Digital integrated planning platform and method for wind power plant

Abstract

The invention belongs to the field of wind power plant planning, and provides a digital integrated planning platform and method for a wind power plant. The wind power plant digital integrated planning platform comprises a wind resource intelligent analysis processing module which processes wind resource data in a set area item set by adopting a twice detection and evaluation mechanism, determines abnormal data and types thereof, and further performs matching interpolation and correction; the wind power plant macroscopic site selection module is used for carrying out wind power plant planning macroscopic optimization based on multiple maps and sensitive factors; the wind power plant equipment type selection and arrangement optimization module is used for carrying out type selection and arrangement optimization on wind power plant equipment to obtain a wind power plant equipment type selection and arrangement optimization scheme; and the wind power plant post-evaluation module is used for comparing the wind resource data in the operation stage with the wind resource data in the design stage after the wind power plant equipment type selection and optimization scheme arrangement are implemented so as to evaluate the operation state of the wind power plant, and early warning and matching are carried out on the abnormal state to generate corresponding solutions.

Description

Technical Field

[0001] The present invention belongs to the field of wind farm planning, and in particular relates to a wind farm digital integrated planning platform and method. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] A wind farm is a place where wind energy is captured, converted into electrical energy, and then fed into the power grid through transmission lines. The planning of a wind farm includes the site selection, unit selection and optimal layout, and wind farm evaluation.

[0004] The current wind farm planning has the following problems: (1) Each link in wind farm planning is an isolated link, which makes each link an isolated island and prevents information exchange between each link. As a result, the wind farm does not consider the dependencies between each link, sacrificing the potential for overall optimization and making it difficult to reduce costs and increase efficiency from a global perspective.

[0005] (2) After wind resource data is measured by the wind towers at each observation station, there may be problems with incomplete or inaccurate data in the measurement link and data transmission link. The existing technical methods match, interpolate and correct different abnormal problems, resulting in the wind resource data being unable to provide accurate data for the subsequent wind farm site selection.

[0006] (3) The existing macro-site selection of wind farm planning only considers the characteristics of wind resources and sensitive factors, but does not consider the impact of the wind farm's projected noise on the surrounding area. It cannot simultaneously meet the balance between the wind farm's projected noise and the total power generation.

[0007] (4) A complete post-evaluation indicator system has not been established, so the role of post-project evaluation has not been fully utilized, and the evaluation results cannot be effectively used for decision-making on subsequent projects and further improvement of wind farm operating conditions. Summary of the invention

[0008] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a digital integrated planning platform and method for wind farms, which can integrate intelligent analysis of wind resources, macro-site selection of wind farms, wind farm equipment selection and layout optimization, and post-evaluation data of wind farms on one platform, thereby improving the overall performance of wind farm planning.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: A first aspect of the present invention provides a wind farm digital integrated planning platform.

[0010] A wind farm digital integrated planning platform, comprising: The wind resource intelligent analysis and processing module is used to process the wind resource data in the set area project set using a two-step detection and evaluation mechanism, determine the abnormal data and its type, and then perform matching interpolation and correction to make the wind resource data meet the preset quality requirements; A wind farm macro-site selection module, which is used to retrieve wind resource data that meets the set quality requirements in the set area project set from the wind resource intelligent analysis and processing module, and then combine the geographical information matching the set area project set to perform macro-optimization of wind farm planning based on multiple maps and sensitive factors; A wind farm equipment selection and layout optimization module, which is used to select and optimize the wind farm equipment based on the wind farm planning macro-optimization result output by the wind farm macro-site selection module, and obtain a wind farm equipment selection and layout optimization plan; The wind farm post-evaluation module is used to compare the wind resource data in the operation phase after the implementation of the wind farm equipment selection and layout optimization plan with the wind resource data in the design phase, so as to evaluate the operation status of the wind farm, and to give early warnings for abnormal conditions and match and generate corresponding solutions.

[0011] As an implementation method, the wind resource intelligent analysis and processing module uses the set prior rules to perform a primary detection on the wind resource data in the retrieved project set and marks the abnormal data; uses the trained data evaluation model to perform a secondary quality evaluation on the marked abnormal data to determine the type of the abnormal data; matches, interpolates and corrects the wind resource data according to the type of the abnormal data until the interpolated and corrected wind resource data meets the preset quality requirements; As an implementation manner, the types of abnormal data include missing wind resource data of the same tower at different heights and missing wind direction and / or wind speed in the wind resource data of the target wind measurement tower.

[0012] As an implementation method, based on the wind resource data of the available height at the time of setting the target wind tower, the wind resource data at different heights at the current moment are interpolated on the same tower; based on the wind resource data of the adjacent wind towers, the wind direction and / or wind speed are interpolated on different towers; wherein the wind resource data at different heights interpolated on the same tower include wind speed data, wind direction data and temperature data.

[0013] As an implementation mode, in the wind farm equipment selection and layout optimization module, the process of selecting and optimizing the layout of wind farm equipment is as follows: Determine the matching wind turbine type according to the wind speed level and trust level requirements of the wind farm; The area within the preset wind farm boundary is gridded, and each grid vertex is set as a wind turbine site. Taking the maximum power generation of the wind farm as the optimization goal, the layout plan of wind turbines of a certain type is optimized to obtain a micro-site selection and layout plan; Under the micro-site selection and layout plan, the influence range of each unit is calculated and drawn based on the preset noise assessment model, and a noise cloud map is synthesized. The location of the unit that affects the sensitive area of ​​residents is adjusted based on the noise cloud map, and the protection distance of the sensitive area is reserved to obtain the revised micro-site selection and layout plan; Based on the revised micro-site selection and layout plan, with the wind farm boundary, the locations of each wind turbine, the sensitive area and the farthest distance from the booster station to the location as constraints, the site within the wind farm boundary with the lowest total cost is selected as the booster station site selection result; The substation site selection results and the revised micro-site selection and layout plan are associated with the map within the preset wind farm boundary to construct a wind farm site selection map. Based on the relevant information of the wind farm site selection map, the optimal results of wind farm roads and collector lines are determined with the goals of minimizing the total road construction cost and the minimum collector line engineering volume, and finally the optimization plan for wind farm equipment selection and layout is obtained.

