Method, device and apparatus for predicting output power of tidal energy power generation device

Abstract

The present application discloses a method, device and equipment for predicting the output power of a tidal energy power generation device, which relates to the field of tidal energy power generation. The method comprises establishing a matching data set between first tidal observation data of a test sea area and average output power data of a tidal energy power generation device; performing data quality control processing on the matching data set to eliminate abnormal data in the matching data set to obtain a target data set; based on the target data set, using an odd-even extraction method of data sequence numbers, constructing a target odd data set and a target even data set; based on the target odd data set, constructing an initial output power learning model of the tidal energy power generation device; based on the target even data set, correcting the initial output power learning model to obtain a target output power learning model, and predicting the output power of the tidal energy power generation device based on the target output power learning model.

Description

Technical Field

[0001] The present application relates to the technical field of tidal energy power generation, and in particular to a method, device and equipment for predicting the output power of a tidal energy power generation device. Background Art

[0002] With the increasing global demand for energy, coupled with the increasingly prominent greenhouse effect and other environmental issues brought about by the consumption of traditional fossil energy, there is an urgent need to build a green, low-carbon energy system. Tidal energy is a green, safe, and pollution-free renewable energy source. Compared to other marine renewable energy sources, tidal energy boasts high energy density and good predictability. Its development and utilization have received widespread attention worldwide, leading to the demonstration and application of numerous tidal energy power generation devices. During these demonstrations, on-site testing and evaluation of tidal energy device output power are conducted, and the annual power generation capacity of the tidal energy device is calculated. This is crucial for the overall economic performance of the tidal energy device and the investment willingness of social capital.

[0003] However, the calculation results of the average output power of the tidal energy power generation device in the related art are not accurate enough. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for predicting the output power of a tidal energy power generation device.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting the output power of a tidal energy power generation device, comprising:

[0007] Establishing a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device;

[0008] Performing data quality control on the matching data set to remove abnormal data in the matching data set to obtain a target data set;

[0009] Based on the target data set, a target odd-numbered data set and a target even-numbered data set are constructed using an odd-numbered and even-numbered data set extraction method of data sequence numbers;

[0010] Based on the target odd-numbered data set, constructing an initial output power learning model of the tidal energy power generation device;

[0011] Based on the target even-numbered data set, the initial output power learning model is modified to obtain a target output power learning model, and the output power of the tidal energy power generation device is predicted based on the target output power learning model.

[0012] In a second aspect, the present application provides an output power prediction device for a tidal energy power generation device, comprising:

[0013] An establishment module is used to establish a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device;

[0014] a processing module, configured to perform data quality control processing on the matching data set to remove abnormal data in the matching data set and obtain a target data set;

[0015] A first construction module is configured to construct a target odd-numbered data set and a target even-numbered data set based on the target data set by using an odd-even extraction method of data sequence numbers;

[0016] A second building module is used to build an initial output power learning model of the tidal energy power generation device based on the target odd-numbered data set;

[0017] A correction module is used to correct the initial output power learning model based on the target even-numbered data set to obtain a target output power learning model, and perform output power prediction of the tidal energy power generation device based on the target output power learning model.

[0018] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the output power prediction method for a tidal energy power generation device described in any one of the above.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the output power prediction method of any one of the above-mentioned tidal energy power generation devices.

[0020] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the output power prediction method of any one of the above-mentioned tidal energy power generation devices.

[0021] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0022] The present application provides a method, device, equipment, medium and product for predicting the output power of a tidal energy power generation device. By performing data quality control processing on the matching data set to eliminate abnormal data in the matching data set and obtain a target data set, the reliability of the input data can be improved and outliers can be avoided from interfering with model training. Based on the target data set, a data sequence number odd-even extraction method is used to construct a target odd data set and a target even data set, and the target data set is split into a training set (target odd data set) and a validation set (target even data set) according to the parity of the sequence number, avoiding local deviations that may be introduced by random partitioning, enabling the model to learn more comprehensive data distribution characteristics, maximizing the utilization of limited data, reducing the risk of overfitting, and enhancing the model's prediction stability for unknown data through the iterative process of training the target odd data set and correcting the target even data set (applicable to complex and changeable marine environments). The present application improves the accuracy and reliability of the output power prediction of the tidal energy power generation device through data quality control, construction of odd and even data sets and iterative model correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of a method for predicting output power of a tidal energy power generation device provided in one embodiment of the present application;

[0025] Figure 2 A schematic diagram of a curve of an initial output power learning model provided in one embodiment of the present application;

[0026] Figure 3 A schematic diagram of average output power predicted by an initial output power learning model provided in one embodiment of the present application;

[0027] Figure 4 A schematic diagram of a correction coefficient provided in one embodiment of the present application;

[0028] Figure 5 A schematic diagram of a fitting curve of a second mathematical expression provided in one embodiment of the present application;

[0029] Figure 6 A schematic diagram of an average output power predicted by a target output power learning model provided in one embodiment of the present application;

[0030] Figure 7A schematic diagram comparing the prediction results of average output power by an initial output power learning model and a target output power learning model provided in one embodiment of the present application;

[0031] Figure 8 A schematic diagram of the functional modules of an output power prediction device for a tidal energy power generation device provided in one embodiment of the present application;

[0032] Figure 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0035] In an exemplary embodiment, Figure 1 As shown, a method for predicting the output power of a tidal energy power generation device is provided. The method is executed by a computer device, specifically, a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method includes the following steps 102 to 110. Among them:

[0036] Step 102: establishing a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device;

[0037] Among them, the test sea area can be an ocean area divided for scientific research, engineering, environmental assessment and other purposes, and the first tidal observation data can be data obtained by measuring and recording the motion characteristics of tidal water flow (tidal) in the ocean at multiple times; the tidal energy power generation device is a device that uses the kinetic energy of ocean tidal flow to generate electricity. Its principle is similar to that of a wind power generation device, but the energy source is converted from air flow to seawater flow; the average output power data of the tidal energy power generation device can be calculated by measuring the actual output power of the tidal energy power generation device measured at multiple times, and a matching data set of the first tidal observation data and the average output power data can be established to determine the correspondence between the first tidal observation data and the average output power data, and provide a data basis and model training basis for the subsequent prediction of the average output power data of the tidal energy power generation device based on the first tidal observation data.

[0038] Step 104: performing data quality control processing on the matching data set to remove abnormal data in the matching data set to obtain a target data set;

[0039] Among them, a data quality control algorithm can be used to perform data quality control on the matching data sets after mutual matching in step 102 to form a target data set after quality control; data quality control can be a process of using a data quality control algorithm to ensure that data meets quality standards such as accuracy, completeness, consistency, timeliness and reliability during the collection, storage, processing and analysis processes. By performing data quality control on the matching data sets, data errors, noise and bias can be eliminated or reduced, making the data credible and suitable for subsequent analysis and decision-making.

