Wind turbine generator monitoring analysis platform and method based on multi-source heterogeneous data

Abstract

The invention provides a wind turbine generator monitoring analysis platform and method based on multi-source heterogeneous data, and belongs to the technical field of multi-source heterogeneous data processing, and the platform comprises a data access layer which is used for obtaining original monitoring data and a wind power plant management system semaphore; the data processing service layer is used for optimizing the original monitoring data; the data scheduling layer is used for performing scheduling execution on a processing process of global shared information of each control strategy algorithm model by adopting a heterogeneous data cross process technology, and performing global mapping processing on the optimized monitoring data to obtain a mapping relationship among the data of each model; generating a monitoring data set according to each mapping relation and the data summarization process; and the application layer is used for executing business logic of monitoring and analysis of the wind turbine generator based on the monitoring data set and each control strategy algorithm model so as to monitor and analyze the running state trend of the wind turbine generator. According to the scheme, the wind turbine generator monitoring analysis efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of multi-source heterogeneous data processing, and in particular to a wind turbine monitoring and analysis platform and method based on multi-source heterogeneous data. Background Art

[0002] The new energy system accumulates a huge amount of data during operation. The data is scattered in different systems of new energy stations, power generation enterprises and power grids, which easily leads to data island effect. At the same time, data exists in various forms, both structured and unstructured, showing the characteristics of "multi-source heterogeneity". Massive data contains huge application value, and it is urgent to realize data collection and centralized processing, and realize the integration and interconnection of multi-source heterogeneous data.

[0003] At present, the main problems in wind farms when processing multi-source heterogeneous data are: lack of timely and effective resource scheduling mechanism, difficulty in effectively sharing computing resources between various models, resulting in low efficiency of wind turbine monitoring and analysis. Therefore, how to improve the efficiency of wind turbine monitoring and analysis has become a problem to be solved. Summary of the invention

[0004] The purpose of this application is to provide a wind turbine monitoring and analysis platform and method based on multi-source heterogeneous data, which can solve the problem of low efficiency of wind turbine monitoring and analysis in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a wind turbine monitoring and analysis platform based on multi-source heterogeneous data, the platform comprising: The data access layer is used to obtain the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; The data processing service layer is used to optimize the original monitoring data, obtain the optimized monitoring data, and standardize the data collection interface; The data scheduling layer is used to schedule and execute the processing process of global shared information of each control strategy algorithm model by adopting heterogeneous data cross-process technology, and to perform global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and to generate the monitoring data set according to each mapping relationship and data aggregation process; The application layer is used to execute the business logic of wind turbine monitoring and analysis based on the monitoring data set and various control strategy algorithm models, so as to monitor and analyze the operating status trend of the wind turbine.

[0006] In a possible implementation of the first aspect, the platform further includes: The data storage layer is used to store historical data, real-time data, and analytical data; historical data refers to the original monitoring data collected before the current time, real-time data refers to the original monitoring data collected in real time, and analytical data refers to the original monitoring data used for model analysis; The data forwarding layer is used to send the original monitoring data to the data processing service layer in a preset communication protocol format, and forward the optimized monitoring data to the application layer.

[0007] In a possible implementation manner of the first aspect, the data forwarding layer includes at least one communication module, and each communication module is used to forward the optimized monitoring data to the application layer.

[0008] In a possible implementation of the first aspect, the data access layer includes: a data query module, a Beckhoff control module, a Bachmann control module and a serial communication module; the data scheduling layer is also used to perform data audits on the optimized monitoring data and build a full life cycle management system for the original monitoring data; the application layer includes: a network terminal, a client terminal, a data acquisition and monitoring system, an energy management module and a centralized control module.

[0009] In a possible implementation of the first aspect, the data processing service layer includes: an interface standardization module, a data cleaning module, a data standardization module and a data preprocessing module; the interface standardization module is used to standardize the data acquisition interface; the data cleaning module is used to clean the original monitoring data; the data standardization module is used to standardize the original monitoring data; the data preprocessing module is used to preprocess the original monitoring data.

[0010] In a possible implementation of the first aspect, the control strategy algorithm model includes: a primary frequency modulation algorithm model, a fan fault warning model, a predictive analysis model, a performance optimization model and a control algorithm model; the data processing service layer is also used to integrate the model configuration elements, and upload the control strategy algorithm, the primary frequency modulation algorithm model, the fan fault warning model, the predictive analysis model, the performance optimization model and the control algorithm model to the data scheduling layer in an encrypted and packaged file format.

[0011] In a possible implementation of the first aspect, the application layer is also used to construct the optimized monitoring data into two types of data streams, classify and analyze and judge each model based on the two types of data streams, analyze and judge each model based on the system signal quantity, and feed back the two types of data streams to the data scheduling layer for processing by the data scheduling layer.

[0012] In a possible implementation manner of the first aspect, the platform also includes a data source device cluster; the data source device cluster is used to collect original monitoring data and send the original monitoring data to the data access layer in a preset communication protocol format.

[0013] In a possible implementation of the first aspect, the original monitoring data includes: blade monitoring data, vibration monitoring data, frequency change monitoring data, single machine information data, wind turbine data, equipment operation data and environmental monitoring data; the data source equipment cluster includes: switches, servers, controllers, sensors, equipment managers, environmental monitors and wind farm operation and maintenance monitoring databases; Sensors are used to collect blade monitoring data, vibration monitoring data, and frequency change monitoring data; controllers are used to collect single-machine information data and wind turbine data; equipment managers are used to collect equipment operation data; environmental monitors are used to collect environmental monitoring data; and wind farm operation and maintenance monitoring databases are used to store raw monitoring data.

[0014] In a possible implementation of the first aspect, the wind farm management system includes: a SCADA monitoring system, a wind power prediction system, an AGC / AVC energy management system, an electric energy metering system and a production management system; the collection types of system signal quantities include: electrical analog quantities, non-electrical analog quantities, interrupt switch quantities and non-interrupt switch quantities.

[0015] In a possible implementation of the first aspect, electrical analog quantities include: voltage, power and current; non-electrical analog quantities include: wind speed, displacement, temperature, vibration frequency, rotation speed, wind direction and radiation; interrupt switch quantities include: accident signals, action signals of circuit breakers and relay protection; non-interrupt switch quantities include: various fault signals, position signals of circuit breakers and disconnectors, and status signals of wind turbines.