[0014] As an implementation method, the process of calculating and drawing the influence range of each unit based on the preset noise assessment model is as follows: Discretize the ground near the wind turbine into a number of grids, divide the period to be evaluated into minute-level time periods, and obtain a first horizontal distance between the highest point of the wind turbine rotor and the ground projection point and a second horizontal distance between the lowest point of the wind turbine rotor and the ground projection point according to the azimuth of the sun in each minute-level time period, wherein the first distance and the second distance are both the horizontal distances between the ground projection point and the wind turbine; For any grid to be evaluated, determine whether it coincides with the projection direction at this time according to the direction of the center of the grid to be evaluated relative to the wind turbine rotor. If it coincides, determine whether the horizontal distance from the center of the grid to be evaluated to the wind turbine is between the second horizontal distance and the first horizontal distance. If so, determine that the grid to be evaluated is affected, add a minute-level period to the affected time, and continue to determine until the grid to be evaluated is not affected, so as to obtain the affected time period and / or cumulative affected time of each grid in the entire period to be evaluated, and then construct a noise cloud map.

[0015] As an implementation mode, in the wind farm post-evaluation module, the wind resource index is selected from wind speed and annual utilization hours, and the power generation index is selected from power generation and energy availability; When the ratio of the wind resource index in the design phase to the wind resource index in the operation phase is less than the first set warning value, a wind resource warning is issued, and a technical transformation strategy of relocating the machine site or increasing the tower height is generated to increase the wind speed value; When the ratio of the power generation index in the design phase to the power generation index in the operation phase is less than the second set warning value, a power generation warning is issued, and a technical transformation strategy for unit blade modification or model replacement is generated to increase the unit's power generation.

[0016] As an implementation mode, in the wind farm post-evaluation module, the computer unit capacity coefficient and the wind turbine unit availability are calculated, and when the unit capacity coefficient is less than the third set warning value, or when the wind turbine unit availability is less than the fourth set warning value, an abnormal unit operation state warning is issued; wherein the unit capacity coefficient is the ratio of the equivalent full-generation hours to the annual hours, and the wind turbine unit availability includes the time-based availability and the power generation-based availability; Time-based availability , A represents the number of downtime hours due to failure, and B represents the number of downtime hours caused by reasons other than the responsibility of the assessed object; Availability of power generation , The actual power generation during the statistical period, The lost power generation during the statistical period.

[0017] As an implementation mode, in the wind farm post-evaluation module, fault detection is performed on the wind turbine set according to a preset fault library and a pre-trained machine learning algorithm, and when a fault is detected, a fault alarm is issued and a technical improvement strategy for maintenance and parts replacement is generated.

[0018] A second aspect of the present invention provides a planning method based on the wind farm digital integrated planning platform as described above.

[0019] A planning method based on the wind farm digital integrated planning platform as described above comprises: A double detection and evaluation mechanism is used to process the wind resource data within the set of regional projects, identify abnormal data and its type, and then perform matching interpolation and correction to ensure that the wind resource data meets the preset quality requirements; Retrieve wind resource data that meets the set quality requirements from the set regional project set, and then combine it with the geographic information that matches the set regional project set to perform macro optimization of wind farm planning based on multiple maps and sensitive factors; Based on the macro optimization results of wind farm planning, the wind farm equipment is selected and arranged to obtain the wind farm equipment selection and arrangement optimization plan; The wind resource data in the operation phase after the implementation of the wind farm equipment selection and layout optimization plan is compared with the wind resource data in the design phase to evaluate the operating status of the wind farm, and to warn of abnormal conditions and generate corresponding solutions.

[0020] The beneficial effects of the present invention are: (1) The wind farm digital integrated planning platform of the present invention integrates a wind resource intelligent analysis and processing module, a wind farm macro-site selection module, a wind farm equipment selection and layout optimization module and a wind farm post-evaluation module. The platform integrates wind resource intelligent analysis, wind farm macro-site selection, wind farm equipment selection and layout optimization and wind farm post-evaluation data on one platform, thereby improving the overall performance of wind farm planning.

[0021] (2) The present invention uses a priori rule settings to perform a primary detection on wind resource data, and then uses a data evaluation model to perform a secondary quality evaluation on the initially marked abnormal data. The two-detection mechanism is used to timely discover and solve data quality problems, thereby improving the integrity, accuracy and credibility of the data, thereby improving the quality and reliability of the data.

[0022] (3) The present invention determines the corresponding wind turbine layout plan based on the wind resource map and geographic information of each wind farm candidate area, and then combines the total power generation and noise map of each wind farm candidate area. From the set of wind farm candidate areas whose maximum area of ​​the noise map does not exceed the set area threshold range, the wind farm candidate area with the largest total power generation is selected as the optimal wind farm area. The wind resource map, noise map and sensitive factors are comprehensively considered to perform macro-optimization of wind farm planning, thereby meeting the balance between the projected noise of the wind farm and the total power generation of the wind farm.