[0040] Step 106: Based on the target data set, using the data sequence number odd-even extraction method, construct a target odd-numbered data set and a target even-numbered data set;

[0041] The target data set after quality control formed in step 104 can be used to construct a data set required for predicting the average output power of the tidal energy power generation device; the odd-even extraction method based on the data sequence number is a data segmentation method based on the data sequence number, which realizes rapid data grouping by extracting the odd-numbered and even-numbered data in the target data set respectively. The data with odd sequence numbers form the target odd-numbered data set, and the data with even sequence numbers form the target even-numbered data set. The target odd-numbered data set can be expressed as , the target even-numbered dataset can be expressed as .

[0042] Step 108: constructing an initial output power learning model of the tidal energy power generation device based on the target odd-numbered data set;

[0043] The initial output power learning model can also be called the initial average output power mathematical model of the tidal energy power generation device, the initial average output power prediction model or the initial model, which can be used to calculate the target odd-numbered data set in step 106. , construct the initial mathematical model of the average output power of the tidal energy power generation device, that is, the target odd data set As a training set to train the initial output power learning model.

[0044] Step 110: Based on the target even-numbered data set, the initial output power learning model is modified to obtain a target output power learning model, and the output power of the tidal energy power generation device is predicted based on the target output power learning model.

[0045] The target output power learning model can also be called the final tidal energy power generation device average output power mathematical model, the final average output power prediction model or the final model, which can be used to calculate the target even data set in step 106. , correct the initial mathematical model of the average output power of the tidal energy power generation device in step 108 to form the final mathematical model of the average output power of the tidal energy power generation device, that is, the target even data set The initial output power learning model is corrected as a validation set to obtain a target output power learning model. Subsequently, new flow observation data can be input into the target output power learning model to make the target output power learning model output the predicted average output power.

[0046] By implementing the above-mentioned steps 102 to 110, data quality control processing is performed on the matching data set to eliminate abnormal data in the matching data set to obtain a target data set, which can improve the reliability of the input data and avoid outliers interfering with model training; based on the target data set, a target odd data set and a target even data set are constructed using the odd-even extraction method of the data sequence number, and the target data set is split into a training set (target odd data set) and a validation set (target even data set) according to the parity of the sequence number, avoiding local deviations that may be introduced by random partitioning, so that the model learns more comprehensive data distribution characteristics, maximizes the utilization of limited data, reduces the risk of overfitting, and enhances the model's prediction stability for unknown data through the iterative process of training the target odd data set and correcting the target even data set (applicable to complex and changeable marine environments); the present application improves the accuracy and reliability of the output power prediction of the tidal energy power generation device through data quality control, construction of odd and even data sets, and iterative correction of the model.

[0047] In another exemplary embodiment of the present application, the above step 102 may be replaced by the following steps 1021 to 1023:

[0048] Step 1021: obtaining original tidal current observation data of the test sea area, performing spatial conversion processing on the original tidal current observation data to obtain first tidal current observation data, wherein the original tidal current observation data is vertical profile data of the test sea area at a historical moment, and the first tidal current observation data is impeller swept cross-section characteristic data input to the tidal current energy power generation device at a historical moment;

[0049] The original tidal current observation data may be data directly obtained by the tidal current observation equipment in the test sea area, and the original tidal current observation data may include observation time data ( ), vertical profile velocity data of tidal flow velocity ( ), vertical cross-section flow data of tidal flow direction ( ); where k is the sequence number of the tidal velocity and flow direction data in the vertical section, and its value can be expressed as , is the total number of tidal flow velocity and direction data in the vertical section.

[0050] The first tidal current observation data may include observation time data ( ), the tidal characteristic velocity data within the sweep cross section of the impeller of the tidal energy power generation device ( ), the tidal current characteristic direction data within the sweep cross section of the impeller of the tidal current energy power generation device ( ); where i is the serial number of the tidal observation data, and its value can be expressed as , is the total number of tidal flow observation data.

[0051] The vertical profile velocity data in the original tidal flow observation data is spatially transformed to obtain the tidal characteristic velocity data, as shown in the following formula (1). The vertical profile velocity data of the tidal flow velocity ( ) Calculate the characteristic flow velocity data of the tidal current inputted into the swept cross section of the impeller of the tidal current energy power generation device ( ):

[0052] (1);

[0053] in, A is the swept area of ​​the impeller of the tidal energy power generation device, The impeller of the tidal energy power generation device is k The swept area of ​​a vertical section, a is the vertical section number of the bottom end of the impeller of the tidal energy power generation device, b It is the vertical section number of the uppermost end of the impeller of the tidal energy power generation device.

[0054] The vertical section flow direction data in the original tidal observation data are spatially transformed to obtain the tidal characteristic flow direction data, as shown in the following formula (2). The vertical section flow direction data of the tidal flow direction ( ), calculate the tidal characteristic direction data input into the swept cross section of the impeller of the tidal energy power generation device ( ):

[0055] (2);

[0056] It should be noted that: When the result of the calculation is negative, The final result is obtained after adding 360°.

[0057] Step 1022: obtaining original output power measurement data of the tidal energy power generation device, performing mean processing on the original output power measurement data, and obtaining average output power data of the tidal energy power generation device;

[0058] The original output power measurement data may be data acquired by a power measurement device of the tidal energy power generation device, and the original output power measurement data may include measurement time data ( ) and the original output power measurement data output by the tidal energy power generation device ( ),in, j The serial number of the power measurement device to obtain data, its value can be expressed as , The total amount of data obtained by the power measurement device. The average output power data refers to the time interval of the power flow observation data. Average output power data within ( ).

[0059] Since the data acquisition frequency of the power measurement device of the tidal energy power generation device is higher than the data acquisition frequency of the tidal observation device during the on-site testing and analysis of the tidal energy power generation device, the time interval of the tidal observation data is The power measurement device will obtain n The original output power measurement data of a tidal power generation device ( ), it is easy to know that when the time of the tidal current observation data is synchronized with the time of the original output power measurement data output by the tidal current energy generation device, that is, hour, The time of the original output power measurement data of the corresponding tidal energy power generation device is .in, It is the serial number of the original output power measurement data output by the tidal energy power generation device at the first time synchronized with the tidal observation time.

[0060] Calculate the time interval of the tidal flow observation data Inside, that is The average output power data of the tidal energy generation device within the time interval ( ), as shown in the following formula (3), the average output power data can be calculated ( ):

[0061] (3);

[0062] in, It means that in the calculation to The average output power data of the tidal energy generation device within the time interval is The original output power measurement data corresponding to the moment is used in the calculation, and The original output power measurement data corresponding to the time is not included in the calculation.

[0063] Step 1023: Match the first power flow observation data and the average output power data to obtain a matching data set.

[0064] Wherein, the matching data set may include observation time data ( ), input to the tidal current characteristic velocity data within the sweep cross section of the impeller of the tidal current energy power generation device ( ), the tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device ( ), and the average output power data of tidal energy generation devices ( ).

[0065] In the embodiment of the present application, “the tidal characteristic direction data ( The calculation method of ")" is formula (2). Formula (2) avoids the calculation error caused by the "direct arithmetic average" calculation method and improves the accuracy of the calculated tidal characteristic direction data. For example, the arithmetic average of 30° and 315° is 172.5°, but the tidal characteristic direction data calculated using the method proposed in the embodiment of the present application is 352.5°, and the calculation result is more consistent with the actual situation.