[0016] In a second aspect, an embodiment of the present application provides a wind turbine monitoring and analysis method based on multi-source heterogeneous data, which is implemented based on a wind turbine monitoring and analysis platform based on multi-source heterogeneous data in any one of the first aspects, and the method includes: Based on the data access layer, the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system are obtained; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; Based on the data processing service layer, the original monitoring data is optimized to obtain the optimized monitoring data, and the data collection interface is standardized; Based on the data scheduling layer, the heterogeneous data cross-process technology is used to schedule and execute the processing process of the global shared information of each control strategy algorithm model, and the optimized monitoring data is globally mapped to obtain the mapping relationship between the data of each model, and the monitoring data set is generated according to each mapping relationship and data aggregation process; Based on the application layer, the business logic of wind turbine monitoring and analysis is executed according to the monitoring data set and various control strategy algorithm models to monitor and analyze the operating status trend of the wind turbine.

[0017] In a possible implementation of the second aspect, optimizing the original monitoring data based on the data processing service layer to obtain the optimized monitoring data, and standardizing the data acquisition interface, including: Based on the data processing service layer, the original monitoring data is cleaned, standardized and pre-processed, and the data acquisition interface is standardized for communication, unified data upload rules and standardized naming of measurement points.

[0018] In a possible implementation manner of the second aspect, before optimizing the original monitoring data based on the data processing service layer, the method further includes: Historical data is selected from the original monitoring data at a preset time or a preset time period, and real-time data is extracted from the original monitoring data at a preset communication time; wherein the historical data is the original monitoring data collected before the current time, and the real-time data is the original monitoring data collected in real time.

[0019] In a possible implementation of the second aspect, the control strategy algorithm model includes: a primary frequency modulation algorithm model, a fan fault warning model, a prediction analysis model, a performance optimization model, and a control algorithm model; the method also includes: Based on the integrated model configuration components of the data processing service layer, the control strategy algorithm, primary frequency modulation algorithm model, fan fault warning model, prediction analysis model, performance optimization model and control algorithm model are uploaded to the data scheduling layer in an encrypted and packaged file format.

[0020] In a possible implementation manner of the second aspect, the global shared information includes a shared data packet; and based on the data scheduling layer, a heterogeneous data cross-process technology is adopted to schedule and execute the processing process of the global shared information of each control strategy algorithm model, including: Sort multiple processes that process shared data packets by preset execution time, put the process with the shortest preset execution time in the ready queue, and initialize shared memory and system semaphores; if the CPU is idle and there is a process in the ready queue, execute the process with the shortest preset execution time until it is completed; if two or more processes have the same execution time, execute them in the order of their arrival; if a new process arrives and its execution time is shorter than that of the current execution process, schedule the new process after the current execution process is completed; When a process is completed, check whether a new process has arrived. If a new process has arrived, reorder the ready queue according to the preset execution time; repeat the steps of sorting by the preset execution time and the steps after it until all processes are scheduled and executed and the shared memory is cleaned up.

[0021] In a possible implementation of the second aspect, a global mapping process is performed on the optimized monitoring data based on the data scheduling layer to obtain a mapping relationship between the data of each model, and a monitoring data set is generated according to each mapping relationship and a data aggregation process, including: Based on the data scheduling layer, the data of each control strategy algorithm model is regularly written into the corresponding shared memory, and a mapping relationship between the data of each control strategy algorithm model is established; according to each mapping relationship, based on the data aggregation process, data is regularly read from the shared memory of each control strategy algorithm model, and the read data is merged into the shared memory public space to generate a monitoring data set for multi-model intelligent operation and maintenance.

[0022] In a possible implementation manner of the second aspect, the method further includes: Based on the data scheduling layer, data audit is performed on the optimized monitoring data, and a full life cycle management system for the original monitoring data is established.

[0023] In a possible implementation of the second aspect, the optimized monitoring data is constructed into two types of data streams based on the application layer, and each model is classified and analyzed and judged based on the two types of data streams, and each model is analyzed and judged based on the system signal quantity, and the two types of data streams are fed back to the data scheduling layer for processing by the data scheduling layer.

[0024] In a possible implementation manner of the second aspect, based on the application layer, the optimized monitoring data is constructed into two types of data streams, the two types of data streams are fed back to the data scheduling layer, and are used for processing by the data scheduling layer, including: The optimized monitoring data are constructed into historical data streams and real-time data streams, which are fed back to the data scheduling layer and used for judging global shared information and generating monitoring data sets. In the shared information mechanism of the data scheduling layer, historical data streams and real-time data streams are used as the common data sources of various control strategy algorithm models.

[0025] In a second aspect, an embodiment of the present application provides a wind turbine monitoring and analysis device based on multi-source heterogeneous data, which is implemented based on the wind turbine monitoring and analysis platform based on multi-source heterogeneous data in any one of the first aspects, and the device includes: An acquisition unit is used to acquire the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system based on the data access layer; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; The optimization processing unit is used to optimize the original monitoring data based on the data processing service layer to obtain the optimized monitoring data and standardize the data collection interface; The data set generation unit is used to schedule and execute the processing process of global shared information of each control strategy algorithm model based on the heterogeneous data cross-process technology adopted by the data scheduling layer, and to perform global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and to generate the monitoring data set according to each mapping relationship and the data aggregation process; The monitoring and analysis unit is used to execute the business logic of wind turbine monitoring and analysis based on the application layer according to the monitoring data set and various control strategy algorithm models, so as to monitor and analyze the operating status trend of the wind turbine.

[0026] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for monitoring and analyzing a wind turbine based on multi-source heterogeneous data in any one of the second aspects described above is implemented.

[0027] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements any one of the wind turbine monitoring and analysis methods based on multi-source heterogeneous data in the second aspect mentioned above.

[0028] In a sixth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device executes any one of the wind turbine monitoring and analysis methods based on multi-source heterogeneous data in the second aspect.

[0029] The wind turbine monitoring and analysis platform based on multi-source heterogeneous data of the present application includes: data access layer, data processing service layer, data scheduling layer and application layer. The wind turbine monitoring and analysis method based on multi-source heterogeneous data of the present application is implemented based on the platform. First, the original monitoring data and wind farm management system signal quantity are obtained based on the data access layer. Secondly, the original monitoring data is optimized and processed based on the data processing service layer. Then, the heterogeneous data cross-process technology is used based on the data scheduling layer to schedule and execute the processing process of the global shared information of each control strategy algorithm model, and the optimized monitoring data is globally mapped to generate a monitoring data set. Finally, the operating status trend of the wind turbine is monitored and analyzed based on the monitoring data set and each model based on the application layer.

[0030] The heterogeneous data cross-process technology adopted in the present application can effectively process multi-source heterogeneous data in wind farms, realize the sharing of information resources generated in real time among multiple models, thereby improving the efficiency of wind turbine monitoring and analysis, and has strong ease of use and practicality.