[0023] (4) The present invention proposes a complete post-evaluation indicator system and evaluation method, which comprehensively evaluates the operating status of wind turbines from three aspects: wind resources, power generation, and operating conditions. Problems are discovered, early warning information is generated, and technically feasible, economically reasonable, and practical solutions are proposed, which greatly improves the comprehensiveness and accuracy of wind farm evaluation.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0026] Picture 1 It is a structural schematic diagram of a wind farm digital integrated planning platform according to an embodiment of the present invention; Picture 2 is a schematic diagram of a macro optimization process of wind farm planning based on multiple graphs and sensitive factors according to an embodiment of the present invention; Picture 3 It is a schematic diagram of the process of optimizing the selection and layout of wind farm equipment according to an embodiment of the present invention; Picture 4 It is a flow chart of a planning method based on a wind farm digital integrated planning platform according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0028] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0029] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0030] Picture 1 Schematic diagram of the structure of a wind farm digital integrated planning platform according to an embodiment of the present invention. Picture 1 , a wind farm digital integrated planning platform according to an embodiment of the present invention comprises: The wind resource intelligent analysis and processing module 101 is used to process the wind resource data in the set area project set using a double detection and evaluation mechanism, determine the abnormal data and its type, and then perform matching interpolation and correction to make the wind resource data meet the preset quality requirements; A wind farm macro-site selection module 102, which is used to retrieve wind resource data that meets the set quality requirements in the set area project set from the wind resource intelligent analysis and processing module, and then combine the geographical information matching the set area project set to perform macro-optimization of wind farm planning based on multiple maps and sensitive factors; A wind farm equipment selection and layout optimization module 103, which is used to select and optimize the wind farm equipment based on the wind farm planning macro-optimization result output by the wind farm macro-site selection module, and obtain a wind farm equipment selection and layout optimization plan; The wind farm post-evaluation module 104 is used to compare the wind resource data in the operation phase after the implementation of the wind farm equipment selection and layout optimization plan with the wind resource data in the design phase to evaluate the wind farm operation status, and to issue early warnings for abnormal status and generate corresponding solutions.

[0031] Specifically, the wind resource intelligent analysis and processing module 101 uses the set prior rules to perform a primary detection on the wind resource data in the retrieved project set and marks the abnormal data; uses the trained data evaluation model to perform a secondary quality evaluation on the marked abnormal data to determine the type of the abnormal data; matches, interpolates and corrects the wind resource data according to the type of the abnormal data until the interpolated and corrected wind resource data meets the preset quality requirements; The types of abnormal data include missing wind resource data of the same tower at different heights and missing wind direction and / or wind speed in the wind resource data of the target wind measurement tower.

[0032] Specifically, based on the wind resource data of the available height at the target wind tower setting time, the wind resource data at different heights at the current time are interpolated on the same tower; based on the wind resource data of the adjacent wind towers, the wind direction and / or wind speed are interpolated on different towers; wherein the wind resource data at different heights interpolated on the same tower include wind speed data, wind direction data and temperature data.

[0033] The process of interpolating wind speed data at different heights on the same tower is as follows: Determine whether there is at least one valid wind speed at the target height at a certain moment. If so, calculate the average of these valid wind speeds as the wind speed value of the target height at that moment; If there is no effective wind speed at the target height at a certain moment, determine whether there is an effective wind speed other than the target height at that moment; When there are effective wind speeds at at least two heights other than the target height at that moment, the Pearson correlation coefficient between the target height and the channels with effective wind speeds at that moment is calculated respectively, and the effective wind speeds of a set number of channels with the highest correlation are selected for same-tower interpolation of the wind speed data of the target height at that moment; when interpolating at the same tower, the wind shear coefficient at that moment is calculated using the selected effective wind speed, and the wind shear profile is calculated based on the wind shear coefficient at that moment, thereby inferring the wind speed data of the target height at that moment; When there is an effective wind speed at a height other than the target height at that moment, the wind shear profile is calculated using the average wind shear coefficient observed in the known wind resource data set at similar times and dates in the day, and then the wind speed data at the target height at that moment is extrapolated.

[0034] In this way, the wind speed data at different heights at the current moment can be accurately interpolated, thus improving the integrity of the data.

[0035] In some specific implementations, the process of interpolating wind direction data / temperature data at different heights at the current moment on the same tower is as follows: Determine the amount of wind direction data / temperature data at the target height at a certain moment; When the number of wind direction data / temperature data at the target height at a certain moment is at least two, the average of these wind direction data / temperature data is calculated as the wind direction data / temperature data at the target height at that moment; When there is only one wind direction data / temperature data at the target height at a certain moment, the wind direction data / temperature data at the target height at that moment are inferred by using the average wind direction deflection / temperature gradient observed at similar times and days in a known wind resource data set.

[0036] In this way, the wind direction data / temperature data at different heights at the current moment can be accurately interpolated, thereby improving the integrity of the data.

[0037] In other embodiments, wind direction and / or wind speed are interpolated from different towers based on wind resource data from adjacent wind towers; Among them, the process of interpolating wind direction from different towers based on the wind resource data of adjacent wind towers is as follows: The neighboring wind tower is used as the reference wind tower, and the wind direction data of the target wind tower is divided into different sectors according to the wind direction data of the reference wind tower. The change from the reference wind direction to the target wind direction at each moment in each sector is calculated respectively, and the average offset of each sector is calculated. The interpolation value at the corresponding moment can be obtained by adding the average sector offset to the reference wind direction.

[0038] For example, when dividing sectors, you first need to specify the number of sectors to be divided, which is generally 16 sectors. When set to 16 sectors, 360° is evenly divided into 16 parts, and the span of each sector is 22.5°. The first sector is 348.75-11.25 degrees, that is, it extends 11.25 degrees to the left and right from 0 degrees. The second sector is 22.5 degrees, which extends 11.25 degrees to the left and right, with a range of 11.25-33.75 degrees, and so on. For the target wind direction data, the corresponding sector can be determined based on the wind direction value of the reference wind tower at the corresponding time.

[0039] In other embodiments, the process of interpolating wind speed from different towers based on wind resource data of adjacent wind towers is as follows: The wind speed data of the target wind tower are divided into several sectors according to the interpolated wind direction data of the target wind tower. The neighboring wind towers are used as reference wind towers, and the relationship between the wind speed data of the target wind tower and the reference wind speed of the reference wind tower is fitted sector by sector. Based on the fitted wind speed relationship of each sector, the wind speed data in each sector of the target wind tower are interpolated.