[0066] In an embodiment of the present application, by converting the original vertical profile data into impeller swept section characteristic data, the effective energy capture area can be focused, the fluid dynamic characteristics of the actual force on the impeller can be more accurately reflected, and the physical rationality of the prediction model can be improved; by performing mean processing on the original output power measurement data to obtain average output power data, the instantaneous fluctuation interference of the power data can be reduced, the long-period change trend of tidal energy can be highlighted, high-frequency noise interference model training can be avoided, and the data signal-to-noise ratio can be improved; by time-aligning and matching the first tidal observation data after spatial conversion processing and the average output power, a matching data set is constructed to ensure that the physical causal relationship between the input (flow velocity) and the output (power) is clear, and to avoid false associations caused by time asynchrony.

[0067] In another exemplary embodiment of the present application, the matching data set includes observation time data, characteristic tidal flow velocity data within the impeller swept cross-section input to the tidal energy power generation device, characteristic tidal direction data within the impeller swept cross-section input to the tidal energy power generation device, and average output power data of the tidal energy power generation device. The above step 104 can be replaced by the following steps 1041 to 1043:

[0068] Step 1041: Divide the matching data set according to a preset first flow rate interval to obtain a plurality of first data groups;

[0069] The first flow rate interval can be expressed as , can be adjusted according to the fixed first flow rate interval , the matching data set is divided, and the number of the first data group can be calculated by the following formula (4):

[0070] (4);

[0071] in, It can represent the maximum value of the tidal flow velocity in the tidal characteristic flow velocity data of the matching data set. It can represent the minimum value of tidal flow velocity in tidal characteristic flow velocity data. Indicates rounding up. Indicates the total number of the first data group divided, using m Represents the sequence number of the first data group after division, and its value can be expressed as , the tidal flow velocity range of the mth first data group can be expressed as .

[0072] Specifically, the matching data set can be divided into two groups according to a fixed first flow rate interval. Divide out data groups, and then match the observation time data ( ), input to the tidal current characteristic velocity data within the sweep cross section of the impeller of the tidal current energy power generation device ( ), the tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device ( ), average output power data of tidal energy generation device ( ) are divided into corresponding data groups.

[0073] Step 1042: Using a data quality control algorithm, perform data quality control processing on the average output power data in each of the first data groups to eliminate abnormal output power data in the corresponding first data group and the observation time data, tidal current characteristic velocity data, and tidal current characteristic direction data corresponding to the abnormal output power data, to obtain a corresponding first sub-data group;

[0074] Among them, during the on-site testing of the tidal energy power generation device, due to the existence of factors such as measurement errors and drift of measurement data, there will inevitably be certain abnormal data in the on-site test data set. In order to ensure the accuracy of the prediction results of the average output power of the tidal energy power generation device, it is necessary to perform quality control on the data in the divided first data group.

[0075] First, the Shapiro-Wilk test method can be used to analyze the average output power data of the tidal energy generation device in each first data group m ( ) to perform a normality test, and secondly, to determine whether each first data group m Average output power data of tidal energy generation devices within ) normality test results, if the discriminant test results are normally distributed, the following formula (5) is used to calculate each first data group m Average output power data of tidal energy generation devices within ) should preserve the distribution range of the data , for those exceeding Average output power data of tidal energy generation devices within the range ( ) to remove and retain the distribution range of the data .

[0076] (5);

[0077] in, Indicates the m Average output power data of the tidal energy power generation device in the first data group ( ), express The average value of the average output power data, express The standard deviation of the average output power data.

[0078] If the discriminant test result is not normally distributed, you can use Origin or MATLAB software to calculate the distribution of each first data group. m Average output power data of tidal energy generation devices within ) and the third quartile , and then use the following formula (6) to calculate each first data group m Average output power data of tidal energy generation devices within ) should preserve the distribution range of the data , for those exceeding Average output power data of tidal energy generation devices within the range ( ) to remove and retain the distribution range of the data .

[0079] (6);

[0080] Wherein, each first data group can be m within or range, will exceed or Average output power data of tidal energy generation devices in the range ( ) and with Each corresponding first data group m Observation time data within ( ), each first data group m The tidal characteristic velocity data within the sweep section of the impeller of the tidal energy power generation device ( ), each first data group m The tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device is input into the tidal current energy power generation device ( ) are removed to obtain a first sub-data group corresponding to each first data group m, where the first sub-data group is the first data group after the abnormal data are removed.

[0081] Step 1043: Sort the multiple first sub-data groups according to the observation time data to obtain the target data set.

[0082] The observation time data in each first sub-data group ( ), input to the tidal current characteristic velocity data within the sweep cross section of the impeller of the tidal current energy power generation device ( ), the tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device ( ), average output power data of tidal energy generation device ( ), and combine them into a new dataset according to the order of observation time data, which is the target dataset after quality control.

[0083] Specifically, the target data set may include observation time data ( ), input to the tidal current characteristic velocity data within the sweep cross section of the impeller of the tidal current energy power generation device ( ), the tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device ( ), average output power data of tidal energy generation device ( ),in, is the serial number of the data in the data set after quality control, and its value can be expressed as , is the total number of data in the target dataset after quality control.

[0084] In the embodiment of the present application, a "data quality control algorithm" is proposed for the average output power prediction work of the tidal energy power generation device. ) is used to conduct a normality test, and the quartile method's insensitivity to extreme outliers and the 3σ method's excellent recognition characteristics for abnormal data in normally distributed data sets are fully utilized. At the same time, this application also considers the risks of false alarms and omissions in data quality control work, and then proposes a "data quality control algorithm" for the average output power prediction of tidal energy power generation devices, which provides reliable data support for constructing a mathematical model of the average output power of tidal energy power generation devices; by grouping and cleaning abnormal data according to the first flow velocity interval and finally reconstructing a target data set with consistent time series, the degree of refinement of data quality control can be improved, and deviations in global outlier detection can be avoided. Traditional methods may lead to misjudgment due to uneven flow velocity distribution (such as less high flow velocity data), while grouping processing can more accurately identify local anomalies. The real physical characteristics of different flow rate ranges are retained (such as large power fluctuations at low flow rates and different noise sources at high flow rates). When eliminating abnormal data, the associated observation time, flow rate, and direction data are simultaneously removed to ensure the integrity of the data record, avoid the involvement of valid tidal data due to a single abnormal power value, and maintain the physical relationship between input (flow rate / direction) and output (power). The first sub-data group after cleaning is reordered by observation time to generate the final target data set, restore the time series characteristics of the data, prevent time gaps caused by data cleaning, and facilitate subsequent model training.

[0085] In another exemplary embodiment of the present application, the matching data set includes observation time data, characteristic tidal flow velocity data within the impeller swept cross-section input to the tidal energy power generation device, characteristic tidal direction data within the impeller swept cross-section input to the tidal energy power generation device, and average output power data of the tidal energy power generation device. The above step 106 can be replaced by the following steps 1061 to 1066:

[0086] Step 1061: Using an odd-even extraction method of data sequence numbers, split the target data set into a first odd-numbered data set and a first even-numbered data set;

[0087] Among them, for the observation time data in the target dataset ( ), tidal characteristic velocity data ( ), tidal characteristic direction data ( ) and average output power data ( ), you can The data for odd numbers are extracted to form a first odd data set ,Will The data when it is an even number is extracted to form a first even number data set .

