New energy power plant management method, device, equipment, medium and product

Abstract

The invention discloses a new energy power plant management method and device, equipment, a medium and a product, and relates to the technical field of data processing, and the method comprises the steps: determining the initial detection information of a power plant; processing the initial detection information by using a preset information mapping rule to obtain target detection information, the target detection information comprising at least one piece of target type information and target detection data corresponding to the target type information; and based on the at least one target type information, determining a target fault diagnosis model of the power generation field, and processing the target detection data corresponding to the at least one target type information by using the target fault diagnosis model to obtain a fault diagnosis result of the power generation field. According to the technical scheme, downstream applications do not need to be stopped, the modification adaptation difficulty and the shutdown frequency of downstream machine learning applications in the new energy field are reduced, the equipment maintenance cost of a new energy power plant is reduced, and the real-time performance of equipment detection and operation and maintenance is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a management method, device, equipment, medium and product for a new energy power plant. Background Art

[0002] As the scale of new energy assets expands, the production and operation management of enterprises such as power plants faces problems such as a large number of equipment and facilities, transformation of old models, limited staffing, and great management difficulty. Therefore, how to achieve large-scale data access and convenient application of new energy assets, improve production efficiency, and reduce operation and maintenance costs is an urgent problem that needs to be solved.

[0003] In the field of renewable energy power generation, electric field equipment is built in multiple phases with a wide variety of models. The number of data measurement points of the equipment is large and the monitoring points are different. The equipment points often change. Moreover, the maintenance and technical transformation of the equipment will also cause the data measurement points of the equipment to change frequently. At present, in the process of electric field construction, downstream services depend on the upstream equipment points, that is, downstream big data and artificial intelligence services need to be frequently shut down and service adjustments are made in response to changes in upstream equipment point data. However, downtime will cause all equipment monitoring services to be suspended, and once downstream services cannot respond to upstream data changes in a timely manner, it will lead to deviations in the monitoring and analysis of equipment data, and then make wrong decision-making guidance for production and operation. Summary of the invention

[0004] The present invention provides a management method, device, equipment, medium and product for a renewable energy power plant, aiming to reduce the modification and adaptation difficulty and downtime of downstream machine learning applications in the renewable energy field, reduce the equipment maintenance cost of renewable energy power plants, and improve the real-time performance of equipment detection and operation and maintenance.

[0005] According to one aspect of the present invention, a management method for a new energy power plant is provided, the method comprising:

[0006] Determining initial detection information of the power plant, wherein the initial detection information includes at least one initial type information and at least one initial detection data corresponding to the initial type information;

[0007] Using a preset information mapping rule, at least one initial type information and initial detection data corresponding to the at least one initial type information are processed to obtain target detection information, wherein the target detection information includes at least one target type information and target detection data corresponding to the target type information;

[0008] Based on at least one target type information, a target fault diagnosis model of the power plant is determined, and the target fault diagnosis model is used to process target detection data corresponding to the at least one target type information to obtain a fault diagnosis result of the power plant.

[0009] According to another aspect of the present invention, a management device for a new energy power plant is provided. The management device for a new energy power plant is used to implement the management method for a new energy power plant in any embodiment of the present invention. The device includes:

[0010] An acquisition module, used to determine initial detection information of the power plant, wherein the initial detection information includes at least one initial type information and at least one initial detection data corresponding to the initial type information;

[0011] A determination module, configured to process at least one initial type information and initial detection data corresponding to at least one initial type information by using a preset information mapping rule to obtain target detection information, wherein the target detection information includes at least one target type information and target detection data corresponding to the target type information;

[0012] The diagnosis module is used to determine a target fault diagnosis model of the power plant based on at least one target type information, and use the target fault diagnosis model to process target detection data corresponding to at least one target type information to obtain a fault diagnosis result of the power plant.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] at least one processor; and a memory communicatively coupled to the at least one processor;

[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the management method of the new energy power plant in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for implementing the management method of the new energy power plant in any embodiment of the present invention when executed by a processor.

[0017] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the management method of the new energy power plant of any embodiment of the present invention is implemented.