[0040] In the application of wind speed interpolation, different fitting methods can be flexibly selected according to the specific data characteristics and interpolation requirements to improve the prediction accuracy. For example, the linear least squares method is simple and easy to use, and is suitable for wind speed data with obvious linear relationships. However, when the wind speed fluctuates greatly, the overall least squares method will be more effective because it can simultaneously consider the measurement errors of the target wind speed and the reference wind speed. For situations where the wind speed distribution is close to the Weibull distribution, the use of Weibull fitting can better reflect the probability characteristics of the wind speed, and is especially suitable for the fitting and prediction of long-term wind speed data.

[0041] In one or more embodiments, the wind resource intelligent analysis and processing module 101 is also used to: use the mesoscale weather data in the wind resource data to correct the interpolated wind resource data into representative wind resource data; determine whether the representative wind resource data has a tower shadow effect, and if not, obtain the final interpolated and corrected target wind tower wind resource data; otherwise, perform tower shadow correction on the representative wind resource data, and use the tower shadow corrected result as the final interpolated and corrected target wind tower wind resource data.

[0042] Among them, if there are two wind measurement channels at the same height of the target wind measurement tower, this phenomenon is called the tower shadow effect. At this time, the tower shadow correction method needs to be used to correct the wind speed data at this height.

[0043] It should be noted here that the tower shadow correction can be based on the actual situation by using the method of correcting according to the area affected by the tower shadow, taking the maximum value method, and selecting the channel with the larger average value in the two wind speed channels. If the tower shadow influence is more obvious in wind speed channels A and B and the tower shadow area can be accurately divided, the correction method according to the area affected by the tower shadow is preferred. This method can correct the specific area affected by the tower shadow with higher accuracy. If it is difficult to clearly define the area affected by the tower shadow and the wind speed fluctuates greatly, it is recommended to use the maximum value method. This method is simple and can avoid the influence of the tower shadow on the reduction of wind speed, and is suitable for real-time correction.

[0044] Specifically, the process of correction according to the area affected by the tower shadow is as follows: Divide the two wind speed channels at the same height into several sectors according to the wind direction; calculate the ratio of the wind speeds of channels A and B at the same time for each sector; calculate the median of the ratio within each sector; For the values ​​obtained in the previous step, take the central angle of the sector where the maximum value is located, and take 15 degrees to the left and right, and regard it as the area where channel B is affected by the tower shadow. The wind speed channel B value in this area is corrected by the corresponding channel A value; similarly, take the sector where the minimum value is located, select the corresponding range, and regard it as the area where channel A is affected by the tower shadow.

[0045] Specifically, the maximum value method is to select the larger value of channels A and B as the value at each moment.

[0046] In the specific implementation process, in the wind farm macro-site selection module 102, as shown in FIG. Picture 2 As shown in the figure, the process of macro optimization of wind farm planning based on multiple graphs and sensitive factors is as follows: S201, obtaining geographic information of the area to be planned, and determining a number of candidate wind farm sites in the area to be planned according to set sensitive factors.

[0047] Among them, the sensitive factors include terrain factors, geological factors, hydrological factors, meteorological factors and set sensitive areas.

[0048] S202: Generate a corresponding wind resource map based on historical wind measurement data in each candidate wind farm area.

[0049] The process of generating a wind resource map is as follows: S2021, further partitioning the candidate wind farm area into several sub-areas, and for each sub-area, performing a mesoscale meteorological model simulation for a specified year to obtain background field data; S2022, for the background field data of each sub-area, dynamic downscaling is performed to obtain a 100-meter resolution wind resource map of a specified year; the 100-meter resolution wind resource maps of all areas of a specified year are spliced ​​to obtain a 100-meter resolution wind resource map of a specified area of ​​a specified year; the wind tower data of a specified area of ​​a specified year are obtained, and after spatial matching of the wind tower data with the 100-meter resolution wind resource map of a specified area of ​​a specified year, the 100-meter resolution wind resource map of a specified area of ​​a specified year is corrected; S2023, obtain reanalysis data of a specified year, use the reanalysis data of a specified year as input and the corrected 100-meter resolution wind resource map of a specified area in a specified year as output, and train a random forest regression model; obtain reanalysis data of non-specified years, perform statistical downscaling using the trained random forest regression model, and obtain a 100-meter resolution wind resource map of a candidate wind farm area in a non-specified year.

[0050] S203, determining the maximum number of wind turbines and the wind turbine layout plan of the set wind turbine type in each wind farm candidate area according to the wind resource map and geographic information of each wind farm candidate area.

[0051] Specifically, the process of determining the maximum number of wind turbines of a set wind turbine type and the wind turbine layout plan for each wind farm candidate site is as follows: S2031: Based on the terrain in the candidate wind farm area, select locations matching the wind turbine layout in the candidate wind farm area, and determine a wind turbine layout algorithm; S2032: Based on the wind resource map in the site area, obtain the dominant wind direction of the site area, and determine the arrangement rule parameters based on the dominant wind direction; S2033: extracting the fan impeller diameter based on the machine attribute parameters matched with the site area, and determining the arrangement rule parameters based on the fan impeller diameter; S2034: Based on the positions and arrangement rule parameters of the matching fan layout, a maximum number of fans and a maximum fan arrangement plan are obtained through a preset fan arrangement algorithm.

[0052] S204, calculating the total power generation and noise spectrum of each candidate wind farm area according to the maximum number of wind turbines and the wind turbine layout plan of each candidate wind farm area; wherein the noise spectrum is synthesized by the time-series projection range of all wind turbines in the candidate wind farm area.

