New energy production early warning method and system based on multi-scale meteorological coupling

Abstract

The present application relates to the field of new energy production safety early warning, and specifically relates to a new energy production early warning method and system based on multi-scale meteorological coupling, comprising: obtaining equipment operation data and meteorological parameter data of different meteorological dimensions; constructing meteorological fault correlation strength based on the meteorological parameter data, thereby screening out key meteorological dimensions; calculating meteorological sensitivity coefficients and forming meteorological coupling characteristic values based on the key meteorological dimensions, and then analyzing real-time working conditions of new energy equipment operation and power grid dispatching states, calculating dynamic safety thresholds, generating device-level early warning information, and outputting early warning results. The present application can improve the accuracy, adaptability and engineering usability of new energy equipment production safety early warning under complex meteorological scenarios.

Description

Technical Field

[0001] This invention relates to the field of early warning for safety in new energy production, specifically to a method and system for early warning of new energy production based on multi-scale meteorological coupling. Background Technology

[0002] With the continuous growth of installed capacity of new energy sources such as wind power, photovoltaics, and energy storage, new energy power plants are gradually showing a development trend of clustering, distribution, and coexistence in complex terrain, significantly increasing the uncertainties in the equipment operating environment. Compared with traditional fixed-condition equipment, the operating status of new energy equipment is not only affected by the equipment's own health and real-time operating conditions, but also continuously affected by external meteorological factors such as wind speed, temperature, humidity, irradiance, and convective weather. In recent years, with the collaborative construction of national meteorological data platforms, regional radar observation systems, micro-meteorological stations, SCADA systems, asset management systems, and GIS systems, the accuracy of meteorological data, equipment operation data, and environmental data acquisition has been continuously improved. Existing technologies are also beginning to combine multi-source meteorological inputs with equipment operation monitoring results for the analysis and early warning of operational risks of new energy equipment.

[0003] However, most existing meteorological early warning schemes for new energy equipment still rely on unified models or fixed safety thresholds for judgment, making it difficult to distinguish the different responses of different equipment to meteorological effects at different scales, and also difficult to express large-scale trends, mesoscale processes, and small-scale disturbances in a unified framework. Especially in scenarios where changes in equipment health status, real-time operating condition switching, and grid dispatch constraints coexist, fixed thresholds or simple experience-based correction methods often fail to accurately reflect the current true risk level of the equipment, easily leading to overly coarse early warning results and a coexistence of false alarms and missed alarms. Summary of the Invention

[0004] This invention provides a method and system for early warning of new energy production based on multi-scale meteorological coupling, in order to solve the problems that existing early warning schemes for new energy equipment are difficult to distinguish the differentiated meteorological responses of equipment, difficult to uniformly express the effects of multi-scale meteorology and dynamically adjust the safety threshold accordingly.

[0005] The new energy production early warning method based on multi-scale meteorological coupling of the present invention adopts the following technical solution: Includes the following steps: Acquire operational data from various equipment and meteorological parameters across different meteorological dimensions; Based on meteorological parameter data of new energy equipment before and after historical failures, the correlation strength between different meteorological dimensions and failures is analyzed to obtain the meteorological failure correlation strength of different meteorological dimensions; based on the meteorological failure correlation strength, several key meteorological dimensions are selected from all meteorological dimensions. Based on the changes in key meteorological dimensions in equipment operation data and meteorological parameter data, the response relationship between key meteorological dimensions and equipment operation and meteorological parameters is analyzed to obtain several meteorological sensitivity coefficients for different key meteorological dimensions. Based on the meteorological sensitivity coefficients, the meteorological parameter data of key meteorological dimensions are weighted to obtain meteorological coupling characteristic values ​​for different key meteorological dimensions. Based on the meteorological coupling characteristic values ​​and meteorological sensitivity coefficients, the real-time operating conditions of new energy equipment and the grid dispatch status are analyzed, and the initial safety threshold is dynamically adjusted to obtain the dynamic safety threshold for different key meteorological dimensions. Based on dynamic safety thresholds, the system generates tiered early warning information for different devices and outputs the warning results.