[0018] The management method of the new energy power plant of the present invention includes: determining the initial detection information of the power plant, wherein the initial detection information includes at least one initial type information and at least one initial detection data corresponding to the initial type information; using a pre-set information mapping rule, processing at least one initial type information and at least one initial detection data corresponding to the initial type information to obtain target detection information, wherein the target detection information includes at least one target type information and target detection data corresponding to the target type information; based on at least one target type information, determining a target fault diagnosis model of the power plant, and using the target fault diagnosis model to process the target detection data corresponding to at least one target type information to obtain a fault diagnosis result of the power plant. The technical solution of the present invention can integrate and map the types and measurement point data of the equipment in the power plant, put them under a unified node measurement method, process the standardized and unified target detection information, obtain the equipment diagnosis results of the power plant, and map different data in a unified reference vector through the mapping method of data stream, that is, directly map the changed upstream information to the pre-set reference vector, without stopping the downstream application, so that the change rhythm of the cluster node is synchronized, reduce the modification and adaptation difficulty and shutdown times of downstream machine learning applications in the new energy field, reduce the equipment maintenance cost of the new energy power plant, and improve the real-time performance of equipment detection and operation and maintenance. It solves the problem that downstream big data and artificial intelligence services need to frequently shut down and adjust services according to the changes in upstream equipment point data. The shutdown will cause the equipment monitoring business to be suspended. Once the downstream service cannot respond to the upstream data changes in time, it will cause deviations in the monitoring and analysis of the equipment data, and then make wrong decision-making guidance for production and operation and maintenance.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0021] Figure 1 It is a flow chart of a management method of a new energy power plant provided by the present invention;

[0022] Figure 2 is a schematic diagram of a device model hierarchy provided by the present invention;

[0023] Figure 3 It is a schematic diagram of a processing flow provided by the present invention;

[0024] Figure 4 It is a structural schematic diagram of a management device for a new energy power plant provided by the present invention;

[0025] Figure 5 It is a structural schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Stream processing is a data processing system that continuously analyzes business data sets that are essentially endless and continuously generated. In the scenario of large-scale streaming data analysis, Apache Flink is the most mature and reliable distributed stream-batch integrated data processing open source framework. Specifically, if the device measurement point data is used as the business data source, all device data is pushed to the center end in a low-latency manner for real-time and uninterrupted analysis and processing. Due to the non-uniformity of device measurement points and the existence of variable objective conditions (including but not limited to changes in measurement point names and increases and decreases in measurement points), it will cause problems such as missing stream processing data, frequent adjustments to data algorithms, distorted data analysis results, and extremely difficult operation and maintenance. If the device data points are modeled in advance according to the model, it can only solve the problem of inconsistent data points. When some equipment is debugged, repaired or technically modified, it will still bring about the problem of frequent model modifications. At the same time, the adjustment of the monitoring and early warning algorithm for some equipment will cause the monitoring of all equipment to be suspended, which cannot solve the problem of uninterrupted production monitoring.

[0029] The present invention classifies and models new energy equipment and records and version-manages the mapping relationship of the original points of the equipment, provides a unified measurement point data reading interface, utilizes the broadcast control flow to adapt to the changes in point mapping in real-time machine learning, and utilizes the hot loading mode to update the algorithm model without stopping, so as to solve the problems of inconsistent measurement points of equipment from different manufacturers in the new energy field and frequent modification and adaptation of downstream machine learning applications and high equipment maintenance costs caused by changes in equipment measurement points.

[0030] Figure 1 This is a flow chart of a management method for a new energy power plant provided by the present invention. This embodiment can be used to reduce the difficulty of modification and adaptation and the number of downtimes of downstream machine learning applications in the field of new energy, reduce the equipment maintenance cost of new energy power plants, and improve the real-time performance of equipment detection and operation and maintenance. The method can be executed by the management device for new energy power plants provided by the present invention. The device can be implemented in the form of hardware and / or software. In a specific embodiment, the device can be integrated in an electronic device. The following embodiments will be described by taking the device integrated in an electronic device as an example. Figure 1 , the method specifically comprises the following steps:

[0031] S101. Determine initial detection information of a power plant.

[0032] The power plant includes multiple devices. To determine the operation status of the power plant or whether there is a fault in the equipment in the power plant, it is necessary to obtain the operation parameters of multiple devices or multiple locations of one device in the power plant. For example, when analyzing a cabin fault, it is necessary to determine the temperature information of multiple cabins, including but not limited to the cabin temperature of fan A, the cabin temperature of fan B, and the cabin temperature of fan C in the power plant. The initial detection information can be understood as the operation information detected in the power plant for determining the fault. The initial detection information includes at least one initial type information and at least one initial detection data corresponding to the initial type information. The initial type information can be understood as an information identifier used to distinguish the various information obtained. The initial detection data corresponding to the initial type information can be understood as the specific parameter value of the initial type information. For example, if the cabin temperature of fan A is X1, the initial type information is the cabin temperature of fan A, and the initial detection data is X1. It is worth noting that there is more than one device in the power plant, so at least one piece of information is obtained, and there is a corresponding relationship between the initial type information and the initial detection data. The corresponding relationship can be one initial type information corresponding to one initial detection data, or one initial type information corresponding to multiple initial detection data. The specific corresponding relationship is related to the data acquisition method, acquisition time and fault detection logic, which is not limited in this embodiment. The advantage of this setting is that it can obtain high-real-time and comprehensive data, improving the accuracy and effectiveness of fault detection.