[0088] The first odd-numbered data set The following may be included: Observation time data ( ), input to the tidal current characteristic velocity data within the sweep cross section of the impeller of the tidal current energy power generation device ( ), the tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device ( ), average output power data of tidal power generation device ( ), Represents the data sequence number in the odd-numbered data set, and its value can be expressed as , is the total number of data in the first odd-numbered data set.

[0089] The first even-numbered data set The following may be included: Observation time data ( ), input into the tidal characteristic velocity data within the swept cross section of the impeller of the tidal energy power generation device ( ), input the tidal characteristic direction data within the swept cross section of the impeller of the tidal energy power generation device ( ), average output power data of tidal power generation device ( ). Represents the data sequence number in the even-numbered data set, and its value can be expressed as , is the total number of data in the first even-numbered data set.

[0090] Step 1062: Divide the first odd-numbered data set according to a preset second flow rate interval to obtain a plurality of second data sets; divide the first even-numbered data set according to the second flow rate interval to obtain a plurality of third data sets;

[0091] The second flow rate interval can be expressed as , can be adjusted at a fixed second flow rate interval , the first odd data set and the first even data set are divided respectively, then the number of the divided second data groups can be calculated by the following formula (7), and the number of the divided third data groups can be calculated by the following formula (8):

[0092] (7);

[0093] (8);

[0094] in, Indicates the first odd data set the total number of second data groups that can be divided, Represents the sequence number of the odd array, and its value can be expressed as . Represents the first even data set the total number of third data groups that can be divided, Indicates the sequence number of the even data group, its value is , . Indicates the first odd data set The maximum tidal flow velocity in Indicates the first odd data set The minimum tidal flow velocity in Represents the first even data set The maximum tidal flow velocity in Represents the first even data set The minimum tidal velocity in The tidal flow velocity range of the second data set can be expressed as , No. The tidal flow velocity range of the third data set can be expressed as . You can follow the first odd data set The tidal characteristic velocity data within the sweep section of the impeller of the tidal energy power generation device ( ), will be The tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device are input one by one ( ) and the average output power data of tidal energy generation devices ( ), divided into the corresponding second data group.

[0095] Similarly, you can also follow the first even data set The tidal characteristic velocity data within the sweep section of the impeller of the tidal energy power generation device ( ), will be The tidal characteristic direction data within the sweep section of the impeller of the tidal energy power generation device are input one by one ( ) and the average output power data of tidal energy generation devices ( ), divided into the corresponding third data group.

[0096] It should be noted that in order to distinguish the first odd data set The obtained second data set is divided into the first even data set The tidal characteristic flow velocity data, tidal characteristic direction data and average output power data obtained in the third data group can be named as the first tidal characteristic flow velocity data, the tidal characteristic direction data in the second data group can be named as the first tidal characteristic direction data, and the average output power data in the second data group can be named as the first average output power data; similarly, the tidal characteristic flow velocity data in the third data group can be named as the second tidal characteristic flow velocity data, the tidal characteristic direction data in the third data group can be named as the second tidal characteristic direction data, and the average output power data in the third data group can be named as the second average output power data.

[0097] Step 1063: Based on the first tidal current characteristic flow velocity data in each second data group, determine the first flow velocity mean value in the corresponding second data group; based on the first tidal current characteristic direction data in each second data group, determine the first coefficient mean value of the utilization coefficient of the tidal current energy resource of the tidal current energy power generation device in the corresponding second data group; based on the first average output power data in each second data group, determine the first power mean value in the corresponding second data group;

[0098] First, each second data group can be calculated as shown in the following formula (9): The first tidal characteristic velocity data ( ) is:

[0099] (9);

[0100] in, Indicates the The first flow velocity mean of the first tidal characteristic flow velocity data of the second data group, Indicates the The number of first tidal characteristic flow velocity data in the second data group, Indicates that it is located at The first tidal characteristic flow velocity data in the second data group.

[0101] Secondly, as shown in the following formula (10), each second data group can be calculated The average value of the utilization coefficient of tidal energy resources by tidal energy power generation devices is:

[0102] (10);

[0103] in, Indicates the The first coefficient average of the utilization coefficient of the tidal energy resource by the tidal energy power generation device in the second data group, Indicates the The number of the first tidal current characteristic velocity data in the second data group, i.e. The number of utilization coefficients of tidal energy resources by tidal energy power generation devices in the second data group, For the The utilization coefficient of tidal energy resources by the tidal energy power generation device in the second data group, The first odd data set The first tidal characteristic direction data ( ) and the acute angle between the swept section of the impeller of the tidal energy power generation device; the utilization coefficient is the utilization coefficient of the tidal energy resources of the tidal energy power generation device calculated on the basis of considering the angular relationship between the tidal characteristic direction data within the swept section of the impeller input into the tidal energy power generation device and the perpendicular to the swept section of the impeller of the tidal energy power generation device, which is crucial for the refined analysis of the energy indicators of the tidal energy resources input into the swept section of the impeller of the tidal energy power generation device.

[0104] Finally, as shown in the following formula (11), each second data group is calculated The first average output power data in ( ) is:

[0105] (11)

[0106] in, Indicates the a first power mean value of the first average output power data in the second data group, Indicates the The number of tidal characteristic velocity data in the second data group, i.e. The first average output power data in the second data group ( ), Indicates that it is located at The first average output power data in the second data group.

[0107] Step 1064: Based on the second tidal current characteristic flow velocity data in each of the third data groups, determine the second flow velocity mean value in the corresponding third data group; based on the second tidal current characteristic direction data in each of the third data groups, determine the second coefficient mean value of the utilization coefficient of the tidal current energy resource of the tidal current energy power generation device in the corresponding third data group; based on the second average output power data in each of the third data groups, determine the second power mean value in the corresponding third data group;

[0108] First, each third data group can be calculated as shown in the following formula (12): The second tidal characteristic velocity data ( ) is:

[0109] (12);

[0110] in, Indicates the The second flow velocity mean of the second tidal characteristic flow velocity data of the third data group, Indicates the The number of the second tidal characteristic flow velocity data in the third data group, Indicates that it is located at The second tidal characteristic flow velocity data in the third data group.

[0111] Secondly, as shown in the following formula (13), each third data group can be calculated The average value of the utilization coefficient of tidal energy resources by tidal energy power generation devices is:

[0112] (13);

[0113] in, Indicates the The second coefficient average of the utilization coefficient of the tidal energy resource by the tidal energy power generation device in the third data group, Indicates the The number of the second tidal characteristic flow velocity data in the third data group, i.e. The number of utilization coefficients of tidal energy resources by tidal energy power generation devices in the third data group, For the The utilization coefficient of tidal energy resources by the tidal energy power generation device in the second data group, The first even data set The second tidal characteristic direction ( ) and the acute angle between the vertical line of the swept section of the impeller of the tidal energy power generation device.