[0006] Preferably, the method for obtaining the meteorological fault correlation strength is as follows: All new energy equipment is divided into several new energy functional equipment types according to equipment function type and energy conversion method; based on the meteorological parameter data of each equipment type, a multidimensional meteorological data sequence within a preset time window is obtained with the fault occurrence time as the benchmark; the deviation and change of the multidimensional meteorological data sequence within the preset time window compared with the historical benchmark state are analyzed, and the meteorological fault correlation strength between each meteorological dimension and the fault is calculated.

[0007] Preferably, the method for obtaining the multidimensional meteorological data sequence is as follows: A time window value is preset, and the time range with the fault occurrence time as the starting point and the duration as the time window value is taken as the effective fault period; the sequence of meteorological parameter data of each meteorological dimension within the effective fault period is taken as the multidimensional meteorological data sequence of each meteorological dimension.

[0008] Preferably, the method for obtaining the key meteorological dimensions is as follows: The correlation strength of meteorological faults is compared with the preset meteorological correlation threshold, and meteorological dimensions whose correlation strength meets the threshold condition are retained as key meteorological dimensions.

[0009] Preferably, the method for obtaining the meteorological sensitivity coefficient is as follows: For any key meteorological dimension, based on the changes in meteorological parameter data and equipment operation data at different scales, the ratio of equipment operation status to meteorological status in terms of status change is compared to analyze the response intensity of different new energy equipment to the key meteorological dimension, and several meteorological sensitivity coefficients of the key meteorological dimension are calculated.

[0010] Preferably, the method for obtaining the meteorological coupling feature value is as follows: For any key meteorological dimension, the different meteorological sensitivity coefficients of the key meteorological dimension are standardized to obtain several scale weights; the meteorological parameter data of the key meteorological dimension are weighted and fused according to the scale weights, and the weighted fusion result is used as the meteorological coupling feature value of the key meteorological dimension.

[0011] Preferably, the method for obtaining the scale weights is as follows: The meteorological sensitivity coefficients of key meteorological dimensions and other key meteorological dimensions are standardized, and the standardized meteorological sensitivity coefficients are used as scale weights.

[0012] Preferably, the method for obtaining the dynamic security threshold is as follows: The baseline threshold for each key meteorological dimension is determined based on the meteorological coupling feature value. The meteorological coupling feature value of each key meteorological dimension is combined with the meteorological sensitivity coefficient to construct the correction factor for each key meteorological dimension. The baseline threshold of each key meteorological dimension is directionally corrected by the correction factor to obtain the dynamic safety threshold for each key meteorological dimension.

[0013] Preferably, the method for obtaining the correction factor is as follows: The product of the meteorological coupling feature value and the meteorological sensitivity coefficient of each key meteorological dimension is used as the correction factor for each key meteorological dimension.

[0014] The present invention also proposes a new energy production early warning system based on multi-scale meteorological coupling, including a memory and a processor. The processor executes a computer program stored in the memory to implement the steps of the above-mentioned new energy production early warning method based on multi-scale meteorological coupling.

[0015] The beneficial effects of the technical solution of this invention are as follows: by first constructing the meteorological fault correlation strength and further calculating the meteorological sensitivity coefficient, it is possible to distinguish the actual response differences of different new energy equipment to different meteorological factors, avoiding the existing solution of placing different equipment under a unified model for coarse-grained judgment; by adaptively coupling multi-scale meteorological data based on the meteorological sensitivity coefficient, it is possible to uniformly transform interference of different scales into meteorological coupling feature values ​​that are more consistent with the actual affected state of the equipment; by combining equipment health, real-time operating conditions and power grid dispatch status to dynamically adjust the safety threshold and generate equipment-specific graded early warning information, it is possible to improve the accuracy, adaptability and engineering usability of new energy production safety early warning in complex meteorological scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the steps of the new energy production early warning method based on multi-scale meteorological coupling of the present invention. Detailed Implementation

[0018] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the new energy production early warning method and system based on multi-scale meteorological coupling proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0020] The following description, in conjunction with the accompanying drawings, details the specific scheme of the new energy production early warning method and system based on multi-scale meteorological coupling provided by this invention.