[0033] The present invention can obtain the operating conditions of the equipment in the power plant regularly or irregularly, and determine the fault conditions of the power plant based on the information obtained. Furthermore, during the construction of the power plant, the equipment is continuously increased, and the present invention can also superimpose the data acquisition method of the newly added equipment on the original equipment acquisition method. The advantage of such a setting is that it can reduce the difficulty and duration of data acquisition work as much as possible, and improve the acquisition efficiency of detection data.

[0034] In one embodiment, S101 may specifically include: determining historical data measurement points and newly added data measurement points of the power plant; based on the historical data measurement points, the detection rules of the historical data measurement points, the newly added data measurement points and the detection rules of the newly added data measurement points, determining at least one initial type information and at least one initial detection data corresponding to the initial type information.

[0035] Among them, the historical data measurement points can be understood as the location of the original equipment in the power plant, the newly added data measurement points can be understood as the location of the newly added equipment in the power plant, the detection rules of the historical data measurement points can be understood as the data acquisition plan of the original equipment in the power plant, including but not limited to data acquisition equipment, data acquisition interval duration and data acquisition method, and the detection rules of the newly added data measurement points can be understood as the data acquisition plan of the newly added equipment in the power plant, including but not limited to data acquisition equipment, data acquisition interval duration and data acquisition method. Specifically, by superimposing the data acquisition tasks of the newly added equipment on the data acquisition tasks of the original equipment, high-real-time detection information that conforms to the current equipment distribution of the power plant can be obtained. This information includes the changes in the equipment measurement points of the power plant, which can better indicate the operation of the power plant, thereby improving the quality of fault analysis.

[0036] S102: Using a preset information mapping rule, process at least one initial type information and initial detection data corresponding to at least one initial type information to obtain target detection information.

[0037] Among them, the pre-set information mapping rules can be understood as information processing schemes set in advance according to the fault analysis logic, and the information mapping rules include type mapping rules and data adjustment rules. Different devices and different manufacturers have certain differences in the naming methods, data generation methods and formats of relative parameters. The type mapping rules are used to standardize and unify the naming of each device, that is, to unify the initial type information, and the data adjustment rules are used to standardize and unify the data of each device, that is, to unify the initial detection data. The target detection information includes at least one target type information and the target detection data corresponding to the target type information. The target detection information can be understood as the standardized and unified initial detection information. The target type information is the standard and unified initial type information. The target detection data can be understood as the standard and unified initial detection data. The advantage of this setting is that it can reduce the difficulty of data processing, reduce the workload of the processor, and improve the efficiency of fault diagnosis.

[0038] Specifically, assuming that the fault diagnosis work is performed by the fault diagnosis model, the temperature identifier identified by the fault diagnosis model is temperature X, the temperature identifier of device A is temperature 1, and the temperature identifier of device B is temperature 2, this step will map the temperature identifiers of device A and device B and convert them into temperature X for processing by the fault diagnosis model. Similarly, assuming that the temperature value format identified by the fault diagnosis model is format X, the temperature value format of device A is format 1, and the temperature value format of device B is format 2, this step will map the temperature value formats of device A and device B and convert them into format X for processing by the fault diagnosis model.

[0039] In one embodiment, S102 may specifically include: using information mapping rules to process at least one initial type information to obtain at least one target type information, wherein the target type information and the initial type information correspond one-to-one, or the target type information corresponds to at least one initial type information; using data adjustment rules to process initial detection data corresponding to at least one initial type information to obtain intermediate detection data; determining type information of the intermediate detection data, and based on the correspondence between the type information of the intermediate detection data and the target type information, determining the target detection data corresponding to each target type information.