[0031] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0033] Figure 1 It is a schematic diagram of the overall architecture of a wind turbine monitoring and analysis platform based on multi-source heterogeneous data provided by an embodiment of the present application; Figure 2 It is a schematic diagram of the specific architecture of a wind turbine monitoring and analysis platform based on multi-source heterogeneous data provided in an embodiment of the present application; Figure 3 is a schematic diagram of a wind farm operation and maintenance monitoring database provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the steps of a wind turbine monitoring and analysis method based on multi-source heterogeneous data provided in an embodiment of the present application; Figure 5 It is a schematic diagram of the overall flow of data processing provided by the embodiment of the present application; Figure 6 It is a structural schematic diagram of a wind turbine monitoring and analysis device based on multi-source heterogeneous data provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0035] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or photovoltaic components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, photovoltaic components and / or combinations thereof.

[0036] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0037] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0038] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0039] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0040] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0041] In recent years, the development of technologies such as big data analysis, cloud computing, and artificial intelligence, and the widespread application of smart operation and maintenance technologies in the field of new energy have brought new changes to wind farm operation and maintenance. New energy systems accumulate massive amounts of data during operation, and the data is dispersed in different systems of new energy stations, power generation companies, and power grids, which can easily cause data island effects. At the same time, data exists in multiple forms, both structured and unstructured, showing the characteristics of "multi-source heterogeneity". Massive data contains huge application value, and it is urgent to realize data collection and centralized processing, and realize the integration and interconnection of multi-source heterogeneous data.

[0042] However, due to the differences in wind turbines produced by different manufacturers, the data generated have different time scales, and the data collection frequency ranges from milliseconds to minutes, which brings challenges to the digital operation and maintenance of wind farms.

[0043] At present, the main problems faced by wind farms in processing multi-source heterogeneous data are: diversified data sources and diversified data collection methods. Most platforms are only applicable to wind turbines of specific brands or models, which makes it difficult to meet the needs of wind farms with multiple models. Single-machine controllers of different wind turbine models use different data collection methods, resulting in complex data formats and processing procedures. The information island phenomenon is serious, and data is stored in new energy stations, power generation companies, and power grid systems in a scattered manner, forming an obvious data island effect. There is a lack of timely and effective resource scheduling mechanisms, and it is difficult to effectively share computing resources between models, resulting in low efficiency in wind turbine monitoring and analysis, affecting the overall operation and maintenance efficiency of wind farms. The operation and maintenance costs increase. With the increase in monitoring and control targets, the requirements for data processing are getting higher and higher, and the corresponding operation and maintenance costs also increase accordingly.

[0044] In view of the above-mentioned defects, the embodiment of the present application provides a wind turbine monitoring and analysis platform and method based on multi-source heterogeneous data, and the platform includes: a data access layer, a data processing service layer, a data scheduling layer and an application layer. The method is implemented based on the platform, firstly, the original monitoring data and the signal quantity of the wind farm management system are obtained based on the data access layer, and then the original monitoring data is optimized and processed based on the data processing service layer, and then the heterogeneous data cross-process technology is used based on the data scheduling layer to schedule and execute the processing process of the global shared information of each control strategy algorithm model, and the optimized monitoring data is globally mapped to generate a monitoring data set, and finally the operating status trend of the wind turbine is monitored and analyzed based on the application layer according to the monitoring data set and each model.

[0045] The heterogeneous data cross-process technology adopted in the present application can effectively process multi-source heterogeneous data in wind farms, realize the sharing of information resources generated in real time among multiple models, thereby improving the efficiency of wind turbine monitoring and analysis, and has strong ease of use and practicality.

[0046] The specific process implemented by this application is introduced below through specific embodiments.

[0047] See also Figure 1 , Figure 1 Schematic diagram of the overall architecture of the wind turbine monitoring and analysis platform based on multi-source heterogeneous data provided by the embodiment of the present application. Figure 1 As shown, the platform includes: a data access layer, a data processing service layer, a data scheduling layer and a data dispatching layer.

[0048] In some embodiments, a large amount of monitoring data obtained by monitoring the wind farm is stored in the wind farm operation and maintenance monitoring database, as well as system signal quantities collected by the wind farm management system. The data access layer is used to obtain the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantities of the wind farm management system. Among them, the original monitoring data is multi-source heterogeneous data with different structures from multiple sources, and the wind farm management system is used to collect system signal quantities.

[0049] The data processing service layer is used to optimize the original monitoring data, obtain the optimized monitoring data, and standardize the data acquisition interface.

[0050] In some embodiments, in order to ensure the quality and consistency of data, the original monitoring data can be optimized. In order to effectively utilize multi-source heterogeneous data, the wind turbine monitoring and analysis platform performs optimization processing during data collection and management to achieve standardization of data collection interfaces.

[0051] The data scheduling layer is used to adopt heterogeneous data cross-process technology to schedule the execution of the processing process of global shared information of each control strategy algorithm model, and to perform global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and generate a monitoring data set based on each mapping relationship and data aggregation process.

[0052] In some embodiments, the wind turbine monitoring and analysis platform is equipped with multiple control strategy algorithm models and multiple processes for processing the global shared information of each control strategy algorithm model. The data scheduling layer uses heterogeneous data cross-process technology to schedule and execute these processes, thereby realizing the sharing of information resources generated in real time among multiple models.

[0053] The data scheduling layer can also perform global mapping processing on the optimized monitoring data to generate a monitoring data set. Through global mapping processing, the mapping relationship between the data of each control strategy algorithm model can be obtained, and the monitoring data set can be generated according to each mapping relationship and data aggregation process.

[0054] Among them, heterogeneous data cross-process technology (Shortest Job First, SJF) supports the use of global shared information in the multi-model platform (wind turbine monitoring and analysis platform). The global shared information in the platform can be called and modified by each control strategy algorithm model carried by the platform, and the content of the shared information can be modified by the platform to facilitate timely correction of necessary data. In addition, the producer-consumer model is used to ensure accurate and timely data updates, and the global shared information model is scheduled as a whole through the SJF cross-process technology.

[0055] The application layer is used to execute the business logic of wind turbine monitoring and analysis based on the monitoring data set and various control strategy algorithm models, so as to monitor and analyze the operating status trend of the wind turbine.

[0056] In some embodiments, each data in the monitoring data set can be input into each control strategy algorithm model through the application layer, and the operating status trend of the wind turbine can be monitored and analyzed through the control strategy algorithm model. The operating status trend of the wind turbine can be observed, and the wind turbine can be intelligently operated and maintained.