[0021] Please see Figure 1 The diagram illustrates a flowchart of a new energy production early warning method based on multi-scale meteorological coupling provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain operational data of several devices and meteorological parameter data from different meteorological dimensions.

[0022] It should be noted that early warning for the production safety of new energy equipment is not based on a single meteorological value or a single equipment status value, but rather needs to consider the combined effects of meteorological changes and equipment differences. Therefore, before proceeding with correlation analysis and risk assessment, it is essential to first generate relevant data that covers the full scale of meteorological impacts and equipment operating status, namely, equipment operating data and meteorological parameter data.

[0023] In one specific implementation of this invention, the method for obtaining equipment operation data and meteorological parameter data is as follows: Preset an early warning period duration The duration before the current moment is Within a given timeframe, several large-scale meteorological parameter data points are acquired from the database of the National Meteorological Science Data Center; several mesoscale meteorological parameter data points are acquired from the database of regional weather radars; and several small-scale meteorological parameter data points are acquired from the database of dedicated sensors at weather stations. This embodiment uses... This example will be used to illustrate the concept of "day," and this embodiment is not specifically limited to any particular instance. It depends on the specific implementation situation.

[0024] It should be noted that in this embodiment, large-scale meteorological dimensions are described using air temperature and wind speed as examples, with a sampling frequency of 1 time per hour; mesoscale meteorological dimensions are described using convective echoes and precipitation as examples, with a sampling frequency of 0.1 times per minute; and small-scale meteorological dimensions are described using photovoltaic module backsheet temperature and energy storage container temperature and humidity as examples, with a sampling frequency of 1 time per minute. The meteorological dimensions at different scales can be adjusted according to specific implementation conditions, and this embodiment does not impose specific limitations. Furthermore, in this embodiment, "meteorological dimension" will be used to refer to the large-scale, mesoscale, and small-scale meteorological dimensions collectively. Further, the duration before the current time is... Within a given timeframe, operational data for several new energy devices under each meteorological dimension are obtained from the new energy equipment database.

[0025] It should be noted that this embodiment describes the new energy equipment using 3 wind turbines and 3 photovoltaic panels as examples, and the equipment operation data is described using current as an example, with a collection frequency of 1 time / minute as an example. The above-mentioned new energy equipment and equipment operation data can be adjusted according to specific implementation conditions, and this embodiment does not impose specific limitations. In addition, the meteorological parameter data retains a fault occurrence time marker in the database.

[0026] It should be further noted that, by default, all meteorological parameter data and equipment operation data for all meteorological dimensions in this embodiment are standardized meteorological parameter data, i.e., all have a dimension of 1.

[0027] Thus, the above methods have yielded several equipment operation data and meteorological parameter data for different meteorological dimensions.

[0028] Step S002: Based on meteorological parameter data of new energy equipment before and after historical failures, analyze the correlation strength between different meteorological dimensions and failures to obtain the meteorological failure correlation strength of different meteorological dimensions; based on the meteorological failure correlation strength, select several key meteorological dimensions from all meteorological dimensions.

[0029] It is important to note that, within the context of new energy production safety, analyzing the relationship between different meteorological dimensions and faults, and selecting those with clear correlations, is a core component in building a precise risk early warning and proactive defense system. This stems primarily from the fact that wind turbines, photovoltaic arrays, and power transmission and transformation equipment are exposed to complex atmospheric environments for extended periods. Their faults are often the result of the coupled effects of multiple meteorological factors: low temperatures and high humidity induce blade icing, strong gusts and turbulence cause tower fatigue and unit overspeed, thunderstorms trigger lightning trips, and high temperatures and drastic changes in irradiance can easily cause inverter overheating, hot spots, and support deformation. A single meteorological factor cannot reveal the hidden conditions and critical thresholds that lead to faults; a systematic consideration of the synergistic effects of wind speed, irradiance, temperature, humidity, air pressure, and thunderstorms is necessary to accurately characterize the disaster-causing mechanisms. Building upon this foundation, focusing on clearly correlated meteorological dimensions has multiple implications: First, it effectively eliminates redundant variables, reduces the complexity of prediction models, significantly improves the accuracy and timeliness of fault forecasts, avoids false alarms and missed alarms caused by irrelevant noise, and effectively ensures the safety of personnel and equipment. Second, strongly correlated factors can be directly transformed into clear and actionable prevention and control criteria. For example, when instantaneous wind speed and turbulence intensity exceed thresholds, proactive power limiting or shutdown can be implemented; when irradiance increases and ambient temperature rises sharply, infrared inspections can be intensified, thereby promoting a shift in operation and maintenance from passive emergency repairs to proactive defense. Third, prioritizing high-impact meteorological elements can optimize sensor deployment and data analysis resource allocation, achieving maximum safety benefits with minimal monitoring costs. Ultimately, through this targeted correlation analysis between meteorology and faults, new energy power plants can reduce the risk of severe accidents such as blade breakage, tower collapse, and large-scale grid disconnection from the source in the face of frequent extreme weather events, achieving a dynamic balance between safe production and operational efficiency.