[0114] Finally, as shown in the following formula (14), each third data group is calculated The second average output power in ) is:

[0115] (14);

[0116] in, Indicates the A second power average of the second average output power data in the third data group. Indicates the The number of tidal characteristic velocity data in the third data group, i.e. The second average output power data in the third data group ( ), Indicates that it is located at The second average output power data in the third data group.

[0117] Step 1065: constructing a target odd-numbered data set based on the first flow velocity mean values, the first coefficient mean values, and the first power mean values ​​of a plurality of the second data groups;

[0118] Among them, the The first flow velocity mean of the first tidal characteristic flow velocity data in the second data group ( ), the first coefficient mean of the utilization coefficient of tidal energy resources by tidal energy power generation devices ( ), the first power mean value of the first average output power data of the tidal energy power generation device ( ), according to the first odd data set Sequence number of the divided data group Sort in positive order to construct the initial target odd-numbered data set required to predict the average output power of tidal energy generation devices .

[0119] Step 1066: Construct a target even data set based on the second flow rate mean, the second coefficient mean and the second power mean of multiple third data groups.

[0120] Among them, the The second flow velocity mean of the second tidal characteristic flow velocity data in the third data group ( ), the second coefficient mean of the utilization coefficient of tidal energy resources by tidal energy power generation devices ( ), the second power mean value of the second average output power data of the tidal energy power generation device ( ), according to the first even data set Sequence number of divided data group Sort in positive order to construct the final target even-numbered data set required to predict the average output power of tidal energy generation devices .

[0121] The embodiment of the present application proposes a first coefficient mean value ( ) and the second coefficient mean ( ) calculation method, by introducing the coefficient mean into the established mathematical model of the average output power of the tidal energy power generation device, the influence of the characteristic direction of the tide on the mathematical model of the average output power of the tidal energy power generation device is corrected, making the mathematical model of the average output power of the tidal energy power generation device constructed in this application more scientific and reasonable; first split the data set according to the odd and even serial numbers, and then group them by flow rate interval to calculate the mean (flow rate, utilization coefficient, power). Through group averaging processing, the measurement error and instantaneous fluctuation can be effectively smoothed; the mean values ​​of different flow rate intervals can accurately reflect the energy capture characteristic curve of the impeller; through independent averaging processing of the odd and even data sets, a training set (odd number) and a validation set (even number) are constructed respectively to avoid data leakage, ensure that the validation set is completely independent of the training set, achieve more accurate model evaluation, and the verification result reflects the true generalization ability.

[0122] In another exemplary embodiment of the present application, the above step 108 may be replaced by the following steps 1081 to 1083:

[0123] Step 1081: setting the first power mean as a first dependent variable, and setting the first flow velocity mean and the first coefficient mean as a first independent variable and a second independent variable, respectively;

[0124] Among them, the target odd data set can be The first power mean value of the first average output power data of the medium-current tidal energy power generation device ( ) is set as the dependent variable ( ), the first velocity mean of the first tidal characteristic velocity data ( ) is set as the first independent variable ( ), the first coefficient mean value of the utilization coefficient of tidal energy resources by tidal energy power generation device ( ) is set as the second independent variable ( ).

[0125] Step 1082: Setting a first mathematical expression, and determining a first parameter, a second parameter, and a third parameter in the first mathematical expression based on the first power mean value, the first flow velocity mean value, the first coefficient mean value, and first preset parameters of the tidal energy power generation device;

[0126] The first preset parameter of the tidal energy power generation device may include the average value of the tidal characteristic flow velocity when the tidal energy power generation device starts to generate electricity (i.e., the cut-in flow velocity). ) and the rated flow rate of the tidal energy power generation device ( ), 、 It can be provided by the R&D unit of the tidal energy power generation device, or it can be obtained based on the on-site test results of the power characteristics of the tidal energy power generation device; the first mathematical expression can be set as , in the first mathematical expression are the first, second, and third parameters that need to be determined, and the first independent variable in the first mathematical expression The domain of is: .

[0127] Can be based on the target odd data set Multiple first flow rate averages in ( ), the first coefficient mean corresponding to each first flow velocity mean ( ), the first power mean value of the first average output power data ( ), the Levenberg-Marquardt iterative optimization algorithm is used (the maximum number of iterations of the Levenberg-Marquardt iterative optimization algorithm is set to 400 and the tolerance is set to ), determine the nonlinear mathematical model in parameter.

[0128] It should be noted that the maximum number of iterations of the Levenberg-Marquardt iterative optimization algorithm is set to 400 and the tolerance is set to , mainly to prevent infinite loops, balance accuracy and computational efficiency, and handle special cases where the algorithm cannot converge.

[0129] Step 1083: Based on the second preset parameters of the tidal energy power generation device and the first mathematical expression, construct an initial output power learning model of the tidal energy power generation device.

[0130] Wherein, the second preset parameter of the tidal energy power generation device may include the cut-out flow rate of the tidal energy power generation device ( ) and the rated output power of the tidal energy generation device under rated flow conditions ( ), similarly, and It can be provided by the R&D unit of the tidal energy power generation device, or it can be obtained based on the on-site test results of the power characteristics of the tidal energy power generation device.

[0131] According to the first mathematical expression determined in step 1082 and the step 1082 determined Parameters, and according to the second preset parameters of the tidal energy power generation device, the initial mathematical model of the average output power of the tidal energy power generation device can be determined, as shown in the following formula (15):

[0132] (15);

[0133] like Figure 2As shown, the initial output power learning model can be expressed as curve 21. When the parameters are determined and the mean value of the first coefficient remains unchanged, curve 21 reflects the corresponding relationship between the first independent variable (i.e., the first flow velocity mean) and the first dependent variable (i.e., the first power mean). R squared is a fitting degree indicator, which is used to reflect the explanatory power of curve 21 on the data.

[0134] In an embodiment of the present application, the first flow velocity mean and the first coefficient mean are used as independent variables, a first preset parameter is introduced to constrain the first mathematical expression, and an initial output power learning model of the tidal energy power generation device is constructed based on the first mathematical expression and the second preset parameters, thereby enhancing the credibility of the model.

[0135] In another exemplary embodiment of the present application, the above step 110 may be replaced by the following steps 1101 to 1105:

[0136] Step 1101: inputting the second flow rate mean and the second coefficient mean into the initial output power learning model to obtain a third power mean output by the initial output power learning model;

[0137] Among them, the target even data set can be The second flow velocity mean of the second tidal characteristic flow velocity in each third data group ( ) and the second coefficient mean of the utilization coefficient of tidal energy resources by tidal energy power generation devices ( ) are substituted into formula (15) and , obtain the third power mean value calculated by applying the initial output power learning model in each third data group ( );like Figure 3 As shown, it is a schematic diagram of the average output power predicted by the initial output power learning model. The second power mean is calculated based on the actual output power of the tidal energy power generation device. In order to distinguish it from the second power mean, the average output power predicted by the initial output power learning model can be named as the third power mean. The initial output power learning model causes some predicted average output power data points to be located below the horizontal line where the average output power is zero, which obviously requires the initial output power learning model to be corrected.