[0053] Among them, the calculation process of the time series projection range of the fan is: Discretize the ground near the wind turbine into a number of grids, divide the period to be evaluated into minute-level time periods, and obtain a first horizontal distance between the highest point of the wind turbine rotor and the ground projection point and a second horizontal distance between the lowest point of the wind turbine rotor and the ground projection point according to the azimuth of the sun in each minute-level time period, wherein the first distance and the second distance are both the horizontal distances between the ground projection point and the wind turbine; For any grid to be evaluated, determine whether it coincides with the projection direction at this time according to the direction of the center of the grid to be evaluated relative to the wind turbine rotor. If it coincides, determine whether the horizontal distance from the center of the grid to be evaluated to the wind turbine is between the second horizontal distance and the first horizontal distance. If so, determine that the grid to be evaluated is affected, add a minute-level period to the affected time, and continue to determine until the grid to be evaluated is not affected. The affected time period and / or cumulative affected time of each grid in the entire period to be evaluated are obtained, and the time series projection range of the wind turbine is obtained.

[0054] Calculating the solar altitude angle is the basis for studying the light and shadow flicker of wind turbines. The calculation formula for the solar altitude angle is as follows:

[0055] Where: is the local latitude, degree ; The sun's red tail angle, degree ; is the solar hour angle, degree .

[0056] Where: Solar declination angle for:

[0057] Where: n To calculate the sequence of days of the year for the current day.

[0058] The specific calculation time and Beijing time can be converted according to the following formula:

[0059] Where: L is the measured local latitude; E To correct the time difference, the calculation formula is as follows:

[0060] In the formula, .

[0061] After calculating the solar altitude angle, the projection length of the wind turbine rotor during this period can be calculated. First, calculate the projection distance of the top of the wind turbine rotor. L1 :

[0062] Wherein, D1 is the sum of the top of the wind turbine rotor and the elevation difference between the sensitive point and the wind turbine coordinates, in meters.

[0063] Then calculate the projection distance of the lower end of the fan rotor L2 :

[0064] in, D2 It is the sum of the lowest point of the wind turbine rotor and the elevation difference between the sensitive point and the wind turbine coordinates, in meters.

[0065] S205 , selecting a wind farm candidate area with the largest power generation in the entire field as the optimal wind farm area from a set of wind farm candidate areas whose maximum area of ​​the noise spectrum does not exceed a set area threshold range.

[0066] Since the noise spectrum is a spectrum that changes over time, after eliminating the wind farm candidate sites whose maximum area of ​​the noise spectrum exceeds the set area threshold range (which can be set according to set specifications or manually), the wind farm candidate site with the largest power generation in the entire field is selected from the remaining set of wind farm candidate sites as the optimal wind farm site.

[0067] In the wind farm equipment selection and layout optimization module 103, as Picture 3 As shown in Figure 1, the process of selecting and optimizing the layout of wind farm equipment is as follows: S301: Determine a matching wind turbine type according to the wind speed level and trust level requirements of the wind farm.

[0068] Under the conditions that the capacity and boundary of the wind farm are known, the type of unit suitable for the wind farm is selected in combination with the rotor diameter, the rated power of a single unit and the wind speed conditions at the location of the wind farm. For the selected wind turbine types, the values ​​greater than 0.48 in their thrust coefficient curves are evaluated for trust levels, and the product of the trust level coefficients of each correction value is the trust level of the wind turbine in the final wind turbine type selection scheme.

[0069] S302: The area within the preset wind farm boundary is gridded, each grid vertex is set as a wind turbine site, and the layout plan of the wind turbines of a certain type is optimized with the maximum power generation of the whole wind farm as the optimization goal to obtain a micro-site selection and layout plan.

[0070] In one or more embodiments, according to the principle of regular arrangement of wind turbines, a grid enumeration algorithm based on equal spacing or a genetic algorithm based on equal spacing is used to optimize and iterate the relevant parameters of the parallelogram; wherein the relevant parameters of the parallelogram include the azimuth of the long side of the parallelogram, the angle between the long side and the short side, the length of the long side, the length of the short side, the long side offset and the short side offset. This method is applicable to plain and offshore wind farms.

[0071] In other embodiments, a genetic algorithm based on real number coding is used to encrypt the grid in areas where the elevation and wind power density are greater than a set threshold, and determine a regular arrangement of wind turbines with the largest power generation in the wind farm. Prioritize screening during the iterative process of the genetic algorithm to improve the efficiency of the genetic algorithm.

[0072] In other optional embodiments, the relevant parameters of the parallelogram are optimized and iterated with the non-equidistant layout of the wind farm; wherein the relevant parameters of the parallelogram include the azimuth of the long side of the parallelogram, the angle between the long side and the short side, the length of the long side, the length of the short side, the offset of the long side, the offset of the short side, the diffusion coefficient of the short side distance and the diffusion coefficient of the long side distance. By introducing the two parameters of the diffusion coefficient of the short side distance and the diffusion coefficient of the long side distance, the non-equidistant layout of the wind farm is realized, and the power generation loss caused by the terrain, environmental turbulence, etc. is reduced. After the algorithm iteration is completed, the total power generation, average wake loss, unit cost, wind turbine foundation cost and total hoisting cost calculated by the corresponding model scheme are output.

[0073] Before formulating the wind turbine layout plan, it is necessary to clarify the site boundaries of the wind farm and the scope of the sensitive area, and use polygons to illustrate the wind farm boundaries and sensitive areas; the wind farm boundaries and sensitive area data are extracted from the map data file or directly obtained from the Excel file.

[0074] In the optimal layout of wind turbines in a wind farm, a grid shape with a parallelogram as the smallest unit is set, and the following assumptions are made for the model: the coordinates of the origin of the coordinate system are (Cx, Cy), the azimuth of the long side is θx, the angle between the long side and the short side is θy, the distance between the starting point and the adjacent point on the short side is Lx1, the distance between the starting point and the adjacent point on the long side is Ly1, the short side distance diffusion coefficient is Sx, and the long side distance diffusion coefficient is Sy.

[0075] When the short side distance diffusion coefficient Sx and the long side distance diffusion coefficient Sy are both equal to 1, the grid is arranged evenly and regularly; when Sx and Sy are not 1, the grid is arranged irregularly. When the starting point is at the boundary, the grid is arranged only to this side of the site, and not to the outside of the boundary; when the starting point is at the center of the site, the grid is arranged to both sides.

