Sea area water taking point determination method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of power plant sea area water taking point selection, in particular to a sea area water taking point determination method and device, electronic equipment and a storage medium, and discloses a sea area water taking point determination method which comprises the steps of firstly obtaining a plurality of sea condition data sets; secondly, for each alternative water taking point, clustering the plurality of sea condition records into a plurality of sea condition classes according to similarity; according to the correspondence between the factor data records and the sea condition classes, utilizing the factor data records extracted from the sea condition data set to construct a plurality of sea condition evaluation models; and finally, according to historical extreme factor data and the plurality of sea condition evaluation models, evaluating the plurality of alternative water taking points, and according to a sea condition estimation result, selecting a target water taking point from the plurality of alternative water taking points. According to the method, a relatively accurate extreme sea condition evaluation result can be obtained without a large amount of data operation or training, and the method is suitable for obtaining a relatively accurate sea area water taking point selection scene under relatively low resource investment.

Description

Technical Field

[0001] The present invention relates to the technical field of selecting water intake points in sea areas of power plants, and in particular to a method, device, electronic equipment and storage medium for determining water intake points in sea areas. Background Art

[0002] Fuel-fired power generation units built along the coast usually draw water from nearby sea areas. After desalination, the seawater is used to cool the generator units. The selection of water intake points should ensure the stability of the water source and the safety of water intake.

[0003] The sea conditions that affect the selection of water intake points usually include: tidal change characteristics, tidal current characteristics, wave characteristics, and sea water temperature. It can be seen that the sea conditions that affect the selection of water intake points are multi-dimensional characteristics, and the above multiple dimensions influence each other.

[0004] At present, the mainstream method of selecting water intake points is to select water intake points in the sea area based on survey and observation results. This selection method is insufficient for the risk assessment that may be encountered in the long term in the future. Some construction units with conditions will work with water conservancy research units or universities to model sea conditions and assess the risks faced in the future, so as to find a more ideal sea water intake point. Since the formation mechanism of sea conditions is relatively complex and is greatly affected by geographical conditions, modeling usually requires a large amount of survey and observation results, which takes a long time and is costly.

[0005] Based on this, it is necessary to develop and design a method for determining water intake points in sea areas. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining a sea area water intake point, which are used to solve the problem of investing a lot of resources in selecting a more reliable sea area water intake point in the prior art.

[0007] In a first aspect, an embodiment of the present invention provides a method for determining a sea area water intake point, comprising:

[0008] Acquire multiple sea state data sets, wherein each sea state data set corresponds to an alternative water selection point, the sea state data set includes multiple sea state records and multiple groups of factor data records, and each sea state record corresponds to a group of factor data records;

[0009] For each alternative water selection point, multiple sea state records are clustered into multiple sea state classes based on similarity;

[0010] According to the correspondence between the factor data records and the sea state classes, multiple sea state assessment models are constructed using the factor data records extracted from the sea state data set, wherein each sea state assessment model corresponds to an alternative water selection point, and the sea state assessment model outputs a sea state estimation according to the factor data;

[0011] Based on the historical extreme factor data and the multiple sea condition assessment models, multiple alternative water intake points are evaluated, and a target water intake point is selected from the multiple alternative water intake points based on the sea condition estimation result.

[0012] In a possible implementation, for each candidate water selection point, a plurality of sea state records are clustered into a plurality of sea state classes according to similarity, including:

[0013] Get the number of clusters;

[0014] Randomly selecting the clustered number of sea state records from the plurality of sea state records as a plurality of target sea state records;

[0015] Classifying each sea state record into the most similar target sea state record to obtain a plurality of first sea state classes;

[0016] Extracting the class center of each first sea condition class to obtain multiple sea condition class centers;

[0017] Calculate the similarity between each sea state class center and the target sea state record to obtain multiple first similarity values;

[0018] If there is a value lower than the similarity threshold value among the multiple first similarity values, the multiple sea state class centers are used as the multiple target sea state records, and the process jumps to the step of classifying each sea state record into the most similar target sea state record to obtain multiple first sea state classes;

[0019] Extracting the lowest similarity value of each first sea state class, wherein the lowest similarity value is the first similarity value of the sea state record with the lowest similarity to the sea state class center in the first sea state class;

[0020] If there is a similarity value lower than the central similarity threshold among the lowest similarity values ​​of the multiple first sea condition classes, the number of clusters is adjusted, and the process jumps to the step of randomly selecting the sea condition records of the cluster number from the multiple sea condition records as the multiple target sea condition records.