[0030] Preferably, in some implementations of the present invention, the method for obtaining the meteorological fault correlation strength is as follows: All new energy devices are divided into several new energy functional device types according to their function type and energy conversion method; based on the meteorological parameter data of each device type, a multi-dimensional meteorological data sequence within a preset time window is obtained, with the fault occurrence time as the benchmark; the deviation and change amplitude of the multi-dimensional meteorological data sequence within the preset time window compared to the historical benchmark state are analyzed, and the meteorological fault correlation strength between each meteorological dimension and the fault is calculated. The specific process is as follows: Preferably, in some implementations of the present invention, the method for obtaining multidimensional meteorological data sequences is as follows: a time window value is preset, and the time range with the fault occurrence time as the starting point and the duration as the time window value is taken as the effective fault period; the sequence of meteorological parameter data of each meteorological dimension within the effective fault period is taken as the multidimensional meteorological data sequence of each meteorological dimension. The specific process is as follows: New energy equipment of type wind turbine is classified as one type of new energy functional equipment, and new energy equipment of type photovoltaic panel is classified as another type of new energy equipment; a time window is preset. Taking the time of the fault occurrence as the starting point, the duration is... The time range is taken as the effective fault period; the sequence of meteorological parameter data for each meteorological dimension within the effective fault period is taken as the multidimensional meteorological data sequence for each meteorological dimension. In this embodiment, [the following is used as an example]. This example uses minutes as an example; no specific limitations are set in this embodiment. It depends on the specific implementation situation.

[0031] Furthermore, as an example, the correlation strength of meteorological faults can be calculated using the following formula:

[0032] in, Indicates the first The correlation strength between meteorological dimensions and faults; Indicates the first The number of meteorological parameter data within a multidimensional meteorological data sequence of each meteorological dimension; Indicates the first Within a multidimensional meteorological data sequence of meteorological dimensions, the first... Meteorological parameter data; Indicates the first The mean of all meteorological parameter data within a multidimensional meteorological data sequence of a meteorological dimension; Indicates taking the absolute value; This represents the normalization function.

[0033] It should be noted that key meteorological dimensions are used to further filter out the core meteorological dimensions that need to be included in subsequent sensitivity quantification and coupled modeling from the fault meteorological association dataset. Without this layer of filtering, the meteorological factors that truly play a major role in different equipment under different fault types will be mixed with general background meteorological factors, affecting the accuracy of subsequent modeling.

[0034] Preferably, in some implementations of the present invention, the method for obtaining key meteorological dimensions is as follows: comparing the correlation strength of meteorological faults with a preset meteorological correlation threshold, and retaining the meteorological dimensions whose correlation strength meets the threshold condition as key meteorological dimensions. The specific process is as follows: Taking any meteorological dimension as an example, a preset meteorological correlation threshold is set. If the correlation strength of meteorological faults in this meteorological dimension Greater than Therefore, this meteorological dimension is used as the key meteorological dimension, and all key meteorological dimensions are obtained. In this embodiment, [the following is used as an example]. This example is used for illustration; no specific limitations are set in this embodiment. It depends on the specific implementation situation.

[0035] Thus, several key meteorological dimensions have been obtained through the above methods.