[0057] In some embodiments, data fusion collection services are used to achieve unified multi-protocol collection and standardized data forwarding. The platform is equipped with a variety of control strategy algorithm models to achieve real-time control (energy management, primary frequency modulation, etc.), status warning, intelligent monitoring and other business logic.

[0058] It should be noted that the mainstream architectures of general big data platforms are heterogeneous hybrid architecture and distributed integrated architecture. Heterogeneous hybrid architecture has simple functions, but has problems such as low flexibility in business support, difficulty in data migration, data redundancy, and difficulty in expansion, and does not focus on the value creation and application of historical accumulated data. Distributed integrated architecture can connect scattered resources into a whole, realize resource integration, sharing and organic collaboration, and establish a unified data system and service system.

[0059] New energy data presents massive multi-source heterogeneous characteristics with large data volume, wide sources and diverse data structures. In addition, based on different application scenarios, real-time interaction and integrated application of data and algorithms are required. Therefore, the new energy big data platform adopts a distributed integrated architecture.

[0060] See also Figure 2 , Figure 2 Schematic diagram of the specific architecture of the wind turbine monitoring and analysis platform based on multi-source heterogeneous data provided by the embodiment of the present application. Figure 2 As shown, the platform also includes: a data storage layer and a data forwarding layer.

[0061] The data storage layer is used to store historical data, real-time data, and analytical data. Historical data refers to the original monitoring data collected before the current time, real-time data refers to the original monitoring data collected in real time, and analytical data refers to the original monitoring data used for model analysis. The data forwarding layer is used to send the original monitoring data to the data processing service layer in a preset communication protocol format, and forward the optimized monitoring data to the application layer.

[0062] In some embodiments, as shown in Table 1, given the multi-source heterogeneity of data generated by multi-source data devices in major wind farms, the multi-source data can be converted into a unified communication protocol format for transmission according to the interface provided by the wind turbine or electrical manufacturer.

[0063] Table 1

[0064] Among them, Modbus is a serial communication protocol, TCP (Transmission Control Protocol) is a transmission control protocol, and the IEC104 standard is a standard for power system communication established by the International Electrotechnical Commission (IEC). m1com is a serial communication, and the serial communication port (cluster communication port) is the COM port, also known as the serial port. ADS (Automation Device Specification) communication is a special protocol defined by Beckhoff.

[0065] Please continue to see Figure 2 According to one embodiment of the present application, the data forwarding layer includes at least one communication module, and each communication module is used to forward the optimized monitoring data to the application layer.

[0066] In some embodiments, the data forwarding layer includes: one or more of an IEC104 communication module, a MODBUS module, an RS-485 module, and an RS-232 module. The data forwarding layer may also include other communication modules, which may be determined according to the specific circumstances in the actual application scenario, and are not listed here one by one.

[0067] Please continue to see Figure 2According to one embodiment of the present application, the data access layer includes: a data query module (phoenix), a Beckhoff control module (beckoff), a Bachmann control module (Bachmann) and a serial communication module (MODBUS). The application layer includes: a network terminal (web terminal), a client, a supervisory control and data acquisition system (SCADA), an energy management (energy) module and a centralized control module.

[0068] Among them, Phoenix is ​​a data query engine, and Beckoff is an open automation technology platform based on PC (Personal Computer) control technology. Bachmann (Bachmann Technology) provides a fieldbus module for the backplane, which can be used as a master module or a slave. The data access layer and application layer can also include other modules, which can be determined according to the specific circumstances in the actual application scenario, and are not listed here one by one.

[0069] In some embodiments, the data scheduling layer is also used to develop data audit functions, conduct data audits on optimized monitoring data, and improve the dimension and standardization of data through automatic identification of wind turbine operating status and quantitative evaluation of operating performance. The data scheduling layer is also used to build a full life cycle management system for original monitoring data, achieve end-to-end transparent management and control through functions such as lineage tracing, and improve data utilization efficiency through the integration and fusion of multi-source data.

[0070] Please continue to see Figure 2 According to one embodiment of the present application, the data processing service layer includes: an interface standardization module, a data cleaning module, a data standardization module and a data preprocessing module. The interface standardization module is used to standardize the data acquisition interface, the data cleaning module is used to clean the original monitoring data, the data standardization module is used to standardize the original monitoring data, and the data preprocessing module is used to preprocess the original monitoring data.

[0071] According to one implementation of the present application, the control strategy algorithm model includes: a primary frequency modulation algorithm model, a fan fault warning model, a prediction analysis model, a performance optimization model, and a control algorithm model. The data processing service layer is also used to integrate the model configuration components, and upload the control strategy algorithm, the primary frequency modulation algorithm model, the fan fault warning model, the prediction analysis model, the performance optimization model, and the control algorithm model to the data scheduling layer in an encrypted and packaged file format.

[0072] Among them, the control strategy algorithm model can also include other control algorithm models, and the file format of the uploaded model can also adopt other formats, which can be determined according to the specific circumstances in the actual application scenario, and are not listed here one by one.

[0073] According to an implementation of the present application, the application layer has two types of data interfaces, and the application layer is also used to receive the optimized monitoring data through the two types of data interfaces, construct the optimized monitoring data into two types of data streams, and classify and analyze and judge each control strategy algorithm model based on the two types of data streams. The application layer is also used to analyze and judge each control strategy algorithm model based on the system signal quantity, and feed back the two types of data streams to the data scheduling layer, and use the two types of data streams for processing in the data scheduling layer.

[0074] Please continue to see Figure 2 According to an implementation of the present application, the platform further includes a data source device cluster. The data source device cluster is used to collect original monitoring data and send the original monitoring data to the data access layer in a preset communication protocol format.

[0075] See also Figure 3 , Figure 3 Schematic diagram of a wind farm operation and maintenance monitoring database provided in an embodiment of the present application. Figure 3 As shown, the original monitoring data includes: blade monitoring data, vibration monitoring data, frequency change monitoring data, single machine information data, wind turbine data, equipment operation data and environmental monitoring data.

[0076] Please continue to see Figure 2 The data source equipment cluster includes: switches, servers, controllers, sensors, device managers, environmental monitors, and wind farm operation and maintenance monitoring databases. Among them, sensors are used to collect blade monitoring data, vibration monitoring data, and frequency change monitoring data, and controllers are used to collect single-machine information data and wind turbine data. The controller can be a PLC (Programmable Logic Controller). The device manager is used to collect equipment operation data, the environmental monitor is used to collect environmental monitoring data, and the wind farm operation and maintenance monitoring database is used to store original monitoring data.