[0040] Among them, after mapping the initial type information, the target type information will be obtained. Each initial type information has its corresponding target type information, but the target type information corresponds to more than one initial type information. Specifically, the temperature identifier of each device needs to be mapped to temperature X, and the humidity information of each device needs to be mapped to humidity X. If there is only one device temperature in the initial detection information, the initial type information and the target type information of the device temperature parameter are one-to-one corresponding. If there are multiple device temperatures in the initial detection information, the initial type information and the target type information of the device temperature parameter are one-to-many, that is, one target type information corresponds to multiple initial type information. It is worth noting that although it is mapped to one target type information, the device data has its own characteristic information. The advantage of this setting is that when a fault occurs, the faulty device can be quickly located and the cause of the fault can be analyzed based on the characteristic information of the fault data.

[0041] Furthermore, after the initial detection information is normalized, it is necessary to analyze the target type information associated with the corresponding initial type information and use it as the target detection data of the target type information. The advantage of this setting is that the processed type information and detection data can be quickly associated according to the corresponding relationship, the information of the same device from different manufacturers can be unified to obtain standardized data, and the data processing time can be reduced while ensuring data integrity, correspondence and standardization.

[0042] The present invention not only includes online fault detection, but also can set up offline fault detection schemes and data integration schemes. Offline fault detection can be applicable to situations such as no network, remote areas or regular fault analysis. The data integration scheme can regularly integrate data, standardize the data, store and present data, improve data standardization and the data viewing experience of technicians, and save the data processing time of the processor for secondary use of the data. Specifically, after using the pre-set information mapping rules to process at least one initial type information and at least one initial type information corresponding to the initial detection data to obtain the target detection information, it also includes: according to the pre-set data processing scheme, the target detection information is processed to obtain offline detection information, wherein the data processing scheme includes a data integration scheme and a data storage scheme; when receiving the offline data analysis instruction, the offline detection information is processed based on the data processing requirements in the offline data analysis instruction to obtain the offline data processing result, wherein the offline data processing result is used to indicate the equipment adjustment plan and / or equipment operation status of the power plant.

[0043] Among them, offline data analysis instructions can be understood as offline data processing instructions, including but not limited to data integration instructions, data analysis instructions, fault analysis instructions and data storage instructions. Offline data analysis instructions can be triggered by users according to usage requirements, or can be triggered by servers at a scheduled time. This embodiment does not limit this.

[0044] Specifically, the offline data processing results can be understood as the processing conclusions of the offline data. For example, when the offline data analysis instructions are data integration instructions, the offline data processing results can be data integration success identification, data integration report, data integration table, data integration failure indication and abnormal reasons, etc.; when the offline data analysis instructions are data storage instructions, the offline data processing results can be data storage success identification, data storage location, data storage failure indication and abnormal reasons, etc.

[0045] In one embodiment, data is stored monthly, the temperature information of device A from January to March is named temperature 1, and the temperature information from April to December is named temperature 2, if the temperature sorting scheme is to sort the temperatures and use them uniformly.

[0046] Table 1

[0047]

[0048]

[0049] Table 2

[0050] month temperature 1 X1 2 X2 3 X3 4 X4 5 X5 6 X6 … …

[0051] Table 1 is the temperature data of device A before sorting, and Table 2 is the temperature data of device A before sorting. It can be seen intuitively from the above two tables that the integrated data has a higher degree of neatness and standardization, and requires less space.

[0052] S103: Determine a target fault diagnosis model of the power plant based on at least one target type information, and use the target fault diagnosis model to process target detection data corresponding to at least one target type information to obtain a fault diagnosis result of the power plant.

[0053] Different types of faults require different fault diagnosis models. The present invention determines the fault diagnosis model to be used according to the fault diagnosis requirements. The target fault diagnosis model can be understood as an algorithm for detecting faults in the direction of target type information in the fault diagnosis model. For example, when the target type information is the cabin temperature, the target fault diagnosis model is a cabin fault analysis model. The advantage of this setting is that it can save the use of non-target diagnosis models, and there is no need to update multiple models, saving unnecessary work and improving the computing efficiency of the processor. The fault diagnosis method is to input the target detection data corresponding to the target type information into the target fault diagnosis model for processing, and determine the fault diagnosis result of the power plant according to the model output. The content of the model output includes but is not limited to the fault diagnosis conclusion, identification information of different faults and fault reports. According to the model output, the fault diagnosis conclusion of the power plant can be obtained. The direct mapping and model control method does not require stopping downstream application services, which can avoid system downtime and reduce maintenance costs.