[0036] Step S003: Based on the changes in key meteorological dimensions in equipment operation data and meteorological parameter data, analyze the response relationship between key meteorological dimensions and equipment operation and meteorological parameters to obtain several meteorological sensitivity coefficients for different key meteorological dimensions; based on the meteorological sensitivity coefficients, assign weights to the meteorological parameter data of key meteorological dimensions to obtain meteorological coupling characteristic values ​​for different key meteorological dimensions; based on the meteorological coupling characteristic values ​​and meteorological sensitivity coefficients, analyze the real-time operating conditions of new energy equipment and the grid dispatch status, dynamically adjust the initial safety threshold, and obtain dynamic safety thresholds for different key meteorological dimensions.

[0037] It should be noted that analyzing the changes in equipment operating parameters with meteorological parameters based on the selected key meteorological dimensions is to quantify the equipment's response sensitivity to different meteorological stresses. The resulting meteorological sensitivity coefficient reveals which dimensions are the main triggers for anomalies. For example, a slight increase in wind speed can cause a sharp increase in unit vibration, while the effect of temperature on insulation may be relatively mild, thus accurately characterizing the intrinsic disaster-causing properties of a single factor. Subsequently, using the sensitivity coefficient as a weight, real-time meteorological parameters are weighted and fused to generate meteorological coupling feature values. Essentially, this combines multiple independent meteorological stresses according to their disaster-causing effects into a comprehensive risk intensity index. This reflects the actual stress level of the site environment caused by multiple concurrent and overlapping factors, avoiding distortion caused by simple superposition. Based on this, the meteorological coupling characteristic value and sensitivity coefficients of various dimensions are linked to the real-time operating conditions of equipment and the grid dispatch status. This is because the same comprehensive meteorological risk has drastically different accident thresholds under different load levels and dispatch requirements: under high load or peak-shaving constraints, the equipment thermal margin decreases, and dispatch cannot arbitrarily reduce the rate. At this time, even a relatively low meteorological coupling stress may approach the safety red line; while under low load and with adjustment space, a higher stress can be accommodated. Therefore, the dynamic safety threshold is not a fixed constant, but a flexible boundary calculated in real time based on the current equipment capacity and system requirements, combined with the "meteorological disaster-causing effect" and "equipment vulnerability". This process ultimately allows the safety defense line to elastically expand and contract with wind speed, irradiance, and grid demand, maximizing power generation revenue while ensuring that the safety bottom line is not exceeded, and achieving a dynamic balance between safe production and grid support capacity.

[0038] Preferably, in some implementations of the present invention, the method for obtaining the meteorological sensitivity coefficient is as follows: For any key meteorological dimension, based on the changes in meteorological parameter data and equipment operation data at different scales, the ratio of equipment operation status to meteorological status in terms of state change is compared to analyze the response intensity of different new energy equipment to the key meteorological dimension, and several meteorological sensitivity coefficients of the key meteorological dimension are calculated. The specific process is as follows: Taking any one key meteorological dimension as the target key meteorological dimension and the other key meteorological dimensions as reference key meteorological dimensions, as an example, the meteorological sensitivity coefficient between the target key meteorological dimension and other reference key meteorological dimensions can be calculated using the following formula:

[0039] in, Indicates the key meteorological dimensions of the target and the first Meteorological sensitivity coefficients for key meteorological dimensions; Indicates the first The average change of equipment operation data for each key meteorological reference dimension during the effective fault period; This represents the average value of equipment operation data for the key meteorological dimensions of the target during the effective fault period. Indicates the first The average value of equipment operation data for each key meteorological reference dimension during the effective fault period; Indicates the first The average change of meteorological parameter data for each key meteorological dimension during the effective period of the fault; This represents the mean value of meteorological parameter data for the key meteorological dimensions of the target during the effective period of the fault. Indicates the first The mean of meteorological parameter data for each key reference meteorological dimension during the effective period of the fault.