[0021] In a possible implementation, the calculating the similarity between each sea state class center and the target sea state record to obtain a plurality of first similarity values ​​includes:

[0022] Arranging multiple record values ​​of each target sea state record in a predetermined order to construct a first vector;

[0023] The similarity between each sea condition class center and the target sea condition record is calculated according to the first formula to obtain multiple first similarity values, wherein the first formula is:

[0024]

[0025] Where E is the first similarity value, cnMax is the total number of elements in the first vector, and ARC is cn is the cnth element of the sea state class center, ARD cn It is the c□th element of the target sea condition record.

[0026] In a possible implementation, the constructing of multiple sea condition assessment models using factor data records extracted from a sea condition data set according to the correspondence between the factor data records and the sea condition classes includes:

[0027] For each alternative water selection point, perform the following steps:

[0028] constructing each group of factor data records into a second vector according to a predetermined factor arrangement order;

[0029] Performing dimension increase on each second vector by means of polynomial regression to obtain a plurality of third vectors, wherein each third vector corresponds to a set of factor data records;

[0030] Substituting the plurality of third vectors into a linear transformation model respectively to obtain a plurality of first results, wherein the linear transformation model includes a plurality of coefficients;

[0031] Sorting the plurality of first results, and dividing the plurality of first results into a first number of intervals according to the sorting, wherein the first number is the number of the plurality of sea condition classes;

[0032] According to the interval to which the first result belongs, the plurality of groups of factor data records are grouped into a plurality of factor classes;

[0033] Verifying the classification deviations of the plurality of factor classes and the plurality of sea condition classes according to the correspondence between the factor data records and the sea condition records;

[0034] If the classification deviation is greater than the classification deviation threshold, adjusting the multiple coefficients of the linear transformation model according to the classification deviation, and jumping to the step of substituting the multiple third vectors into the linear transformation model respectively to obtain multiple first result vectors;

[0035] Otherwise, the linear transformation model is used as the sea state assessment model.

[0036] In a possible implementation, the step of performing dimension increase on each second vector by means of polynomial regression to obtain multiple third vectors includes:

[0037] Each second vector is dimensionally increased according to the second formula to obtain multiple third vectors, wherein the second formula is:

[0038]

[0039] Where AF3，cm is the cm-th element of the third vector, F 2，in is the inth element of the second vector, W in is the inth first coefficient, ckMax is the total number of elements in the second vector, mod() is the remainder function, and int() is the integer function;

[0040] The linear transformation model is:

[0041]

[0042] Where SC is the evaluation result of the linear transformation model on the sea conditions, w cm is the cm-th second coefficient, AF cm is the cm-th element of the input vector, cmMax is the total number of input vector elements, and b1 is the first bias coefficient.

[0043] In a possible implementation manner, adjusting the multiple coefficients of the linear conversion model according to the classification deviation includes:

[0044] The multiple coefficients of the linear conversion model are adjusted according to a third formula, wherein the third formula is:

[0045]

[0046] In the formula, is the i-th coefficient of the adjusted linear transformation model, is the i-th coefficient of the linear conversion model before adjustment, k is the adjustment ratio, Bias is the classification bias, cmMax is the total number of elements in the third vector, and b2 is the second bias coefficient.

[0047] In a possible implementation, the evaluating of multiple alternative water selection points based on the historical extreme factor data and the multiple sea condition evaluation models includes:

[0048] For each alternative water selection point, perform the following steps:

[0049] Inputting the historical extreme factor data into a sea condition assessment model for alternative water selection points to obtain a second result;

[0050] Find a first result closest to the second result from the multiple first results as the third result;

[0051] Finding a first result closest to a target difference from the multiple first results as the fourth result, wherein the target difference is a difference between the second result and the third result;

[0052] Extracting the class center of the sea condition class corresponding to the third result and the class center of the sea condition class corresponding to the fourth result as the first reference sea condition and the second reference sea condition;

[0053] The extreme sea conditions of the alternative water selection points are determined according to the first reference sea condition and the second reference sea condition.