[0054] In one embodiment, based on at least one target type information, a target fault diagnosis model of a power plant is determined, including: based on at least one target type information, searching in the correspondence between type information and diagnosis models to obtain a candidate fault diagnosis model; determining whether there is an update indication for the candidate fault diagnosis model; if there is no update indication for the candidate fault diagnosis model, determining the candidate fault diagnosis model to be the target fault diagnosis model; if there is an update indication for the candidate fault diagnosis model, updating the candidate fault diagnosis model based on the update indication, and determining the updated candidate fault diagnosis model to be the target fault diagnosis model.

[0055] Among them, the candidate fault diagnosis model can be understood as a model that matches the target type information, that is, an algorithm for determining the fault in the direction of the target type information. The update indication is used to indicate whether the candidate fault diagnosis model needs to be optimized, that is, whether the program package of the current model needs to be updated and reloaded. If there is an update indication, it proves that the candidate fault diagnosis model is not the latest and needs to be optimized and updated. If there is no update indication, it proves that the candidate fault diagnosis model is the latest and does not need to be optimized and updated. It can be used directly to parse equipment faults in power plants.

[0056] The advantage of this setting is that only the models that need to be updated are updated, which can ensure the quality of fault diagnosis without wasting processor computing power.

[0057] The present invention will systematically name the point information of the equipment (wind turbines, inverters, booster stations, etc.) in order to distinguish large components (logical nodes), data names, data types and other information. Specifically, combined with the self-developed FLINK DATASOURCE & RichFlatMapFunction SDK, considering machine resources and performance, the four-segment type of the point name is configured for regular matching, and the model-dependent input is obtained on demand to reduce the amount of data transmission. In order to represent the hierarchical structure of the equipment model and the parsing logic of unified data, a model path representation method is designed to represent the hierarchical structure of the equipment information model. The model path is in the form of four segments separated by dot numbers, for example, the first segment. The second segment. The third segment. The fourth segment {. The fifth segment}. Among them, the first segment represents the logical node (LN), the second segment represents the data name, the third segment represents the data flow identifier, the fourth segment represents the data type, and the fifth segment in brackets is optional content, which can be set, adjusted and increased or decreased according to specific business and measurement points. Figure 2 It is a schematic diagram of a device model hierarchy provided by the present invention. XXX in the figure represents the name of a power plant. It can be seen from the figure that the power plant includes multiple devices, the device includes multiple logical nodes, each logical node includes multiple data, and the data includes information such as data name, data volume identifier and type.

[0058] It is worth noting that before processing the data, the model can also filter and discard the target detection information according to the model path and data processing logic, and only select necessary data for processing. For example, if the model only needs the data of the temperature logic node, the data except the temperature node will be discarded. The advantage of this setting is that it can greatly reduce the data processing amount of the model.

[0059] Optionally, after obtaining the fault diagnosis results of the power plant, it also includes: determining whether the fault diagnosis results have any abnormal operation indications; if the fault diagnosis results do not have any abnormal operation indications, generating equipment control parameters, and controlling the equipment in the power plant to operate based on the equipment control parameters; if the fault diagnosis results have abnormal operation indications, generating a fault adjustment report based on the fault diagnosis results, and displaying the fault adjustment report, wherein the fault adjustment report is used to indicate the equipment abnormality information and equipment adjustment plan of the power plant.

[0060] Among them, determining whether there is an abnormal operation indication in the fault diagnosis result can be understood as determining whether there is abnormal operation information of the power plant equipment in the fault diagnosis result. If not, it proves that the equipment in the power plant is normal, and the optimized control mode of the power plant equipment (i.e., the equipment control parameters) will be generated, and the equipment in the power plant will be controlled to operate based on the optimized control mode to adjust the operation mode of each device in the power plant and improve the performance of the power plant. If it exists, it proves that there is abnormal equipment in the power plant, and it is necessary to locate the abnormal equipment, analyze the cause of the equipment abnormality, generate a fault adjustment report, and instruct the operation and maintenance personnel to debug the equipment to minimize the loss of the power plant.

[0061] In the present invention, by extending the SOURCE interface of FLINK, an SDK for reading device data is provided, and a simple configuration method for obtaining model data on demand is implemented in the SDK. At the same time, the SDK also provides FLINK's Broadcast Process Function customization. When the upstream data point changes and the data source cannot standardize the measurement point name, the mapping relationship management of the measurement point naming is used, and the Broadcast State&Stream mechanism of the FLINK framework is used to issue the control flow, and the data measurement point name is changed globally to ensure that each node in the computing cluster is synchronized during the change, thereby achieving a globally consistent effect of business decision-making of the model output. Figure 3 It is a schematic diagram of a processing flow provided by the present invention. The implementation device of the present invention is a processor between the upstream and the downstream. Instruction 1 represents the instruction sent from the upstream to the processor, the data represents the data transmitted from the upstream to the processor, and the instruction 2 represents the control information sent by the processor to the downstream. The present invention will perform four-segment regular matching configuration of the point name and measurement point coding mapping configuration information processing according to instruction 1 and data, perform functional processing in the use model, and then obtain the downstream control instruction.