[0077] Please continue to see Figure 3According to one embodiment of the present application, the wind farm management system includes: a SCADA monitoring system, a wind power prediction system, an AGC / AVC (AGC: Automatic Gain Control, automatic gain control; AVC: Automatic Voltage Control, automatic voltage control) energy management system, an electric energy metering system and a production management system. The acquisition types of system signal quantities include: electrical analog quantity, non-electrical analog quantity, interruption switch quantity and non-interruption switch quantity.

[0078] According to one embodiment of the present application, electrical analog quantities include: voltage, power and current; non-electrical analog quantities include: wind speed, displacement, temperature, vibration frequency, rotation speed, wind direction and radiation. Interrupt switch quantities include: accident signals, action signals of circuit breakers and relay protection. Non-interrupt switch quantities include: various fault signals, position signals of circuit breakers and disconnectors, and status signals of wind turbines.

[0079] See also Figure 4 , Figure 4 Schematic diagram of the steps of the wind turbine monitoring and analysis method based on multi-source heterogeneous data provided by the embodiment of the present application. The method is implemented based on a wind turbine monitoring and analysis platform based on multi-source heterogeneous data, such as Figure 4 As shown, the method may include the following steps: S401, based on the data access layer, the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system are obtained; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity.

[0080] It should be noted that the specific implementation principle of this embodiment has been described in the above embodiments and will not be repeated here.

[0081] S402, optimizing the original monitoring data based on the data processing service layer to obtain optimized monitoring data, and standardizing the data collection interface.

[0082] According to an implementation of the present application, optimizing the original monitoring data based on the data processing service layer to obtain the optimized monitoring data and standardizing the data acquisition interface may include the following steps: Based on the data processing service layer, the original monitoring data is cleaned, standardized and pre-processed, and the data acquisition interface is standardized for communication, unified data upload rules and standardized naming of measurement points.

[0083] It should be noted that the specific implementation principle of this embodiment has been described in the above embodiments and will not be repeated here.

[0084] According to an implementation manner of the present application, before optimizing the original monitoring data based on the data processing service layer, the method may further include the following steps: Historical data is selected from the original monitoring data at a preset time or a preset time period, and real-time data is extracted from the original monitoring data at a preset communication time; wherein the historical data is the original monitoring data collected before the current time, and the real-time data is the original monitoring data collected in real time.

[0085] Among them, the preset time or preset time period can be determined according to the specific situation in the actual application scenario, and is not specifically limited here.

[0086] In some embodiments, the platform supports accurate time selection of historical data and time length selection of historical data. Real-time data extraction of the multi-model platform includes data acquisition and real-time control, which can achieve stable 50ms high-speed communication. The multi-model platform supports free dynamic point selection in data selection. According to the data analysis points required by the model, any available data point in all the quantity points can be freely selected, and the data analysis stream is automatically generated and sent to the corresponding model carried by the multi-model platform for analysis and application.

[0087] See also Figure 5 , Figure 5 This is a schematic diagram of the overall process of data processing provided by the embodiment of the present application. Figure 5 As shown, the solid arrows indicate the program flow direction, and the dotted arrows indicate the data flow direction. The overall process of data processing may include the following steps: Set the configuration file related data, start the acquisition program, and load the node configuration file. The configuration file is divided into two types: controller and pc. The controller controls the data acquisition thread through the plc, and each site has a data acquisition thread. The plc controls the phoenix, beckoff and Bachmann access data, and the model-carrying platform transmits data through IEC104 and MODBUS.

[0088] After accessing the data, the data is first cached, and then historical data is stored by data storage (csv files are stored every minute, and folders are compressed every hour), and real-time data is stored (data is collected in 50ms or 1s according to the frequency parameters configured in node.xml). Among them, csv files: comma-separated values ​​(CSV, sometimes also called character-separated values, because the separator character can also be other than a comma), which stores tabular data (numbers and text) in plain text. node.xml: eXtensible Markup Language, XML, extensible markup language (a subset of standard generalized markup language) is a simple data storage language.

[0089] The historical data is transmitted to the PC (data receiver) through files, and the real-time data is transmitted to the PC through the IEC104 module and the Modbus module using the UDP protocol (User Datagram Protocol). Among them, the functions of the IEC104 module and the Modbus module are the same, and the Modbus module is an externally developed module. The PC is configured with: sacda1 module, sacda2 module, data carrying platform and third-party applications.

[0090] According to an implementation of the present application, the control strategy algorithm model includes: a primary frequency modulation algorithm model, a fan fault warning model, a prediction analysis model, a performance optimization model and a control algorithm model. The method may also include the following steps: Based on the integrated model configuration components of the data processing service layer, the control strategy algorithm, primary frequency modulation algorithm model, fan fault warning model, prediction analysis model, performance optimization model and control algorithm model are uploaded to the data scheduling layer in an encrypted and packaged file format.

[0091] S403, based on the data scheduling layer, adopts heterogeneous data cross-process technology to schedule and execute the processing process of global shared information of each control strategy algorithm model, and performs global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and generates a monitoring data set according to each mapping relationship and data aggregation process.

[0092] It should be noted that the specific implementation principle of this embodiment has been described in the above embodiments and will not be repeated here.

[0093] According to an implementation of the present application, the global shared information includes a shared data packet. Based on the data scheduling layer, the heterogeneous data cross-process technology is used to schedule and execute the processing process of the global shared information of each control strategy algorithm model, which may include the following steps: Sort multiple processes that process shared data packets by preset execution time, put the process with the shortest preset execution time in the ready queue, and initialize shared memory and system semaphores. If the CPU is idle and there is a process in the ready queue, execute the process with the shortest preset execution time until it is completed. If two or more processes have the same execution time, execute them in the order of their arrival; if a new process arrives and its execution time is shorter than that of the current execution process, schedule the new process after the current execution process is completed.

[0094] When a process is completed, check whether a new process has arrived. If a new process has arrived, reorder the ready queue according to the preset execution time. Repeat the steps of sorting by preset execution time and the steps after that until all processes are scheduled and executed and the shared memory is cleaned up.

[0095] In some embodiments, the heterogeneous data cross-processing technology may include the following steps: (1) Initialization: Sort all the processes that have arrived by their estimated execution time. Put the first process with the shortest estimated execution time into the ready queue and initialize the shared memory and semaphore.

[0096] (2) Process selection: If the CPU is idle and there are processes in the ready queue, the process with the shortest estimated execution time is selected for execution.

[0097] (3) Executing process: The selected process will continue to run until it is completed. If a new process arrives and its estimated execution time is shorter than the currently executing process, it is necessary to wait until the current process is completed before considering scheduling the new process.

[0098] (4) Update status: When a process is completed, check whether there are new processes arriving. If so, reorder the ready queue according to the estimated execution time.

[0099] (5) Loop: Repeat the above process until all processes are scheduled.