[0054] In a second aspect, an embodiment of the present invention provides a device for determining a sea area water intake point, which is used to implement the method for determining a sea area water intake point as described in the first aspect or any possible implementation of the first aspect, and the device for determining a sea area water intake point includes:

[0055] A sea state record acquisition module is used to acquire multiple sea state data sets, wherein each sea state data set corresponds to an alternative water selection point, and the sea state data set includes multiple sea state records and multiple groups of factor data records, and each sea state record corresponds to a group of factor data records;

[0056] A sea state clustering module is used to cluster multiple sea state records into multiple sea state classes according to similarity for each alternative water selection point;

[0057] A sea state assessment model building module is used to build multiple sea state assessment models using factor data records extracted from a sea state data set according to the correspondence between factor data records and sea state classes, wherein each sea state assessment model corresponds to an alternative water selection point, and the sea state assessment model outputs a sea state estimate according to the factor data;

[0058] as well as,

[0059] The water intake point determination module is used to evaluate multiple alternative water intake points based on historical extreme factor data and the multiple sea condition assessment models, and select a target water intake point from the multiple alternative water intake points based on the sea condition estimation result.

[0060] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation method of the first aspect.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0062] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0063] The embodiment of the present invention discloses a method for determining a water intake point in a sea area, which first obtains multiple sea condition data sets, wherein each sea condition data set corresponds to an alternative water intake point, the sea condition data set includes multiple sea condition records and multiple groups of factor data records, and each sea condition record corresponds to a group of factor data records; then for each alternative water intake point, the multiple sea condition records are clustered into multiple sea condition classes according to similarity; then, according to the correspondence between the factor data records and the sea condition classes, multiple sea condition assessment models are constructed using the factor data records extracted from the sea condition data set, wherein each sea condition assessment model corresponds to an alternative water intake point, and the sea condition assessment model outputs a sea condition estimation according to the factor data; finally, according to the historical extreme factor data and the multiple sea condition assessment models, the multiple alternative water intake points are evaluated, and a target water intake point is selected from the multiple alternative water intake points according to the sea condition estimation result. The implementation mode of the present invention completes the construction of the sea condition assessment model based on the clustering of sea condition records and the evaluation value output by the linear model according to the factor data records. The construction process requires a small amount of preliminary data and does not require a large amount of data calculation or training to obtain relatively accurate extreme sea condition assessment results. It is suitable for obtaining relatively accurate sea area water intake point selection scenarios with less resource investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0065] Figure 1 It is a flow chart of a method for determining a sea area water intake point provided by an embodiment of the present invention;

[0066] Figure 2 It is a schematic diagram of a process of aggregating sea condition records into multiple sea condition categories provided by an embodiment of the present invention;

[0067] Figure 3 It is a schematic diagram of a process of upgrading the dimension of factor data records, outputting results through a linear transformation model, and classifying the factor data records according to the output results provided by an embodiment of the present invention;

[0068] Figure 4 It is a schematic diagram of adjusting the current conversion model according to the deviation between the classification result of the factor data record and the sea condition class provided by the embodiment of the present invention;

[0069] Figure 5 It is a functional block diagram of a device for determining a water intake point in a sea area provided in an embodiment of the present invention;

[0070] Figure 6It is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0072] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0073] The following is a detailed description of an embodiment of the present invention. This example is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0074] Figure 1 A flow chart of a method for determining a sea area water intake point provided in an embodiment of the present invention.

[0075] like Figure 1 As shown, it shows a flow chart of the implementation of the method for determining the sea area water intake point provided by an embodiment of the present invention, which is described in detail as follows:

[0076] In step 101, a plurality of sea state data sets are obtained, wherein each sea state data set corresponds to an alternative water selection point, the sea state data set includes a plurality of sea state records and a plurality of groups of factor data records, and each sea state record corresponds to a group of factor data records.

[0077] Exemplarily, the implementation method of the present invention collects sea condition data for each alternative watering point, for example, collects the water level, flow rate, wave height and water temperature of the sea condition to form a sea condition record. At the same time, some factor data affecting the sea condition are recorded, such as wind speed, temperature, and in some scenarios, the movement of celestial bodies may also be included. These factor data form factor data records. In other words, the sea condition record and the factor data record are collected based on the same time period and have temporal correspondence. Multiple sea condition records and multiple factor records are enough to form a sea condition data set for alternative watering points.