[0062] Table 3

[0063]

[0064] Table 3 shows the measurement point code mapping configuration information, wherein the mapping effective start event can be configured in advance in combination with the on-site implementation, and the above table can be updated and overwritten when the configuration information changes, including but not limited to changing the configuration content and adjusting the effective time.

[0065] Furthermore, in production scenarios, when equipment undergoes component replacement, technical changes, and other scenarios, and the data points of the equipment increase or decrease, the downstream real-time model also needs to make corresponding changes. For resource and performance considerations, multiple models often share a data stream. Secondly, real-time scenarios are very sensitive to availability, and real-time machine learning operations usually need to avoid starting and stopping. The present invention can combine JAVA's CLASSLOADER mechanism and use URLCLASSLOADER to achieve non-stop hot loading of data models, implement model hot loading management through self-developed SDK, and also use FLINK's Broadcast State&Stream to issue change commands to ensure that the change rhythm of cluster nodes is synchronized, so as to achieve a globally consistent output of model results. The configuration information and the use and implementation of the issuance are the same as above. Specifically, the model configuration information is shown in Table 4.

[0066] Table 4

[0067]

[0068] The present invention can model the equipment classification in the field of new energy, standardize the equipment measurement points, record and version the mapping relationship between the source data measurement points and the platform standardized measurement points (equivalent to the recording and management of historical measurement point information and program packages), use the broadcast control event stream method in FLINK real-time machine learning, use the self-developed SDK and point mapping relationship to adapt to the modification of source data, and hot-load the corresponding algorithm changes without stopping, so as to achieve high availability in real-time scenarios. It is worth noting that point mapping relationships and version management are also used to isolate upstream measurement point changes in offline machine learning. This solves the problem of frequent repairs and extremely high maintenance costs of downstream machine learning applications caused by inconsistent measurement points of equipment from different manufacturers in the new energy field and changes in measurement points after equipment technical transformation. It also avoids the frequent start and stop of real-time algorithm models, ensures the synchronization of the change rhythm of cluster nodes, and achieves the effect of global consistency in model result output. The solution of the present invention is built on FLINK, which itself has a highly available and scalable architecture and can support the analysis and processing of massive data.

[0069] Exemplarily, the method of the present invention can be used in wind farm equipment monitoring and fault warning, as well as solar power station data collection and intelligent optimization. 1) Due to the wide variety of equipment, different models and the non-uniform coding of equipment data measurement points provided by different manufacturers, traditional data analysis and monitoring systems need to be frequently adjusted, and the operation and maintenance costs are high. By adopting the technical solution of the present invention, wind farms can realize unified modeling and mapping management of equipment data measurement points, seamlessly update the algorithm model through the hot loading mechanism when the equipment undergoes technical changes or repairs, avoid system downtime, and use real-time data stream processing to monitor and warn the equipment operation status, greatly improving the operation and maintenance efficiency and reducing the failure rate. 2) Due to the long-term operation of solar power stations, not only the measurement points of some equipment have changed, but also performance optimization is required. The present invention uses the FLINK stream processing framework, combined with the self-developed SDK to realize unified reading and parsing of equipment data, and adaptively adjusts the algorithm model through the measurement point mapping relationship to achieve non-stop updates. In the actual application of solar power stations, the present invention can monitor the equipment operation status in real time, adjust the power generation strategy in time, and improve energy utilization efficiency. In addition, the present invention can also be applied to other industrial scenarios that need to process large amounts of real-time data and have high requirements for system availability, such as smart grids, Industrial Internet of Things (IIoT) and other fields. The technical solution of the present invention can achieve efficient data collection, processing and analysis, and improve the stability and intelligence level of the system.