[0040] Preferably, in some implementations of the present invention, the method for obtaining meteorological coupling feature values ​​is as follows: for any key meteorological dimension, the different meteorological sensitivity coefficients of the key meteorological dimension are standardized to obtain several scale weights; the meteorological parameter data of the key meteorological dimension are weighted and fused according to the scale weights, and the weighted fusion result is used as the meteorological coupling feature value of the key meteorological dimension. The specific process is as follows: Preferably, in some implementations of the present invention, the method for obtaining the scale weights is as follows: The meteorological sensitivity coefficients of key meteorological dimensions and other key meteorological dimensions are standardized, and the standardized meteorological sensitivity coefficients are used as the scale weights. The specific process is as follows: Obtain the meteorological sensitivity coefficients of the target key meteorological dimension and each reference key meteorological dimension, normalize all meteorological sensitivity coefficients, and use each normalized meteorological sensitivity coefficient as a scale weight.

[0041] Furthermore, the mean of all meteorological parameter data of the target key meteorological dimension is taken as the first mean of the target key meteorological dimension; the mean of all scale weights of the target key meteorological dimension is taken as the second mean; and the product of the first mean and the second mean is taken as the meteorological coupling feature value of the target key meteorological dimension.

[0042] It should be noted that this embodiment defaults to... Normalization is performed on the function as an example, and the implementer can choose the normalization function according to the actual situation.

[0043] Preferably, in some implementations of the present invention, the method for obtaining the dynamic safety threshold is as follows: a baseline threshold for each key meteorological dimension is determined based on meteorological coupling feature values; a correction factor for each key meteorological dimension is constructed by combining the meteorological coupling feature values ​​of each key meteorological dimension with the meteorological sensitivity coefficient; and the baseline threshold for each key meteorological dimension is directionally corrected using the correction factor to obtain the dynamic safety threshold for each key meteorological dimension. The specific process is as follows: Preferably, in some implementations of the present invention, the correction factor is obtained by multiplying the meteorological coupling feature value of each key meteorological dimension by the meteorological sensitivity coefficient, and using the product as the correction factor for each key meteorological dimension. The specific process is as follows: The normalized values ​​of the meteorological coupling feature values ​​of the key meteorological dimensions of the target are used as the baseline thresholds for the key meteorological dimensions of the target; the product of the meteorological coupling feature values ​​of the key meteorological dimensions of the target and the meteorological sensitivity coefficient is used as the correction factor for the key meteorological dimensions of the target.

[0044] Furthermore, the normalized value of the product between the baseline threshold and the correction factor is used as the dynamic safety threshold for the target key meteorological dimensions; the dynamic safety threshold for each key meteorological dimension is obtained.

[0045] Thus, the dynamic safety thresholds for different key meteorological dimensions were obtained using the methods described above.

[0046] Step S004: Based on the dynamic safety threshold, generate device-specific and graded early warning information and output the early warning results.

[0047] In one specific implementation of this invention, the process of obtaining the early warning result is as follows: three pre-defined hierarchical intervals are used. , , If the dynamic safety threshold of the target's key meteorological dimensions is within Within this range, the warning level is Level 1, indicating minimal risk to the operation of new energy equipment; if the dynamic safety threshold of the target's key meteorological dimensions is within... Within this area, the warning level is Level 2, indicating that the operational risks of new energy equipment are relatively significant and require close monitoring; if the dynamic safety thresholds of key meteorological dimensions of the target are within... Within this context, the warning level is Level 3, indicating that the operation of new energy equipment faces the greatest risk and requires shutdown for maintenance. This embodiment uses... , , , This example is used for illustration; no specific limitations are set in this embodiment. , , , It depends on the specific implementation situation.

[0048] This concludes the embodiment.

[0049] Another embodiment of the present invention provides a new energy production early warning system based on multi-scale meteorological coupling. The system includes a memory and a processor. When the processor executes the computer program stored in the memory, it performs the above method steps S001 to S004.

[0050] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A new energy production early warning method based on multi-scale meteorological coupling, characterized in that, The method includes the following steps: Acquire operational data from various equipment and meteorological parameters across different meteorological dimensions; Based on meteorological parameter data of new energy equipment before and after historical failures, the correlation strength between different meteorological dimensions and failures is analyzed to obtain the meteorological failure correlation strength of different meteorological dimensions; based on the meteorological failure correlation strength, several key meteorological dimensions are selected from all meteorological dimensions. Based on the changes in key meteorological dimensions in equipment operation data and meteorological parameter data, the response relationship between key meteorological dimensions and equipment operation and meteorological parameters is analyzed to obtain several meteorological sensitivity coefficients for different key meteorological dimensions. Based on the meteorological sensitivity coefficients, the meteorological parameter data of key meteorological dimensions are weighted to obtain meteorological coupling characteristic values ​​for different key meteorological dimensions. Based on the meteorological coupling characteristic values ​​and meteorological sensitivity coefficients, the real-time operating conditions of new energy equipment and the grid dispatch status are analyzed, and the initial safety threshold is dynamically adjusted to obtain the dynamic safety threshold for different key meteorological dimensions. Based on dynamic safety thresholds, the system generates tiered early warning information for different devices and outputs the warning results.