[0076] Specifically, the present implementation adopts a general model of an eight-variable variable spacing layout method: Cx, Cy, θx, θy, Lx1, Ly1, Sx, and Sy. In the regular layout optimization process of wind turbines, the maximum power generation of the entire wind farm is taken as the optimization goal, and the above eight parameters are iteratively selected to finally obtain a regular layout scheme for wind turbines that meets the above requirements.

[0077] S303: Under the micro-site selection and layout plan, the influence range of each unit is calculated and drawn based on the preset noise assessment model and a noise cloud map is synthesized. The location of the units that affect the sensitive areas of residents is adjusted based on the noise cloud map and a protection distance for the sensitive areas is reserved to obtain a revised micro-site selection and layout plan.

[0078] S304: Based on the revised micro-site selection and layout plan, with the wind farm boundary, the sites of each wind turbine, the sensitive area and the maximum distance from the booster station to the site as constraints, the site within the wind farm boundary with the lowest total construction cost is taken as the booster station site selection result.

[0079] The site selection optimization process mainly includes the comparison of earthwork volume and distance engineering volume of the alternative sites. This implementation method designs a weighted earthwork algorithm for the substation. Considering the possible complex terrain conditions in the mountains, the earthwork weighted algorithm mainly adopts the digital ground model method. Through the existing model three-dimensional coordinates ( x , y , z ) Adjacent coordinate points are connected to generate a triangulated network to calculate the earthwork excavation volume of each triangular pyramid. The earthwork excavation volume of each triangular pyramid calculated by the software is superimposed to obtain the earthwork volume of the alternative site for the mountain wind farm booster station at the design elevation. Considering the influence of actual engineering factors, it is necessary to use the earthwork weighting factor to correct the calculation results. The earthwork weighting factor of this implementation method is mainly determined by terrain, environmental conditions, engineering requirements, and site factors.

[0080]

[0081] In the formula, e is the earthwork weighting factor; T is the terrain factor, which reflects the influence of different terrain characteristics on the earthwork volume estimation; S is the site factor, reflecting the influence of site factors such as soil type and soil quality; E It is the engineering factor, which reflects the influence of the actual conditions of the project on the earthwork estimate; En It is an environmental factor, which reflects the impact of environmental factors such as temperature and rainfall on earthwork estimation.

[0082] In the process of determining the wind farm road, an objective function of the weighted total road construction cost is constructed based on the road construction cost of each road section, road longitudinal slope coefficient, road longitudinal slope gradient, road turning radius coefficient, road earthwork cost coefficient, filling volume, excavation volume, unit excavation cost and unit filling cost.

[0083] The calculation points of the distance engineering quantity are fitted with the established DEM model. In order to improve the calculation accuracy, the fitting points that meet the conditions are automatically selected from the two points where the distance calculation is required, and the longer road engineering is fitted into a combination of multiple shorter roads. Taking the road points A and G to be calculated as an example, the fitting points B, C, D, E, and F are inserted in the road calculation process, and the distance calculation of road AE is converted into the sum of the distances of AB, BC, CD, DE, and EF. At the same time, considering the impact of the model accuracy on the distance fitting results, the distance fitting coefficient is added for correction. The fitting distance calculation formula between any two is as follows:

[0084] In the formula, xA , yA, zA are the ordered numerical arrays of the DEM model of point A, xB , yB, zB They are the ordered numerical arrays of the DEM model of point B; l is the distance fitting coefficient.

[0085] S305: The booster station site selection results and the revised micro-site selection layout plan are associated with the map within the preset wind farm boundary to construct a wind farm site selection map. Based on the relevant information of the wind farm site selection map, the optimal results of the wind farm roads and collector lines are determined with the minimum total road construction cost and the minimum collector line engineering volume as the goals, and finally the wind farm equipment selection and layout optimization plan is obtained.

[0086] The process of determining the optimal wind farm road with the minimum total road construction cost includes: According to the wind farm boundary, prohibited construction area, confirmed machine site, road access point and road delivery point, the area where topographic map needs to be generated is exported from Aowei Map in .kmz or .kml format; the obtained .kmz or .kml format file is imported into Global Mapper, the contour interval value is modified to 10, the topographic map is generated and the horizontal and elevation data are extracted; For the acquired map data, the approximate geodesic method is used to calculate the distance between two points. Specifically, firstly, project points A and E to the ground to generate points A' and E', insert multiple points B', C', D'...M', N' into the line connecting points A'E', and then find the points B, C, E...M, N projected to the actual terrain by these three points. The path length between points AE is approximately converted into the sum of the Euclidean distances between AB, BC, CD, DE...MN. The distance calculation formula between any two points is as follows:

[0087] in xA , yA , zA They are A The coordinates and elevation of the point, B I agree.

[0088] A weighted total cost function model for road construction is established, specifically:

[0089]

[0090]

[0091]

[0092]

[0093]

[0094] in, Ct is the weighted total road construction cost; Ci For the i Cost of road construction; αi For the i Longitudinal slope coefficient of section road; si For the i The longitudinal slope of the road section; βi For the i Turning radius coefficient of road section; Ei , F , Vi , , Respectivelyi The earthwork cost coefficient, filling volume, excavation volume, unit excavation cost and unit filling cost of the road section. The optimization goal is to minimize the total weighted road construction cost. minCt .

[0095] Based on the determined unit coordinates and road access points and delivery points, the minimum weighted total road construction cost is optimized.

[0096] The process of determining the optimal collector line results includes: A clustering algorithm is used to divide the collector line loops of the units and delineate the subordinate booster stations. Taking the wind farm boundary, sensitive area, cable limit area, maximum line voltage drop and other constraints as constraints, a greedy algorithm is used to generate the initial solution of the collector line. The layout plan is matched to the collector line topology structure, and the random forest algorithm or genetic algorithm is further used to optimize the initial solution to obtain the optimal solution for the collector line engineering volume.