[0100] (6) Cleanup: Clean up shared memory segments that are no longer needed.

[0101] It should be noted that compared with the traditional distributed integrated architecture, the new energy multi-model platform adopts heterogeneous data SJF cross-process technology to achieve data interoperability between multiple models based on the characteristics of wind farm scenarios. According to the needs of each model for global shared variables, it effectively schedules shared data packets to ensure that the data packets with the shortest processing time are processed first, thereby minimizing waiting time. This method is suitable for processing a large number of small shared data packets, because it can significantly reduce the overall waiting time of the data packets, reduce the performance loss caused by data transmission between model nodes on the multi-model platform, and improve large-scale data processing capabilities and efficiency.

[0102] Shortest Job First (SJF) is a process scheduling algorithm. The goal of SJF is to minimize the average waiting time of all processes. SJF will select the process with the shortest remaining execution time to execute. When new processes arrive, they are added to the ready queue, and the operating system will select the process with the shortest remaining execution time to execute. If there are two or more processes with the same remaining execution time, they are usually selected in the order in which they arrive.

[0103] The SJF algorithm is suitable for systems that handle a large number of short jobs or processes. The multi-model platform of the power generation system has certain requirements on the execution frequency and time of the process in which the model is located. Therefore, the shortest job first process scheduling strategy is adopted to facilitate timely updating of shared data.

[0104] The heterogeneous data cross-process scheduling algorithm is as follows: Input: arrival_time, burst_time, data_buffer Output: completed_processes Initial processes and data_buffer while True do Sort the ready_queue by burst_time ifready_queue!=None and CPU do Select the job with Min (arrival_time - burst_time) Update arrival_time, burst_time ifready_queue has a new process do Reorder ready_queue by Min(burst_time) Add to completed_processes In this algorithm, the producer is responsible for generating the data that the model will put into the shared memory, and the consumer is responsible for processing the overall shared memory data. The algorithm table shows the algorithm for processing data. In the algorithm, the data packets to be sent to the shared memory are regarded as jobs, and each data packet has an arrival time and a processing time. The goal of this algorithm is to effectively schedule these data packets to minimize the waiting time.

[0105] processes is a list containing all processes, each process contains a (arrival_time, burst_time) tuple, arrival_time is the arrival time of the process, burst_time is the estimated execution time of the process, data_buffer is a shared memory buffer, ready_queue is a dynamically updated queue containing all ready processes. completed_processes is a list used to record completed processes.

[0106] According to an implementation of the present application, a global mapping process is performed on the optimized monitoring data based on the data scheduling layer to obtain a mapping relationship between the data of each model, and a monitoring data set is generated according to each mapping relationship and a data aggregation process, which may include the following steps: Based on the data scheduling layer, the data of each control strategy algorithm model is regularly written into the corresponding shared memory, and the mapping relationship between the data of each control strategy algorithm model is established. According to each mapping relationship, based on the data aggregation process, the data is regularly read from the shared memory of each control strategy algorithm model, and the read data is merged into the shared memory public space to generate a monitoring data set for multi-model intelligent operation and maintenance.

[0107] In some embodiments, each computing model periodically writes its own data to its dedicated shared memory segment. Use synchronization mechanisms (such as mutexes) to protect the data update process and ensure data consistency. Set up a process or thread responsible for aggregating data. This aggregator periodically reads data from the shared memory of each computing model and merges it into the common shared memory space. Use synchronization mechanisms to ensure that data reading and writing do not conflict. Other processes or threads that need to access the aggregated data can read data from the common shared memory space.

[0108] According to one embodiment of the present application, the method may further include the following steps: Based on the data scheduling layer, data audit is performed on the optimized monitoring data, and a full life cycle management system for the original monitoring data is established.

[0109] S404, based on the application layer, executes the business logic of wind turbine monitoring and analysis according to the monitoring data set and various control strategy algorithm models to monitor and analyze the operating status trend of the wind turbine.

[0110] According to one implementation of the present application, the optimized monitoring data is constructed into two types of data streams based on the application layer, and each model is classified and analyzed and judged based on the two types of data streams, and each model is analyzed and judged based on the system signal quantity, and the two types of data streams are fed back to the data scheduling layer for processing by the data scheduling layer.

[0111] According to an implementation of the present application, based on the application layer, the optimized monitoring data is constructed into two types of data streams, the two types of data streams are fed back to the data scheduling layer, and they are used for processing by the data scheduling layer, which may include the following steps: The optimized monitoring data is constructed into historical data streams and real-time data streams, which are fed back to the data scheduling layer for judging global shared information and generating monitoring data sets. In the shared information mechanism of the data scheduling layer, historical data streams and real-time data streams are used as the public data sources of various control strategy algorithm models.

[0112] In one embodiment, multiple processes in a background shared information mechanism provide the common data source requirements of each model in a highly concurrent manner.

[0113] The wind turbine monitoring and analysis platform based on multi-source heterogeneous data of the present application includes: data access layer, data processing service layer, data scheduling layer and application layer. The wind turbine monitoring and analysis method based on multi-source heterogeneous data of the present application is implemented based on the platform. First, the original monitoring data and wind farm management system signal quantity are obtained based on the data access layer. Secondly, the original monitoring data is optimized and processed based on the data processing service layer. Then, the heterogeneous data cross-process technology is used based on the data scheduling layer to schedule and execute the processing process of the global shared information of each control strategy algorithm model, and the optimized monitoring data is globally mapped to generate a monitoring data set. Finally, the operating status trend of the wind turbine is monitored and analyzed based on the monitoring data set and each model based on the application layer.

[0114] The heterogeneous data cross-process technology adopted in the present application can effectively process multi-source heterogeneous data in wind farms, realize the sharing of information resources generated in real time among multiple models, thereby improving the efficiency of wind turbine monitoring and analysis, and has strong ease of use and practicality.

[0115] This application scheme uses efficient data scheduling technology to effectively process various heterogeneous data in wind farms, and applies it to multi-model intelligent operation and maintenance, thereby improving the operation and maintenance efficiency of wind farms and the safety of equipment operation. The platform can uniformly obtain wind turbine data, monitor and analyze the operating status trends of the fleet through a multi-model platform, and realize the sharing of information resources generated in real time between multiple models.

[0116] Compared with the existing technology, the present application has the following advantages: High compatibility: It can adapt to the data formats and communication protocols of various wind turbine models, and realize data integration between different wind turbine models. Information resource sharing: It breaks down the barriers of information transmission, realizes data sharing between multiple models, and improves the accuracy and timeliness of data analysis. Efficient resource utilization: It optimizes resource allocation, reduces unnecessary data processing and transmission processes, and thus reduces operation and maintenance costs.

