in fig. 10 is the residual.
m is a margin value (margin value) greater than 0. It can be understood as a threshold, only the case that the difference of the Euclidean distances of the two sample features is between 0 and margin is considered in the calculation process, when the distance exceeds margin, the loss is regarded as 0 (i.e. when the two sample features are dissimilar, the larger the Euclidean distance is, the smaller the loss is, and for the case that the two samples are similar, the farther the distance is, the larger the loss is)
By the aid of the method, previously accumulated experience data can be applied to fault handling work of the on-site wind generating set, fault points can be located more quickly and accurately by means of expert remote guidance, maintenance efficiency of the wind generating set is greatly improved, and meanwhile maintenance personnel can improve self ability and accumulate experiences through continuously updated maintenance data.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The utility model provides a wind generating set intelligence auxiliary maintenance system which characterized in that includes:
the working condition data interface is in communication connection with an external fan working condition data source and is used for reading external monitoring data;
the field maintenance working end is used for acquiring field maintenance information and performing virtual-real fusion processing;
the expert client is used for acquiring and inputting expert knowledge data and providing a self-learning processing model of related operation and maintenance affairs of the unit, spare part attribute information and unit mechanism model data;
the coordination processor is in communication connection with the working condition data interface, the field maintenance working end and the expert client, and is used for analyzing, processing and forwarding the received data; and
and the coordination processor is also in communication connection with the intelligent processing module, and the intelligent processing module is used for storing and managing system related data and executing an intelligent computing function.
2. The intelligent auxiliary maintenance system of the wind generating set according to claim 1, wherein the working condition data interface comprises a unit SCADA system interface and a unit operation log interface.
3. The intelligent auxiliary maintenance system of the wind generating set according to claim 1, wherein the field maintenance work end comprises a maintenance data acquisition unit, a first data identification unit, a first virtual-real fusion unit and a first human-computer interaction unit, the maintenance data acquisition unit is connected with the first human-computer interaction unit sequentially through the first data identification unit and the first virtual-real fusion unit, and the first data identification unit, the first virtual-real fusion unit and the first human-computer interaction unit are respectively connected with the coordination processor;
the maintenance data acquisition unit is used for acquiring maintenance data of a user in the maintenance process of the wind generating set, the first data identification unit is used for extracting key information in the maintenance data acquired by the maintenance data acquisition unit, the first virtual-real fusion unit is used for fusing real graphs in the key information with virtual graphs stored in advance, and the first human-computer interaction unit is used for displaying the fused data.
4. The intelligent auxiliary maintenance system of the wind generating set according to claim 1, wherein the expert client comprises an expert data acquisition unit, a second data identification unit, a second virtual-real fusion unit and a second human-computer interaction unit, the expert data acquisition unit is connected with the second human-computer interaction unit sequentially through the second data identification unit and the second virtual-real fusion unit, and the second data identification unit, the second virtual-real fusion unit and the second human-computer interaction unit are respectively connected with the coordination processor;
the expert data acquisition unit is used for acquiring input expert knowledge data, the second data identification unit is used for extracting key information in the expert knowledge data acquired by the expert data acquisition unit, the second virtual-real fusion unit is used for fusing real graphs in the key information with virtual graphs stored in the key information, and the second human-computer interaction unit is used for displaying the fused data.
5. The intelligent auxiliary maintenance system of the wind generating set according to claim 1, wherein the intelligent processing module comprises a storage unit and an intelligent processor, the storage unit is connected with the intelligent processor, the intelligent processor is further in communication connection with the coordination processor, the intelligent processor is used for performing data interaction with the coordination processor and analyzing and processing the received data, and the storage unit is used for storing the data received and processed by the intelligent processor in real time.
6. The intelligent auxiliary maintenance system of the wind generating set according to claim 5, wherein the storage unit comprises a self-learning model storage unit, an empirical knowledge data storage unit, a fact data storage unit, a spare part data storage unit, a unit structure data storage unit and a personal ability evaluation storage unit, and the self-learning model storage unit, the empirical knowledge data storage unit, the fact data storage unit, the spare part data storage unit, the unit structure data storage unit and the personal ability evaluation storage unit are respectively electrically connected with the intelligent processor;
the self-learning model storage unit is used for storing and updating a unit related operation and maintenance affair self-learning processing model, the empirical knowledge data storage unit is used for storing knowledge data learned by the self-learning model, the fact data storage unit is used for storing expert knowledge data extracted by the expert client and animation demonstration data of related troubleshooting and troubleshooting generated by processing maintenance data extracted by the field maintenance working end through the intelligent processor, the spare part data storage unit is used for storing the number of spare parts, spare part attribute information and a three-dimensional model, the unit structure data storage unit is used for storing a unit structure, a part connection condition and the three-dimensional model of the unit, and the personal ability evaluation storage unit is used for storing evaluation data of a system on the ability of maintenance personnel.