[0070] The technical solution of this embodiment can integrate and map the types and measurement point data of the equipment in the power plant, put them under a unified node measurement method, process the standardized and unified target detection information, obtain the equipment diagnosis results of the power plant, and map different data in a unified reference vector through the mapping method of data stream, that is, directly map the changed upstream information to the pre-set reference vector, without stopping the downstream application, so that the change rhythm of the cluster nodes is synchronized, reduce the modification and adaptation difficulty and downtime of downstream machine learning applications in the new energy field, reduce the equipment maintenance cost of new energy power plants, and improve the real-time performance of equipment detection and operation and maintenance. It solves the problem that downstream big data and artificial intelligence services need to frequently shut down and adjust services according to the changes in upstream equipment point data. The downtime will cause the equipment monitoring business to be suspended. Once the downstream service cannot respond to the upstream data changes in time, it will cause deviations in the monitoring and analysis of the equipment data, and then make wrong decision-making guidance for production and operation and maintenance.

[0071] Figure 4 Schematic diagram of the structure of a management device for a new energy power plant provided by the present invention. Figure 4 As shown, the device includes: an acquisition module 201, a determination module 202 and a diagnosis module 203.

[0072] The acquisition module 201 is used to determine initial detection information of the power plant, where the initial detection information includes at least one initial type information and at least one initial detection data corresponding to the initial type information.

[0073] The determination module 202 is used to process at least one initial type information and at least one initial detection data corresponding to the initial type information using a preset information mapping rule to obtain target detection information, wherein the target detection information includes at least one target type information and target detection data corresponding to the target type information.

[0074] The diagnosis module 203 is used to determine a target fault diagnosis model of the power plant based on at least one target type information, and use the target fault diagnosis model to process target detection data corresponding to at least one target type information to obtain a fault diagnosis result of the power plant.

[0075] Optionally, acquisition module 201 is specifically used to determine historical data measurement points and newly added data measurement points of the power plant; based on historical data measurement points, detection rules of historical data measurement points, newly added data measurement points and detection rules of newly added data measurement points, determine at least one initial type information and initial detection data corresponding to at least one initial type information.

[0076] Optionally, the information mapping rules include type mapping rules and data adjustment rules, and the determination module 202 is specifically used to use the information mapping rules to process at least one initial type information to obtain at least one target type information, wherein the target type information and the initial type information correspond one-to-one, or the target type information corresponds to at least one initial type information; use the data adjustment rules to process the initial detection data corresponding to the at least one initial type information to obtain intermediate detection data; determine the type information of the intermediate detection data, and based on the correspondence between the type information of the intermediate detection data and the target type information, determine the target detection data corresponding to each target type information.

[0077] Optionally, the diagnosis module 203 is specifically used to search in the correspondence between type information and the diagnosis model based on at least one target type information to obtain a candidate fault diagnosis model; determine whether there is an update indication for the candidate fault diagnosis model; if there is no update indication for the candidate fault diagnosis model, determine that the candidate fault diagnosis model is the target fault diagnosis model; if there is an update indication for the candidate fault diagnosis model, update the candidate fault diagnosis model based on the update indication, and determine that the updated candidate fault diagnosis model is the target fault diagnosis model.

[0078] Optionally, the diagnostic module 203 is further used to process at least one initial type information and at least one initial detection data corresponding to the initial type information using a pre-set information mapping rule, and after obtaining the target detection information, process the target detection information according to a pre-set data processing scheme to obtain offline detection information, wherein the data processing scheme includes a data integration scheme and a data storage scheme; when receiving an offline data analysis instruction, process the offline detection information based on the data processing requirements in the offline data analysis instruction to obtain an offline data processing result, and the offline data processing result is used to indicate the equipment adjustment plan and / or equipment operation status of the power plant.

[0079] Optionally, the diagnostic module 203 is also used to determine whether there is any abnormal operation indication in the fault diagnosis result after obtaining the fault diagnosis result of the power plant; if there is no abnormal operation indication in the fault diagnosis result, generate equipment control parameters, and control the equipment in the power plant to operate based on the equipment control parameters; if there is an abnormal operation indication in the fault diagnosis result, generate a fault adjustment report based on the fault diagnosis result, and display the fault adjustment report, wherein the fault adjustment report is used to indicate the equipment abnormality information and equipment adjustment plan of the power plant.

[0080] The management device for the new energy power plant provided in this embodiment can execute the management method for the new energy power plant provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0081] Figure 5 : is a schematic diagram of the structure of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0082] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (also called random access memory, RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0083] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a management method for a new energy power plant.

[0085] In some embodiments, the management method of the renewable energy power plant may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the management method of the renewable energy power plant described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the management method of the renewable energy power plant by any other appropriate means (e.g., by means of firmware).