[0097] In the specific implementation process, in the wind farm post-evaluation module 104, the wind resource index is selected as wind speed and annual utilization hours, and the power generation index is selected as power generation and energy availability; When the ratio of the wind resource index in the design phase to the wind resource index in the operation phase is less than the first set warning value, a wind resource warning is issued, and a technical transformation strategy of relocating the machine site or increasing the tower height is generated to increase the wind speed value; When the ratio of the power generation index in the design phase to the power generation index in the operation phase is less than the second set warning value, a power generation warning is issued, and a technical transformation strategy for unit blade modification or model replacement is generated to increase the unit's power generation.

[0098] In this embodiment, the designed power generation of the wind farm is also reviewed. During the review, the power generation compliance rate is calculated, the power generation in the design stage and the operation stage is statistically analyzed and a bar chart is drawn, and the power generation of the wind turbines is visually compared through images.

[0099] When verifying the power generation situation, the actual power generation and the designed power generation are used to verify the actual reduction factor. The power curve of the actual operation period and the wind resource data of the design stage are used to calculate the design stage power generation under the operation period power curve. The power generation calculation method is:

[0100] in, nD is the number of wind direction sectors; nU is the number of wind speed intervals; nT is the number of wind turbines; Fijk It is a wind turbine k In the wind sector i Wind speed is in the range j probability; PijkUnder the corresponding power curve, the wind turbine is in the wind direction sector i Wind speed range j The power generation power (unit is kW), the annual power generation hours are 8766, that is, the average annual hours of four years considering leap years. The total power generation is the average power generation for one year, the unit is kWh.

[0101] The theoretical grid-connected power of each wind turbine in the design year is obtained. Ei After that, by comparing it with the theoretical power generation, the comprehensive reduction factor at each unit location can be obtained. δi , the calculation method is:

[0102] Where: E0i Indicates i Theoretical power generation of a typhoon turbine during the design phase.

[0103] This method can be used to review the designed power generation of the wind farm, analyze the reasons for the differences in the reduction factors at the locations of each wind turbine, and provide a reference for future calculations of wind farm power generation.

[0104] Specifically, in the wind farm post-evaluation module 104, the computer unit capacity coefficient and the wind turbine unit availability are calculated, and when the unit capacity coefficient is less than the third set warning value, or when the wind turbine unit availability is less than the fourth set warning value, an abnormal unit operation state warning is issued; wherein the unit capacity coefficient is the ratio of the equivalent full-generation hours to the annual hours, and the wind turbine unit availability includes the availability based on time and the availability based on power generation; Time-based availability , A represents the number of downtime hours due to failure, and B represents the number of downtime hours caused by reasons other than the responsibility of the assessed object; Availability of power generation , The actual power generation during the statistical period, The lost power generation during the statistical period.

[0105] In the wind farm post-evaluation module 104, fault detection is performed on the wind turbine generator system according to a preset fault library and a pre-trained machine learning algorithm, and when a fault is detected, a fault alarm is issued and a technical improvement strategy for maintenance and parts replacement is generated.

[0106] To evaluate the operating status and fault conditions of wind turbine equipment, it is necessary to collect statistics and analyze wind turbine faults and unit output in the wind farm. First, a fault library is established, and machine learning algorithms are used to diagnose unit faults, and the causes of faults are analyzed based on the fault library. In addition, by collecting statistics on the fault time, maintenance time, and fault time of each system in the wind farm throughout the year for each unit and drawing a graph, it is not only convenient to judge and compare the fault conditions of different units, but also to intuitively show the failure rate and severity of different systems in the wind farm.

[0107] like Picture 4 As shown, the present invention provides a planning method based on the wind farm digital integrated planning platform as described above, comprising: S401: using a double detection and evaluation mechanism to process the wind resource data in the set area project set, determine the abnormal data and its type, and then perform matching interpolation and correction to make the wind resource data meet the preset quality requirements; S402: Retrieving wind resource data that meets the set quality requirements in the set regional project set, and then combining it with the geographic information matching the set regional project set, performing macro optimization of wind farm planning based on multiple maps and sensitive factors; S403: Based on the macro optimization result of wind farm planning, the wind farm equipment is selected and arranged to optimize the wind farm equipment selection and arrangement to obtain the wind farm equipment selection and arrangement optimization plan; S404: Compare the wind resource data of the operation phase after the implementation of the wind farm equipment selection and layout optimization plan with the wind resource data of the design phase to evaluate the operation status of the wind farm, and issue early warnings for abnormal conditions and match and generate corresponding solutions.

[0108] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A digital integrated planning platform for wind farms, characterized in that: include: The wind resource intelligent analysis and processing module is used to process the wind resource data in the set area project set using a two-step detection and evaluation mechanism, determine the abnormal data and its type, and then perform matching interpolation and correction to make the wind resource data meet the preset quality requirements; A wind farm macro-site selection module, which is used to retrieve wind resource data that meets the set quality requirements in the set area project set from the wind resource intelligent analysis and processing module, and then combine the geographical information matching the set area project set to perform macro-optimization of wind farm planning based on multiple maps and sensitive factors; A wind farm equipment selection and layout optimization module, which is used to select and optimize the wind farm equipment based on the wind farm planning macro-optimization result output by the wind farm macro-site selection module, and obtain a wind farm equipment selection and layout optimization plan; The wind farm post-evaluation module is used to compare the wind resource data in the operation phase after the implementation of the wind farm equipment selection and layout optimization plan with the wind resource data in the design phase, so as to evaluate the operation status of the wind farm, and to give early warnings for abnormal conditions and match and generate corresponding solutions.

2. The wind farm digital integrated planning platform according to claim 1, characterized in that: The wind resource intelligent analysis and processing module uses set prior rules to perform a primary detection on the wind resource data in the retrieved project set and marks abnormal data; uses the trained data evaluation model to perform a secondary quality evaluation on the marked abnormal data to determine the type of abnormal data; and matches, interpolates and corrects the wind resource data according to the type of abnormal data until the interpolated and corrected wind resource data meets the preset quality requirements.