[0138] Step 1102: Determine a correction coefficient of the initial output power learning model based on the second power average value and the third power average value;

[0139] Using the calculated third power mean and target even dataset The second power mean of the second average output power of the tidal energy power generation device in each third data group ( ), calculate the correction coefficient of the initial output power learning model in each third data group ( ), which is calculated as shown in the following formula (16):

[0140] (16);

[0141] like Figure 4 As shown, according to the correction coefficient calculation method proposed in this application, the correction coefficient of the initial output power learning model can be calculated. Since the second flow rate mean, second coefficient mean and second power mean in different third data groups may be different, each of the third data groups corresponds to a correction coefficient.

[0142] Step 1103: setting the correction coefficient as a second dependent variable, and setting the second flow velocity mean as a third independent variable;

[0143] The correction coefficient obtained in step 1102 ( ) is set as the second dependent variable ( ), the second flow velocity mean of the second tidal characteristic flow velocity in each third data group ( ) is set as the third independent variable ( ).

[0144] Step 1104: setting a second mathematical expression, and determining a fourth parameter, a fifth parameter, and a sixth parameter in the second mathematical expression based on the correction coefficient and the second flow velocity mean;

[0145] As shown in the following formula (17), a nonlinear mathematical relationship (i.e., a second mathematical expression) between the correction coefficient and the second flow velocity mean of the second tidal characteristic flow velocity can be constructed:

[0146] (17);

[0147] in, are the fourth, fifth and sixth parameters that need to be determined respectively, which can be determined according to the correction coefficient ( ) and the second velocity mean of the second tidal characteristic velocity in each third data group ( ), using the mathematical method of polynomial fitting, determine the parameter.

[0148] like Figure 5 As shown, according to the correction coefficient fitting method proposed in this application, a nonlinear mathematical relationship (ie, a second mathematical expression) 31 between the correction coefficient and the second flow velocity mean value can be obtained.

[0149] Step 1105: Based on the second mathematical expression, the initial output power learning model is modified to obtain a target output power learning model.

[0150] The target output power learning model can also be called the final mathematical model of the average output power of the tidal energy power generation device, and the second power mean of the second average output power of the tidal energy power generation device predicted in each third data group can be set as the first dependent variable , set the second velocity mean of the second tidal characteristic velocity in each third data group as the first independent variable The second coefficient mean of the utilization coefficient of the tidal energy resource by the tidal energy power generation device in each third data group is set as the second independent variable .

[0151] Set 、 、 Substituting them into formula (15) respectively, and using the second mathematical expression to correct the initial output power learning model, the final mathematical model of the average output power of the tidal energy power generation device can be obtained, and its mathematical expression is shown in the following formula (18):

[0152] (18);

[0153] like Figure 6 As shown, the average output power predicted by the target output power learning model can be obtained, and the average output power predicted by the target output power learning model can be named as the fourth power mean, as shown Figure 7 As shown, the average output power predicted by the target output power learning model can be compared with the average output power predicted by the initial output power learning model. As shown in Table 1 below, it is a comparison table of the average output power prediction results of the initial output power learning model and the target output power learning model.

[0154] Table 1 Comparison of the average output power prediction results of the initial mathematical model and the final mathematical model

[0155]

[0156] It can be seen from Table 1 above that the average output power predicted by the target output power learning model is closer to the actual average output power of the tidal energy power generation device, and the prediction result is more accurate.

[0157] In the embodiments of the present application, the limitations of the initial constructed mathematical model of the average output power of the tidal energy power generation device on the prediction results of the average output power of the tidal energy power generation device are studied, and a calculation method for the "correction coefficient of the initial mathematical model of the average output power of the tidal energy power generation device" is proposed, which improves the accuracy of the final constructed mathematical model of the average output power of the tidal energy power generation device. The calculation results in Table 1 also prove that the accuracy of the final constructed mathematical model of the average output power of the tidal energy power generation device is improved.

[0158] The embodiment of the present application proposes a fitting method for a nonlinear mathematical expression between a correction coefficient and the second flow velocity mean of the second tidal characteristic flow velocity data, and then determines a mathematical expression between the correction coefficient and the mean of the tidal characteristic flow velocity, making it possible to determine the correction coefficient of the tidal energy power generation device in any flow velocity data group. Furthermore, based on the determined mathematical expression between the correction coefficient and the mean of the tidal characteristic flow velocity, the initial mathematical model of the average output power of the tidal energy power generation device is corrected, and the construction of the final mathematical model of the average output power of the tidal energy power generation device is completed, forming a method for predicting the average output power of the tidal energy power generation device; by establishing an error compensation mechanism, the accuracy and robustness of the output power prediction model of the tidal energy power generation device are significantly improved.

[0159] In another exemplary embodiment of the present application, the output power prediction method of the tidal energy power generation device further includes:

[0160] Step 111: Acquire second tidal current observation data of the test sea area, where the second tidal current observation data is impeller swept cross-section characteristic data currently input to the tidal current energy power generation device;

[0161] The second tidal current observation data may be the observation time data obtained at the current moment ( ), the tidal characteristic velocity data within the sweep cross section of the impeller of the tidal energy power generation device ( ), the tidal current characteristic direction data within the sweep cross section of the impeller of the tidal current energy power generation device ( ); where i is the serial number of the tidal observation data, and its value can be expressed as , O is the total number of tidal flow observation data.

[0162] Step 112: Input the second tidal current observation data into the target output power learning model to obtain the average output power of the tidal current energy power generation device output by the target output power learning model.

[0163] Among them, the newly acquired second flow observation data can be input into the trained target output power learning model, and the target output power learning model outputs the predicted average output power; it should be noted that the target output power learning model can also be continuously updated by the second flow observation data and the actual average output power to realize dynamic update of the target output power learning model.

[0164] Based on the same inventive concept, embodiments of the present application also provide an output power prediction device for a tidal energy power generation device for implementing the aforementioned method for predicting the output power of a tidal energy power generation device. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the embodiments of the output power prediction device for one or more tidal energy power generation devices provided below can be found in the above-mentioned limitations of the optimization scheduling method and will not be repeated here.

[0165] In an exemplary embodiment, Figure 8 As shown, an output power prediction device 400 of a tidal energy power generation device is provided, comprising:

[0166] Establishing module 401, for establishing a matching data set between first tidal current observation data of a test sea area and average output power data of a tidal current energy power generation device;

[0167] The processing module 402 is configured to perform data quality control on the matching data set to remove abnormal data in the matching data set and obtain a target data set;

[0168] A first constructing module 403 is configured to construct a target odd-numbered data set and a target even-numbered data set based on the target data set by using an odd-even extraction method of data sequence numbers;

[0169] A second building module 404 is configured to build an initial output power learning model of the tidal energy power generation device based on the target odd-numbered data set;

[0170] The correction module 405 is used to correct the initial output power learning model based on the target even-numbered data set to obtain a target output power learning model, and perform output power prediction of the tidal energy power generation device based on the target output power learning model.

[0171] Illustratively, the output power prediction device 400 of the tidal energy power generation device may be a component of the tidal energy power generation device itself. In some embodiments, the output power prediction device 400 of the tidal energy power generation device may also be a device independent of the tidal energy power generation device.