[0086] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0088] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server) or a computing system that includes middleware components (e.g., an application server) or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein) or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0091] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0092] In one embodiment, the present invention further includes a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the management method of the new energy power plant of any embodiment of the present invention is implemented.

[0093] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0094] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0095] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A management method for a new energy power plant, characterized in that: include: Determining initial detection information of the power plant, wherein the initial detection information includes at least one initial type information and initial detection data corresponding to the at least one initial type information; Using a preset information mapping rule, the at least one initial type information and the initial detection data corresponding to the at least one initial type information are processed to obtain target detection information, wherein the target detection information includes at least one target type information and the target detection data corresponding to the target type information; Based on the at least one target type information, a target fault diagnosis model of the power plant is determined, and the target fault diagnosis model is used to process the target detection data corresponding to the at least one target type information to obtain a fault diagnosis result of the power plant.

2. The method according to claim 1, characterized in that The determining of initial detection information of the power plant includes: Determine historical data measurement points and newly added data measurement points of the power plant; Based on the historical data measurement points, the detection rules of the historical data measurement points, the newly added data measurement points and the detection rules of the newly added data measurement points, the at least one initial type information and the initial detection data corresponding to the at least one initial type information are determined.

3. The method according to claim 1, characterized in that The information mapping rule includes a type mapping rule and a data adjustment rule, and the at least one initial type information and the initial detection data corresponding to the at least one initial type information are processed by using the preset information mapping rule to obtain the target detection information, including: Processing the at least one initial type information by using the information mapping rule to obtain the at least one target type information, wherein the target type information corresponds to the initial type information one-to-one, or the target type information corresponds to at least one initial type information; Using the data adjustment rule, processing the initial detection data corresponding to the at least one initial type information to obtain intermediate detection data; The type information of the intermediate detection data is determined, and based on the correspondence between the type information of the intermediate detection data and the target type information, the target detection data corresponding to each target type information is determined.

4. The method according to claim 1, characterized in that: The step of determining a target fault diagnosis model of the power plant based on the at least one target type information comprises: Based on the at least one target type information, searching in the correspondence between the type information and the diagnosis model to obtain a candidate fault diagnosis model; Determining whether there is an update indication for the candidate fault diagnosis model; If the candidate fault diagnosis model does not have the update instruction, determining the candidate fault diagnosis model as the target fault diagnosis model; If the candidate fault diagnosis model has the update indication, the candidate fault diagnosis model is updated based on the update indication, and the updated candidate fault diagnosis model is determined to be the target fault diagnosis model.

5. The method according to claim 1, characterized in that After the at least one initial type information and the initial detection data corresponding to the at least one initial type information are processed by using the preset information mapping rule to obtain the target detection information, the method further includes: Processing the target detection information according to a pre-set data processing scheme to obtain offline detection information, wherein the data processing scheme includes a data integration scheme and a data storage scheme; When an offline data analysis instruction is received, the offline detection information is processed based on the data processing requirements in the offline data analysis instruction to obtain an offline data processing result, wherein the offline data processing result is used to indicate the equipment adjustment plan and / or equipment operation status of the power plant.

6. The method according to claim 1, characterized in that After obtaining the fault diagnosis result of the power plant, the method further includes: Determining whether the fault diagnosis result indicates abnormal operation; If the fault diagnosis result does not include the abnormal operation indication, generating a device control parameter, and controlling the devices in the power plant to operate based on the device control parameter; If the fault diagnosis result contains the abnormal operation indication, a fault adjustment report is generated based on the fault diagnosis result and displayed, wherein the fault adjustment report is used to indicate the equipment abnormality information and equipment adjustment plan of the power plant.

7. A management device for a new energy power plant, characterized in that: A method for managing a new energy power plant according to any one of claims 1 to 6, wherein the management device for the new energy power plant comprises: An acquisition module, used to determine initial detection information of the power plant, wherein the initial detection information includes at least one initial type information and initial detection data corresponding to the at least one initial type information; a determination module, configured to process the at least one initial type information and the initial detection data corresponding to the at least one initial type information by using a preset information mapping rule to obtain target detection information, wherein the target detection information includes at least one target type information and the target detection data corresponding to the target type information; A diagnostic module is used to determine a target fault diagnosis model of the power plant based on the at least one target type information, and use the target fault diagnosis model to process target detection data corresponding to the at least one target type information to obtain a fault diagnosis result of the power plant.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the management method of the new energy power plant described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the management method of a new energy power plant as described in any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the management method of the new energy power plant according to any one of claims 1 to 6.

Images