7. An intelligent auxiliary maintenance method for a wind generating set is characterized by comprising the following steps:
s1: the method comprises the steps of storing an operation and maintenance affair self-learning processing model related to the unit, animation demonstration data of fault processing steps, spare part attribute information and three-dimensional models thereof, unit structure and component connection conditions and three-dimensional models thereof in a classified manner in advance;
s2: collecting working condition historical data of the wind generating set, carrying out deep mining and fusion on the working condition historical data and the structure knowledge data according to a pre-stored self-learning model of related operation and maintenance affairs of the wind generating set and the structure knowledge data of the wind generating set to generate experience knowledge, and storing the experience data in real time;
s3: receiving a fault code when a fault occurs, positioning a maximum-possibility damaged component according to prestored empirical data, recommending the maximum-possibility damaged component to a field maintenance working end, and determining a target fault point by the field maintenance working end according to the received maximum-possibility damaged component;
s4: acquiring video data of a target fault point in real time, calling prestored animation demonstration data of the target fault point, fusing the animation demonstration data with the video data of the target fault point acquired in real time, and displaying the video data to field maintenance personnel;
s5: if the component can not be located to the maximum possibility to be damaged according to the prestored experience data, automatically connecting the field maintenance working end to the expert client, transmitting the fault code and the maintenance field video to the expert client in real time, and determining a fault point and providing a maintenance scheme by the real-time butt joint of the expert client and the field maintenance working end;
s6: and storing the final maintenance scheme in real time, and updating experience data.
8. The intelligent auxiliary maintenance method for the wind generating set according to claim 7, wherein the step S3 specifically comprises:
s301: determining the most probable damaged component according to the received fault code and by combining empirical data, and acquiring a picture of the most probable damaged component;
s302: the field maintenance working end collects the video data of the electric appliance cabinet where the most-possibly-damaged part is located in real time;
s303: respectively acquiring current frame data of the video data when suspected damaged parts appear each time, and extracting semantic features of each current frame data;
s304: and performing data fusion on semantic features of a plurality of current frame data in a stacking mode, and judging whether a suspected damaged part appearing in the video data is the most possibly damaged part or not according to the similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010290769.7A CN111472946A (en) | 2020-04-14 | 2020-04-14 | Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010290769.7A CN111472946A (en) | 2020-04-14 | 2020-04-14 | Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111472946A true CN111472946A (en) | 2020-07-31 |
Family
ID=71752507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010290769.7A Pending CN111472946A (en) | 2020-04-14 | 2020-04-14 | Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111472946A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112637A (en) * | 2021-03-30 | 2021-07-13 | 北京国电思达科技有限公司 | Handheld terminal and fan inspection online help seeking method and system |
| TWI735329B (en) * | 2020-09-03 | 2021-08-01 | 國立臺灣大學 | Decision making system for maintenance of offshore wind farm |
| CN114093145A (en) * | 2021-11-12 | 2022-02-25 | 许继集团有限公司 | Visual-auditory cooperative power equipment inspection system and method |
-
2020
- 2020-04-14 CN CN202010290769.7A patent/CN111472946A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI735329B (en) * | 2020-09-03 | 2021-08-01 | 國立臺灣大學 | Decision making system for maintenance of offshore wind farm |
| CN113112637A (en) * | 2021-03-30 | 2021-07-13 | 北京国电思达科技有限公司 | Handheld terminal and fan inspection online help seeking method and system |
| CN114093145A (en) * | 2021-11-12 | 2022-02-25 | 许继集团有限公司 | Visual-auditory cooperative power equipment inspection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111472946A (en) | Intelligent auxiliary maintenance system and auxiliary maintenance method for wind generating set | |
| CN110728443A (en) | Motor full life cycle management and control system | |
| CN104680260A (en) | Method and system for establishing power grid visualized perceptual model | |
| CN112769908A (en) | Cooperative control method and device and electronic equipment | |
| CN110689148A (en) | Metering equipment fault detection method based on AR technology | |
| CN111062504A (en) | AR technology-based intelligent power distribution station operation and maintenance system and method | |
| CN113472079B (en) | Power distribution station operation and maintenance monitoring cloud robot system, background processing and operation task method | |
| EP4134877A1 (en) | Training method and apparatus for fault recognition model, fault recognition method and apparatus, and electronic device | |
| CN111652406A (en) | Method and system for predicting running state of power grid equipment under cloud-edge cooperation | |
| CN112507945B (en) | Method and device for managing and controlling behavior of operator, electronic equipment and storage medium | |
| CN115309913A (en) | Deep learning-based financial data risk identification method and system | |
| CN114996936A (en) | Equipment operation and maintenance method, equipment operation and maintenance device, equipment operation and maintenance equipment and storage medium | |
| CN112419683A (en) | Machine room equipment monitoring method and system | |
| CN115618303B (en) | Automatic dispatch monitoring and fault locating system based on information fusion technology | |
| CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
| CN114237135A (en) | Information communication machine room 3D visualization method and system based on digital twin technology | |
| CN113541320A (en) | Power grid power failure and restoration visual monitoring method and system and storage medium | |
| CN113223121A (en) | Video generation method and device, electronic equipment and storage medium | |
| CN115186842B (en) | Management cloud platform | |
| CN113129160A (en) | Electric power communication network inspection method based on equipment state perception and intellectualization | |
| CN117692610B (en) | AR workshop inspection system | |
| CN116956174A (en) | Classification model for cold head state classification detection and life prediction and generation method of prediction model | |
| CN109257206A (en) | A kind of method of data inputting and evaluation diagnostic message feedback | |
| CN117539674B (en) | Exception handling method, device, equipment and storage medium | |
| CN114004548B (en) | Production line management and control method, device and medium based on edge calculation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200731 |
|
| RJ01 | Rejection of invention patent application after publication |