2. The new energy production early warning method based on multi-scale meteorological coupling according to claim 1, characterized in that, The method for obtaining the correlation strength of the meteorological fault is as follows: All new energy equipment is divided into several new energy functional equipment types according to equipment function type and energy conversion method; based on the meteorological parameter data of each equipment type, a multi-dimensional meteorological data sequence within a preset time window is obtained with the fault occurrence time as the benchmark; The study analyzes the deviation and magnitude of change of multidimensional meteorological data series relative to historical baselines within a preset time window, and calculates the meteorological fault correlation strength between each meteorological dimension and the fault.

3. The new energy production early warning method based on multi-scale meteorological coupling according to claim 2, characterized in that, The method for obtaining the multidimensional meteorological data sequence is as follows: A time window value is preset, and the time range with the fault occurrence time as the starting point and the duration as the time window value is taken as the effective fault period; the sequence of meteorological parameter data of each meteorological dimension within the effective fault period is taken as the multidimensional meteorological data sequence of each meteorological dimension.

4. The new energy production early warning method based on multi-scale meteorological coupling according to claim 1, characterized in that, The method for obtaining the key meteorological dimensions is as follows: The correlation strength of meteorological faults is compared with the preset meteorological correlation threshold, and meteorological dimensions whose correlation strength meets the threshold condition are retained as key meteorological dimensions.

5. The new energy production early warning method based on multi-scale meteorological coupling according to claim 1, characterized in that, The method for obtaining the meteorological sensitivity coefficient is as follows: For any key meteorological dimension, based on the changes in meteorological parameter data and equipment operation data at different scales, the ratio of equipment operation status to meteorological status in terms of status change is compared to analyze the response intensity of different new energy equipment to the key meteorological dimension, and several meteorological sensitivity coefficients of the key meteorological dimension are calculated.

6. The new energy production early warning method based on multi-scale meteorological coupling according to claim 1, characterized in that, The method for obtaining the meteorological coupling feature value is as follows: For any key meteorological dimension, the different meteorological sensitivity coefficients of the key meteorological dimension are standardized to obtain several scale weights; the meteorological parameter data of the key meteorological dimension are weighted and fused according to the scale weights, and the weighted fusion result is used as the meteorological coupling feature value of the key meteorological dimension.

7. The new energy production early warning method based on multi-scale meteorological coupling according to claim 6, characterized in that, The method for obtaining the scale weights is as follows: The meteorological sensitivity coefficients of key meteorological dimensions and other key meteorological dimensions are standardized, and the standardized meteorological sensitivity coefficients are used as scale weights.

8. The new energy production early warning method based on multi-scale meteorological coupling according to claim 1, characterized in that, The method for obtaining the dynamic security threshold is as follows: The baseline threshold for each key meteorological dimension is determined based on the meteorological coupling feature value. The meteorological coupling feature value of each key meteorological dimension is combined with the meteorological sensitivity coefficient to construct the correction factor for each key meteorological dimension. The baseline threshold of each key meteorological dimension is directionally corrected by the correction factor to obtain the dynamic safety threshold for each key meteorological dimension.

9. The new energy production early warning method based on multi-scale meteorological coupling according to claim 8, characterized in that, The method for obtaining the correction factor is as follows: The product of the meteorological coupling feature value and the meteorological sensitivity coefficient of each key meteorological dimension is used as the correction factor for each key meteorological dimension.

10. A new energy production early warning system based on multi-scale meteorological coupling, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it implements the steps of the new energy production early warning method based on multi-scale meteorological coupling as described in any one of claims 1-9.

Images