[0078] In step 102, for each candidate water selection point, multiple sea state records are clustered into multiple sea state classes according to similarity.

[0079] In some embodiments, for each candidate water selection point, clustering multiple sea state records into multiple sea state classes according to similarity includes:

[0080] Get the number of clusters;

[0081] Randomly selecting the clustered number of sea state records from the plurality of sea state records as a plurality of target sea state records;

[0082] Classifying each sea state record into the most similar target sea state record to obtain a plurality of first sea state classes;

[0083] Extracting the class center of each first sea condition class to obtain multiple sea condition class centers;

[0084] Calculate the similarity between each sea state class center and the target sea state record to obtain multiple first similarity values;

[0085] If there is a value lower than the similarity threshold value among the multiple first similarity values, the multiple sea state class centers are used as the multiple target sea state records, and the process jumps to the step of classifying each sea state record into the most similar target sea state record to obtain multiple first sea state classes;

[0086] Extracting the lowest similarity value of each first sea state class, wherein the lowest similarity value is the first similarity value of the sea state record with the lowest similarity to the sea state class center in the first sea state class;

[0087] If there is a similarity value lower than the central similarity threshold among the lowest similarity values ​​of the multiple first sea condition classes, the number of clusters is adjusted, and the process jumps to the step of randomly selecting the sea condition records of the cluster number from the multiple sea condition records as the multiple target sea condition records.

[0088] In some embodiments, calculating the similarity between each sea state class center and the target sea state record to obtain a plurality of first similarity values ​​includes:

[0089] Arranging multiple record values ​​of each target sea state record in a predetermined order to construct a first vector;

[0090] The similarity between each sea condition class center and the target sea condition record is calculated according to the first formula to obtain multiple first similarity values, wherein the first formula is:

[0091]

[0092] Where E is the first similarity value, cnMax is the total number of elements in the first vector, and ARC is cn is the cnth element of the sea state class center, ARD cn It is the cnth element of the target sea state record.

[0093] Exemplarily, the present invention clusters the sea state records of each candidate water selection point to form multiple classes, and the deviations between the sea state records in the class are controlled within a predetermined range, the purpose of which is to facilitate the construction of a linear model to complete the mapping of the sea state. In other words, the factor data records are mapped to the class through a linear equation.

[0094] like Figure 2 As shown, each data set sea condition data set includes multiple one-to-one corresponding multiple sea condition records 201 and multiple groups of factor data records 202, wherein the multiple sea condition records 201 are clustered into multiple first sea condition classes 203 by clustering, and the multiple groups of factor data records 202 are constructed as vectors and transformed by dimensionality increase to obtain a new vector: a third vector 204, and different elements of the third vector 204 are assigned different weights and clustered. If the clustering results are consistent, it means that the weight setting is reasonable, and the mapping from the factor data record 202 to the sea condition record 201 is completed. At this time, after obtaining the new factor data dimensionality increase transformation, a new vector is obtained, and the corresponding sea condition can be obtained through weight processing.

[0095] Based on the above concept, an embodiment of the present invention clusters sea conditions by comparing the similarity of sea conditions. Specifically, first, sea condition records of the clustered number are randomly selected from multiple sea condition records as multiple target sea condition records; then each sea condition record is classified into the most similar target sea condition record to obtain multiple first sea condition classes; then the class center of each first sea condition class is extracted to obtain multiple sea condition class centers; then the similarity between each sea condition class center and the target sea condition record is calculated to obtain multiple first similarity values; finally, if there is a value lower than the similarity threshold among the multiple first similarity values, the multiple sea condition class centers are used as the multiple target sea condition records, and the process jumps to the step of classifying each sea condition record into the most similar target sea condition record to obtain multiple first sea condition classes.

[0096] In the above process, the similarity value is calculated by taking multiple record values ​​of the target sea state record as a vector according to the first formula:

[0097]

[0098] Where E is the first similarity value, cnMax is the total number of elements in the first vector, and ARC is cn is the cnth element of the sea state class center, ARD cn It is the cnth element of the target sea state record.

[0099] The clustering of sea condition records is completed through the above process. Generally, a deviation test is performed after the clustering is completed. Generally speaking, the similarity value between each class and the class center is determined. When this similarity value is relatively low, it means that the deviation of this class is large. At this time, the class deviation is generally adjusted by increasing the number of clusters.