[0117] Through the heterogeneous data SJF cross-process technology, multi-source data can be efficiently shared and scheduled, and effective processing of various heterogeneous data in wind farms can be achieved, and it can be applied to the intelligent operation and maintenance of multiple models, thereby improving the operation and maintenance efficiency of wind farms and the safety of equipment operation. Based on multi-source heterogeneous data, the present application scheme can deploy various intelligent operation and maintenance models, such as fault prediction models, performance optimization models, etc. The platform can implement algorithm encapsulation and support the encryption and encapsulation of control logic composed of multiple algorithm blocks into specific algorithm packages. The encapsulated algorithm should have the same configuration, operation and maintenance methods as conventional algorithms, which is conducive to the reuse of technical achievements in a concise manner.

[0118] This application solution adopts multi-protocol unified collection to ensure that data between different devices and systems can be seamlessly connected. The integrated and standardized forwarding of data improves data processing efficiency, reduces data redundancy, facilitates rapid control decisions, reduces delays, and improves the response speed of the system. The platform can integrate a variety of optimization, control, and prediction operation models to provide flexible control solutions to adapt to different working conditions. This gives this application solution obvious advantages in opening up information channels, consolidating strategy algorithms, simplifying personnel operations, and improving production efficiency.

[0119] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0120] Corresponding to the method of the above embodiment, Figure 6 1 is a schematic diagram of the structure of a wind turbine monitoring and analysis device based on multi-source heterogeneous data provided by an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0121] Reference Figure 6 , the device comprises: The acquisition unit 601 is used to acquire the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system based on the data access layer; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; The optimization processing unit 602 is used to optimize the original monitoring data based on the data processing service layer to obtain the optimized monitoring data and standardize the data collection interface; The data set generation unit 603 is used to schedule and execute the processing process of the global shared information of each control strategy algorithm model based on the heterogeneous data cross-process technology adopted in the data scheduling layer, and perform global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and generate the monitoring data set according to each mapping relationship and the data aggregation process; The monitoring and analysis unit 604 is used to execute the business logic of wind turbine monitoring and analysis based on the application layer according to the monitoring data set and various control strategy algorithm models, so as to monitor and analyze the operating status trend of the wind turbine.

[0122] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0123] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0124] See also Figure 7 , Figure 7 Schematic diagram of the structure of the electronic device 7 provided in the embodiment of the present application. Figure 7 As shown, the electronic device 7 of this embodiment includes: at least one processor 701 ( Figure 7 Only one is shown in the figure), a memory 703, and a computer program 702 stored in the memory 703 and executable on at least one processor 701, wherein the processor 701 implements the steps in the above method embodiment when executing the computer program 702.

[0125] The electronic device 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a mobile phone. The electronic device 7 may include, but is not limited to, a processor 701 and a memory 703. Those skilled in the art will appreciate that Figure 7 It is only an example of the electronic device 7 and does not constitute a limitation on the electronic device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0126] The processor 701 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware photovoltaic modules, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0127] In some embodiments, the memory 703 may be an internal storage unit of the electronic device 7, such as a hard disk or memory of the electronic device 7. In other embodiments, the memory 703 may also be an external storage device of the electronic device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital card (SecureDigital, SD), a flash card (Flash Card), etc. equipped on the electronic device 7. Further, the memory 703 may also include both an internal storage unit of the electronic device 7 and an external storage device. The memory 703 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as program codes of computer programs, etc. The memory 703 may also be used to temporarily store data that has been output or is to be output.

[0128] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, when the present application implements all or part of the processes in the above-mentioned embodiment method, it can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps applied to the above-mentioned method embodiment. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may at least include: any entity or device that can carry the computer program code to the computing device / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, such as USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electric carrier signals and telecommunication signals.

[0129] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0130] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps in the above-mentioned method embodiments.

[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. The device / electronic device embodiments described above are merely schematic, and the division of the above modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or photovoltaic components can be combined or integrated into another system, and some features can be ignored and not executed. Another point is that the indirect coupling, direct coupling or communication connection between each other shown or discussed can be an indirect coupling, direct coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0134] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A wind turbine monitoring and analysis platform based on multi-source heterogeneous data, characterized in that: The platform includes: The data access layer is used to obtain the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; The data processing service layer is used to optimize the original monitoring data to obtain the optimized monitoring data and standardize the data acquisition interface; The data scheduling layer is used to schedule and execute the processing process of global shared information of each control strategy algorithm model by adopting heterogeneous data cross-process technology, and to perform global mapping processing on the optimized monitoring data to obtain the mapping relationship between the data of each model, and to generate the monitoring data set according to each mapping relationship and data aggregation process; The application layer is used to execute the business logic of wind turbine monitoring and analysis based on the monitoring data set and various control strategy algorithm models, so as to monitor and analyze the operating status trend of the wind turbine.

2. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The platform also includes: The data storage layer is used to store historical data, real-time data, and analytical data; historical data refers to the original monitoring data collected before the current time, real-time data refers to the original monitoring data collected in real time, and analytical data refers to the original monitoring data used for model analysis; The data forwarding layer is used to send the original monitoring data to the data processing service layer in a preset communication protocol format, and forward the optimized monitoring data to the application layer.

3. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 2 is characterized in that: The data forwarding layer includes at least one communication module, and each communication module is used to forward the optimized monitoring data to the application layer.

4. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The data access layer includes: a data query module, a Beckhoff control module, a Bachmann control module and a serial communication module; the data scheduling layer is also used to perform data audits on the optimized monitoring data and build a full life cycle management system for the original monitoring data; the application layer includes: a network terminal, a client terminal, a data acquisition and monitoring system, an energy management module and a centralized control module.

5. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The data processing service layer includes: an interface standardization module, a data cleaning module, a data standardization module and a data preprocessing module; The interface standardization module is used to standardize the data acquisition interface; the data cleaning module is used to clean the original monitoring data; the data standardization module is used to standardize the original monitoring data; the data preprocessing module is used to preprocess the original monitoring data.

6. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The control strategy algorithm model includes: primary frequency modulation algorithm model, fan fault warning model, prediction analysis model, performance optimization model and control algorithm model; The data processing service layer is also used to integrate model configuration elements, and upload the control strategy algorithm, primary frequency modulation algorithm model, fan fault warning model, prediction analysis model, performance optimization model and control algorithm model to the data scheduling layer in an encrypted and packaged file format.

7. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The application layer is also used to construct the optimized monitoring data into two types of data streams, classify and analyze and judge each model based on the two types of data streams, analyze and judge each model based on the system signal quantity, and feed back the two types of data streams to the data scheduling layer for processing by the data scheduling layer.

8. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 1 is characterized in that: The platform also includes a data source device cluster; the data source device cluster is used to collect the original monitoring data and send the original monitoring data to the data access layer in a preset communication protocol format.

9. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 8 is characterized in that: The original monitoring data includes: blade monitoring data, vibration monitoring data, frequency change monitoring data, single machine information data, wind turbine data, equipment operation data and environmental monitoring data; the data source equipment cluster includes: switches, servers, controllers, sensors, equipment managers, environmental monitors and wind farm operation and maintenance monitoring database; The sensor is used to collect blade monitoring data, vibration monitoring data and frequency change monitoring data; the controller is used to collect single-machine information data and wind turbine data; the equipment manager is used to collect equipment operation data; the environmental monitor is used to collect environmental monitoring data; the wind farm operation and maintenance monitoring database is used to store the original monitoring data.

10. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to any one of claims 1 to 9, characterized in that: The wind farm management system includes: SCADA monitoring system, wind power prediction system, AGC / AVC energy management system, electric energy metering system and production management system; the collection types of the system signal quantities include: electrical analog quantity, non-electrical analog quantity, interrupt switch quantity and non-interrupt switch quantity.

11. The wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to claim 10, characterized in that: The electrical analog quantity includes: voltage, power and current; the non-electrical analog quantity includes: wind speed, displacement, temperature, vibration frequency, rotation speed, wind direction and radiation; The interruption switch quantity includes: accident signals, action signals of circuit breakers and relay protection; the non-interruption switch quantity includes: various fault signals, position signals of circuit breakers and disconnectors, and status signals of wind turbines.

12. A wind turbine monitoring and analysis method based on multi-source heterogeneous data, characterized in that: A wind turbine monitoring and analysis platform based on multi-source heterogeneous data according to any one of claims 1 to 11 is implemented, and the method comprises: Based on the data access layer, the original monitoring data in the wind farm operation and maintenance monitoring database and the system signal quantity of the wind farm management system are obtained; the original monitoring data is multi-source heterogeneous data, and the wind farm management system is used to collect the system signal quantity; Based on the data processing service layer, the original monitoring data is optimized to obtain the optimized monitoring data, and the data collection interface is standardized; Based on the data scheduling layer, the heterogeneous data cross-process technology is used to schedule and execute the processing process of the global shared information of each control strategy algorithm model, and the optimized monitoring data is globally mapped to obtain the mapping relationship between the data of each model, and the monitoring data set is generated according to each mapping relationship and data aggregation process; Based on the application layer, the business logic of wind turbine monitoring and analysis is executed according to the monitoring data set and various control strategy algorithm models to monitor and analyze the operating status trend of the wind turbine.

13. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12, characterized in that: The original monitoring data is optimized based on the data processing service layer to obtain optimized monitoring data, and the data collection interface is standardized, including: Based on the data processing service layer, the raw monitoring data is cleaned, standardized and pre-processed, and the communication of the data acquisition interface is standardized, the data upload rules are unified, and the measurement point naming is standardized.

14. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12 or 13, characterized in that: Before optimizing the original monitoring data based on the data processing service layer, the method further includes: Historical data is selected from the original monitoring data at a preset time or a preset time period, and real-time data is extracted from the original monitoring data at a preset communication time; wherein historical data is the original monitoring data collected before the current time, and real-time data is the original monitoring data collected in real time.

15. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12, characterized in that: The control strategy algorithm model includes: a primary frequency modulation algorithm model, a fan fault warning model, a prediction analysis model, a performance optimization model and a control algorithm model; the method also includes: Based on the integrated model configuration element of the data processing service layer, the control strategy algorithm, primary frequency modulation algorithm model, fan fault warning model, prediction analysis model, performance optimization model and control algorithm model are uploaded to the data scheduling layer in an encrypted and packaged file format.

16. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12, characterized in that: The global shared information includes a shared data packet; based on the data scheduling layer, the heterogeneous data cross-process technology is used to schedule and execute the processing process of the global shared information of each control strategy algorithm model, including: Sorting the multiple processes processing the shared data packet according to preset execution time, placing the process with the shortest preset execution time in a ready queue, and initializing the shared memory and the system semaphore; If the CPU is idle and there are processes in the ready queue, the process with the shortest preset execution time will be executed until its execution is completed; if two or more processes have the same execution time, they will be executed in the order of their arrival; if a new process arrives and its execution time is shorter than that of the current execution process, the new process will be scheduled after the current execution process is completed; When a process is completed, check whether a new process has arrived. If a new process has arrived, reorder the ready queue according to the preset execution time; Repeat the steps sorted by the preset execution time and the steps thereafter until all processes are scheduled to be executed and the shared memory is cleaned up.

17. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12 or 16, characterized in that: Based on the data scheduling layer, the optimized monitoring data is globally mapped to obtain the mapping relationship between the data of each model, and the monitoring data set is generated according to each mapping relationship and data aggregation process, including: Based on the data scheduling layer, the data of each control strategy algorithm model is regularly written into the corresponding shared memory, and a mapping relationship between the data of each control strategy algorithm model is established; According to each mapping relationship, data is read from the shared memory of each control strategy algorithm model regularly based on the data aggregation process, and the read data is merged into the shared memory public space to generate a monitoring data set for multi-model intelligent operation and maintenance.

18. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 12, characterized in that: The method further comprises: Based on the data scheduling layer, data audit is performed on the optimized monitoring data, and a full life cycle management system for the original monitoring data is established.

19. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 14, characterized in that: Based on the application layer, the optimized monitoring data is constructed into two types of data streams, and each model is classified and analyzed and judged based on the two types of data streams. Each model is analyzed and judged based on the system signal quantity, and the two types of data streams are fed back to the data scheduling layer for processing by the data scheduling layer.

20. The wind turbine monitoring and analysis method based on multi-source heterogeneous data according to claim 19, characterized in that: Based on the application layer, the optimized monitoring data is constructed into two types of data streams, and the two types of data streams are fed back to the data scheduling layer for processing by the data scheduling layer, including: The optimized monitoring data is constructed into a historical data stream and a real-time data stream, and the historical data stream and the real-time data stream are fed back to the data scheduling layer to be used for judging global shared information and generating monitoring data sets; In the shared information mechanism of the data scheduling layer, the historical data stream and the real-time data stream are used as the common data sources of each control strategy algorithm model.

21. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the wind turbine monitoring and analysis method based on multi-source heterogeneous data described in any one of claims 12-20 is implemented.

22. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the wind turbine monitoring and analysis method based on multi-source heterogeneous data described in any one of claims 12 to 20 is implemented.

Images