[0172] As an optional implementation, the establishment module 401 includes: a first acquisition submodule, used to acquire the original tidal observation data of the test sea area, and perform spatial conversion processing on the original tidal observation data to obtain first tidal observation data, wherein the original tidal observation data is the vertical profile data of the test sea area at a historical moment, and the first tidal observation data is the impeller swept section characteristic data input into the tidal energy power generation device at a historical moment; a second acquisition submodule, used to acquire the original output power measurement data of the tidal energy power generation device, and perform mean processing on the original output power measurement data to obtain the average output power data of the tidal energy power generation device; a matching submodule, used to match the first tidal observation data and the average output power data to obtain a matching data set.

[0173] As an optional embodiment, the matching data set includes observation time data, tidal characteristic flow velocity data within the impeller swept section range input into the tidal energy power generation device, tidal characteristic direction data within the impeller swept section range input into the tidal energy power generation device, and average output power data of the tidal energy power generation device. The processing module 402 includes: a first division submodule, used to divide the matching data set according to a preset first flow velocity interval to obtain multiple first data groups; a processing submodule, used to use a data quality control algorithm to perform data quality control processing on the average output power data in each of the first data groups to eliminate abnormal output power data in the corresponding first data group and the observation time data, tidal characteristic flow velocity data and tidal characteristic direction data corresponding to the abnormal output power data, to obtain the corresponding first sub-data group; a sorting submodule, used to sort the multiple first sub-data groups according to the observation time data to obtain the target data set.

[0174] As an optional implementation, the matching data set includes observation time data, tidal characteristic velocity data within the swept cross-section of the impeller input to the tidal energy power generation device, tidal characteristic direction data within the swept cross-section of the impeller input to the tidal energy power generation device, and average output power data of the tidal energy power generation device. The first construction module 403 includes: a splitting submodule for splitting the target data set into a first odd data set and a first even data set by using an odd-even extraction method of a data sequence number; a second division submodule for dividing the first odd data set according to a preset second flow velocity interval to obtain a plurality of second data groups; according to the second flow velocity interval, The first even-numbered data set is divided to obtain a plurality of third data groups; a first determining submodule is used to determine the first flow velocity mean in the corresponding second data group based on the first tidal characteristic flow velocity data in each of the second data groups; based on the first tidal characteristic direction data in each of the second data groups, a first coefficient mean of the utilization coefficient of the tidal energy resource of the tidal energy power generation device in the corresponding second data group is determined; based on the first average output power data in each of the second data groups, a first power mean in the corresponding second data group is determined; a second determining submodule is used to determine the first power mean in the corresponding third data group based on the second tidal characteristic flow velocity data in each of the third data groups two flow velocity means; based on the second tidal characteristic direction data in each of the third data groups, determine the second coefficient mean of the utilization coefficient of the tidal energy resources of the tidal energy power generation device in the corresponding third data group; based on the second average output power data in each of the third data groups, determine the second power mean in the corresponding third data group; a first construction submodule, for constructing a target odd data set based on the first flow velocity mean, the first coefficient mean and the first power mean of multiple second data groups; a second construction submodule, for constructing a target even data set based on the second flow velocity mean, the second coefficient mean and the second power mean of multiple third data groups.

[0175] As an optional embodiment, the second construction module 404 includes: a first setting submodule, used to set the first power mean as the first dependent variable, and set the first flow velocity mean and the first coefficient mean as the first independent variable and the second independent variable, respectively; a second setting submodule, used to set a first mathematical expression, and determine the first parameter, second parameter and third parameter in the first mathematical expression based on the first power mean, the first flow velocity mean, the first coefficient mean and the first preset parameters of the tidal energy power generation device; a third construction submodule, used to construct an initial output power learning model of the tidal energy power generation device based on the second preset parameters of the tidal energy power generation device and the first mathematical expression.

[0176] As an optional embodiment, the correction module 405 includes: a third acquisition submodule, used to input the second flow rate mean and the second coefficient mean into the initial output power learning model to obtain the third power mean output by the initial output power learning model; a third determination submodule, used to determine the correction coefficient of the initial output power learning model based on the second power mean and the third power mean; a third setting submodule, used to set the correction coefficient as the second dependent variable and the second flow rate mean as the third independent variable; a fourth setting submodule, used to set a second mathematical expression and determine the fourth parameter, fifth parameter and sixth parameter in the second mathematical expression based on the correction coefficient and the second flow rate mean; a correction submodule, used to correct the initial output power learning model based on the second mathematical expression to obtain a target output power learning model.

[0177] As an optional embodiment, the device also includes: a first acquisition module, used to obtain second tidal observation data of the test sea area, where the second tidal observation data is the impeller swept section characteristic data input into the tidal energy power generation device at the current moment; a second acquisition module, used to input the second tidal observation data into the target output power learning model to obtain the average output power of the tidal energy power generation device output by the target output power learning model.

[0178] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes an output power prediction method of a tidal energy power generation device.

[0179] Those skilled in the art will understand that Figure 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0180] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0181] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0182] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0183] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0184] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0185] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for predicting the output power of a tidal energy power generation device, characterized in that: The output power prediction method of the tidal energy power generation device includes: Establishing a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device; Performing data quality control on the matching data set to remove abnormal data in the matching data set to obtain a target data set; Based on the target data set, a target odd-numbered data set and a target even-numbered data set are constructed using an odd-numbered and even-numbered data set extraction method of data sequence numbers; Based on the target odd-numbered data set, constructing an initial output power learning model of the tidal energy power generation device; Based on the target even-numbered data set, the initial output power learning model is modified to obtain a target output power learning model, and the output power of the tidal energy power generation device is predicted based on the target output power learning model; The matching data set includes observation time data, characteristic tidal flow velocity data within the sweep cross section of the impeller input to the tidal energy power generation device, characteristic tidal direction data within the sweep cross section of the impeller input to the tidal energy power generation device, and average output power data of the tidal energy power generation device. The method of constructing a target odd-numbered data set and a target even-numbered data set based on the target data set by using an odd-numbered and even-numbered data set extraction method of data sequence numbers includes: Using an odd-even extraction method of data sequence numbers, the target data set is split into a first odd-numbered data set and a first even-numbered data set; Dividing the first odd-numbered data set according to a preset second flow rate interval to obtain a plurality of second data groups; dividing the first even-numbered data set according to the second flow rate interval to obtain a plurality of third data groups; Based on the first tidal current characteristic flow velocity data in each of the second data groups, determining a first flow velocity mean value in the corresponding second data group; based on the first tidal current characteristic direction data in each of the second data groups, determining a first coefficient mean value of a utilization coefficient of tidal current energy resources by the tidal current energy power generation device in the corresponding second data group; based on the first average output power data in each of the second data groups, determining a first power mean value in the corresponding second data group; Based on the second tidal current characteristic flow velocity data in each of the third data groups, determining a second flow velocity mean value in the corresponding third data group; based on the second tidal current characteristic direction data in each of the third data groups, determining a second coefficient mean value of the utilization coefficient of the tidal current energy resource of the tidal current energy power generation device in the corresponding third data group; based on the second average output power data in each of the third data groups, determining a second power mean value in the corresponding third data group; constructing a target odd-numbered data set based on the first flow velocity mean values, the first coefficient mean values, and the first power mean values ​​of a plurality of the second data groups; constructing a target even-numbered data set based on the second flow velocity means, the second coefficient means, and the second power means of a plurality of the third data groups; The constructing of an initial output power learning model of the tidal energy power generation device based on the target odd-numbered data set includes: Setting the first power mean as a first dependent variable, and setting the first flow velocity mean and the first coefficient mean as a first independent variable and a second independent variable respectively; Setting a first mathematical expression, and determining a first parameter, a second parameter, and a third parameter in the first mathematical expression based on the first power mean value, the first flow velocity mean value, the first coefficient mean value, and a first preset parameter of the tidal energy power generation device; constructing an initial output power learning model of the tidal energy power generation device based on a second preset parameter of the tidal energy power generation device and the first mathematical expression; The step of modifying the initial output power learning model based on the target even-numbered data set to obtain a target output power learning model includes: Inputting the second flow rate mean and the second coefficient mean into the initial output power learning model to obtain a third power mean output by the initial output power learning model; determining a correction coefficient of the initial output power learning model based on the second power mean and the third power mean; Setting the correction coefficient as a second dependent variable and setting the second flow velocity mean as a third independent variable; Setting a second mathematical expression, and determining a fourth parameter, a fifth parameter, and a sixth parameter in the second mathematical expression based on the correction coefficient and the second flow velocity mean value; Based on the second mathematical expression, the initial output power learning model is modified to obtain a target output power learning model.