3. The wind farm digital integrated planning platform according to claim 1, characterized in that: The types of abnormal data include missing wind resource data of the same tower at different heights and missing wind direction and / or wind speed in the wind resource data of the target wind measurement tower.

4. The wind farm digital integrated planning platform according to claim 3, characterized in that: According to the wind resource data of the available height at the target wind tower at the set time, the wind resource data at different heights at the current time are interpolated on the same tower; according to the wind resource data of the adjacent wind towers, the wind direction and / or wind speed are interpolated on different towers; wherein, the wind resource data at different heights interpolated on the same tower include wind speed data, wind direction data and temperature data.

5. The wind farm digital integrated planning platform according to claim 1, characterized in that: In the wind farm equipment selection and layout optimization module, the process of selecting and optimizing the layout of wind farm equipment is as follows: Determine the matching wind turbine type according to the wind speed level and trust level requirements of the wind farm; The area within the preset wind farm boundary is gridded, and each grid vertex is set as a wind turbine site. Taking the maximum power generation of the wind farm as the optimization goal, the layout plan of wind turbines of a certain type is optimized to obtain a micro-site selection and layout plan; Under the micro-site selection and layout plan, the influence range of each unit is calculated and drawn based on the preset noise assessment model, and a noise cloud map is synthesized. The location of the unit that affects the sensitive area of ​​residents is adjusted based on the noise cloud map, and the protection distance of the sensitive area is reserved to obtain the revised micro-site selection and layout plan; Based on the revised micro-site selection and layout plan, with the wind farm boundary, the locations of each wind turbine, the sensitive area and the farthest distance from the booster station to the location as constraints, the site within the wind farm boundary with the lowest total cost is selected as the booster station site selection result; The substation site selection results and the revised micro-site selection and layout plan are associated with the map within the preset wind farm boundary to construct a wind farm site selection map. Based on the relevant information of the wind farm site selection map, the optimal results of wind farm roads and collector lines are determined with the goals of minimizing the total road construction cost and the minimum collector line engineering volume, and finally the optimization plan for wind farm equipment selection and layout is obtained.

6. The wind farm digital integrated planning platform according to claim 5, characterized in that: The process of calculating and drawing the influence range of each unit based on the preset noise assessment model is as follows: Discretize the ground near the wind turbine into a number of grids, divide the period to be evaluated into minute-level time periods, and obtain a first horizontal distance between the highest point of the wind turbine rotor and the ground projection point and a second horizontal distance between the lowest point of the wind turbine rotor and the ground projection point according to the azimuth of the sun in each minute-level time period, wherein the first distance and the second distance are both the horizontal distances between the ground projection point and the wind turbine; For any grid to be evaluated, determine whether it coincides with the projection direction at this time according to the direction of the center of the grid to be evaluated relative to the wind turbine rotor. If it coincides, determine whether the horizontal distance from the center of the grid to be evaluated to the wind turbine is between the second horizontal distance and the first horizontal distance. If so, determine that the grid to be evaluated is affected, add a minute-level period to the affected time, and continue to determine until the grid to be evaluated is not affected, so as to obtain the affected time period and / or cumulative affected time of each grid in the entire period to be evaluated, and then construct a noise cloud map.

7. The wind farm digital integrated planning platform according to claim 1, characterized in that: In the wind farm post-evaluation module, the wind resource index is selected as wind speed and annual utilization hours, and the power generation index is selected as power generation and energy availability; When the ratio of the wind resource index in the design phase to the wind resource index in the operation phase is less than the first set warning value, a wind resource warning is issued, and a technical transformation strategy of relocating the machine site or increasing the tower height is generated to increase the wind speed value; When the ratio of the power generation index in the design phase to the power generation index in the operation phase is less than the second set warning value, a power generation warning is issued, and a technical transformation strategy for unit blade modification or model replacement is generated to increase the unit's power generation.

8. The wind farm digital integrated planning platform according to claim 1, characterized in that: In the wind farm post-evaluation module, the computer unit capacity coefficient and the wind turbine unit availability are calculated, and when the unit capacity coefficient is less than the third set warning value, or when the wind turbine unit availability is less than the fourth set warning value, an abnormal unit operation state warning is issued; wherein the unit capacity coefficient is the ratio of the equivalent full-generation hours to the annual hours, and the wind turbine unit availability includes the availability based on time and the availability based on power generation; Time-based availability , A represents the number of downtime hours due to failure, and B represents the number of downtime hours caused by reasons not attributable to the assessed object; Availability of power generation , The actual power generation during the statistical period, The lost power generation during the statistical period.

9. The wind farm digital integrated planning platform according to claim 1, characterized in that: In the wind farm post-evaluation module, fault detection is performed on the wind turbine set according to a preset fault library and a pre-trained machine learning algorithm, and when a fault is detected, a fault alarm is issued and a technical improvement strategy for maintenance and parts replacement is generated.

10. A planning method based on the wind farm digital integrated planning platform according to any one of claims 1 to 9, characterized in that: include: A double detection and evaluation mechanism is used to process the wind resource data within the set of regional projects, identify abnormal data and its type, and then perform matching interpolation and correction to ensure that the wind resource data meets the preset quality requirements; Retrieve wind resource data that meets the set quality requirements from the set regional project set, and then combine it with the geographic information that matches the set regional project set to perform macro optimization of wind farm planning based on multiple maps and sensitive factors; Based on the macro optimization results of wind farm planning, the wind farm equipment is selected and arranged to obtain the wind farm equipment selection and arrangement optimization plan; The wind resource data in the operation phase after the implementation of the wind farm equipment selection and layout optimization plan is compared with the wind resource data in the design phase to evaluate the operating status of the wind farm, and to warn of abnormal conditions and generate corresponding solutions.

Images