2. The method for predicting the output power of a tidal energy power generation device according to claim 1, characterized in that: The step of establishing a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device includes: Obtaining original tidal current observation data of the test sea area, performing spatial conversion processing on the original tidal current observation data to obtain first tidal current observation data, wherein the original tidal current observation data is vertical profile data of the test sea area at a historical moment, and the first tidal current observation data is impeller swept cross-section characteristic data input to the tidal current energy power generation device at a historical moment; Obtaining original output power measurement data of the tidal energy power generation device, performing mean processing on the original output power measurement data, and obtaining average output power data of the tidal energy power generation device; The first power flow observation data and the average output power data are matched to obtain a matching data set.

3. The method for predicting the output power of a tidal energy power generation device according to claim 1, characterized in that: The matching data set includes observation time data, characteristic tidal flow velocity data within the impeller swept cross-section of the tidal energy power generation device, characteristic tidal direction data within the impeller swept cross-section of the tidal energy power generation device, and average output power data of the tidal energy power generation device. The matching data set is subjected to data quality control processing to eliminate abnormal data in the matching data set to obtain a target data set, including: Dividing the matching data set according to a preset first flow rate interval to obtain a plurality of first data groups; Using a data quality control algorithm, performing data quality control processing on the average output power data in each of the first data groups to eliminate abnormal output power data in the corresponding first data group and the observation time data, tidal characteristic flow velocity data, and tidal characteristic direction data corresponding to the abnormal output power data, to obtain a corresponding first sub-data group; The plurality of first sub-data groups are sorted according to the observation time data to obtain a target data set.

4. The method for predicting the output power of a tidal energy power generation device according to any one of claims 1 to 3, characterized in that: The output power prediction method of the tidal energy power generation device further includes: Acquiring second tidal current observation data of the test sea area, where the second tidal current observation data is impeller swept cross-section characteristic data currently input to the tidal current energy power generation device; The second tidal current observation data is input into the target output power learning model to obtain the average output power of the tidal current energy power generation device output by the target output power learning model.

5. An output power prediction device for a tidal energy power generation device, characterized in that: The output power prediction device of the tidal energy power generation device includes: An establishment module is used to establish a matching data set between the first tidal current observation data of the test sea area and the average output power data of the tidal current energy power generation device; a processing module, configured to perform data quality control processing on the matching data set to remove abnormal data in the matching data set and obtain a target data set; A first construction module is configured to construct a target odd-numbered data set and a target even-numbered data set based on the target data set by using an odd-even extraction method of data sequence numbers; A second building module is used to build an initial output power learning model of the tidal energy power generation device based on the target odd-numbered data set; a correction module, configured to correct the initial output power learning model based on the target even-numbered data set to obtain a target output power learning model, and perform output power prediction of the tidal energy power generation device based on the target output power learning model; The matching data set includes observation time data, characteristic tidal flow velocity data within the sweep cross section of the impeller input to the tidal energy power generation device, characteristic tidal direction data within the sweep cross section of the impeller input to the tidal energy power generation device, and average output power data of the tidal energy power generation device; The first building block is specifically configured to: Using an odd-even extraction method of data sequence numbers, the target data set is split into a first odd-numbered data set and a first even-numbered data set; Dividing the first odd-numbered data set according to a preset second flow rate interval to obtain a plurality of second data groups; dividing the first even-numbered data set according to the second flow rate interval to obtain a plurality of third data groups; Based on the first tidal current characteristic flow velocity data in each of the second data groups, determining a first flow velocity mean value in the corresponding second data group; based on the first tidal current characteristic direction data in each of the second data groups, determining a first coefficient mean value of a utilization coefficient of tidal current energy resources by the tidal current energy power generation device in the corresponding second data group; based on the first average output power data in each of the second data groups, determining a first power mean value in the corresponding second data group; Based on the second tidal current characteristic flow velocity data in each of the third data groups, determining a second flow velocity mean value in the corresponding third data group; based on the second tidal current characteristic direction data in each of the third data groups, determining a second coefficient mean value of the utilization coefficient of the tidal current energy resource of the tidal current energy power generation device in the corresponding third data group; based on the second average output power data in each of the third data groups, determining a second power mean value in the corresponding third data group; constructing a target odd-numbered data set based on the first flow velocity mean values, the first coefficient mean values, and the first power mean values ​​of a plurality of the second data groups; constructing a target even-numbered data set based on the second flow velocity means, the second coefficient means, and the second power means of a plurality of the third data groups; The second building block is specifically configured to: Setting the first power mean as a first dependent variable, and setting the first flow velocity mean and the first coefficient mean as a first independent variable and a second independent variable respectively; Setting a first mathematical expression, and determining a first parameter, a second parameter, and a third parameter in the first mathematical expression based on the first power mean value, the first flow velocity mean value, the first coefficient mean value, and a first preset parameter of the tidal energy power generation device; constructing an initial output power learning model of the tidal energy power generation device based on a second preset parameter of the tidal energy power generation device and the first mathematical expression; The correction module is specifically used to: Inputting the second flow rate mean and the second coefficient mean into the initial output power learning model to obtain a third power mean output by the initial output power learning model; determining a correction coefficient of the initial output power learning model based on the second power mean and the third power mean; Setting the correction coefficient as a second dependent variable and setting the second flow velocity mean as a third independent variable; Setting a second mathematical expression, and determining a fourth parameter, a fifth parameter, and a sixth parameter in the second mathematical expression based on the correction coefficient and the second flow velocity mean value; Based on the second mathematical expression, the initial output power learning model is modified to obtain a target output power learning model.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting the output power of a tidal energy power generation device according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the output power of a tidal energy power generation device according to any one of claims 1 to 4 are implemented.

Images