[0100] In step 103, according to the correspondence between the factor data records and the sea state classes, multiple sea state assessment models are constructed using the factor data records extracted from the sea state data set, wherein each sea state assessment model corresponds to an alternative water selection point, and the sea state assessment model outputs a sea state estimate based on the factor data.

[0101] In some embodiments, the step of constructing a plurality of sea condition assessment models using factor data records extracted from a sea condition data set according to the correspondence between the factor data records and the sea condition classes includes:

[0102] For each alternative water selection point, perform the following steps:

[0103] constructing each group of factor data records into a second vector according to a predetermined factor arrangement order;

[0104] Performing dimension increase on each second vector by means of polynomial regression to obtain a plurality of third vectors, wherein each third vector corresponds to a set of factor data records;

[0105] Substituting the plurality of third vectors into a linear transformation model respectively to obtain a plurality of first results, wherein the linear transformation model includes a plurality of coefficients;

[0106] Sorting the plurality of first results, and dividing the plurality of first results into a first number of intervals according to the sorting, wherein the first number is the number of the plurality of sea condition classes;

[0107] According to the interval to which the first result belongs, the plurality of groups of factor data records are grouped into a plurality of factor classes;

[0108] Verifying the classification deviations of the plurality of factor classes and the plurality of sea condition classes according to the correspondence between the factor data records and the sea condition records;

[0109] If the classification deviation is greater than the classification deviation threshold, adjusting the multiple coefficients of the linear transformation model according to the classification deviation, and jumping to the step of substituting the multiple third vectors into the linear transformation model respectively to obtain multiple first result vectors;

[0110] Otherwise, the linear transformation model is used as the sea state assessment model.

[0111] In some embodiments, the step of performing dimension increase on each second vector by means of polynomial regression to obtain a plurality of third vectors includes:

[0112] Each second vector is dimensionally increased according to the second formula to obtain multiple third vectors, wherein the second formula is:

[0113]

[0114] Where AF 3，cm is the cm-th element of the third vector, F 2，in is the inth element of the second vector, W in is the inth first coefficient, ckMax is the total number of elements in the second vector, mod() is the remainder function, and int() is the integer function;

[0115] The linear transformation model is:

[0116]

[0117] Where SC is the evaluation result of the linear transformation model on the sea conditions, w cm is the cm-th second coefficient, AF cm is the cm-th element of the input vector, cmMax is the total number of input vector elements, and b1 is the first bias coefficient.

[0118] In some implementations, adjusting the plurality of coefficients of the linear conversion model according to the classification bias comprises:

[0119] The multiple coefficients of the linear conversion model are adjusted according to a third formula, wherein the third formula is:

[0120]

[0121] In the formula, is the i-th coefficient of the adjusted linear transformation model, is the i-th coefficient of the linear conversion model before adjustment, k is the adjustment ratio, Bias is the classification bias, cmMax is the total number of elements in the third vector, and b2 is the second bias coefficient.

[0122] Exemplarily, an implementation of the present invention is to construct a linear expression equation to map factor data to sea condition data, but generally speaking, direct mapping is difficult or there is a possibility that the mapping cannot be completed. Therefore, it is necessary to first perform a dimensionality increase conversion on the factor data.

[0123] Before the dimensionality-upgrading conversion, each group of factor data records is first constructed as a second vector according to a predetermined factor arrangement order; then each second vector is dimensionally upgraded by polynomial regression to obtain multiple third vectors. The embodiment of the present invention applies the second formula to upgrade the second vector into a third vector:

[0124]

[0125] Where AF 3，cm is the cm-th element of the third vector, F 2，in is the inth element of the second vector, W in is the in-th first coefficient, ckMax is the total number of elements in the second vector, mod() is the remainder function, and int() is the integer function.

[0126] like Figure 3 As shown, after the second vector 202 constructed by the factor data record 202 is upgraded to the third vector 204, it is sent to the linear transformation model 301, and this model will give a result: the first result 302, multiple first results 302 are sorted and divided into intervals, and the factor data record 202 is classified into multiple factor classes 303 according to the divided intervals. Finally, as Figure 4 As shown, the linear conversion model 301 is adjusted according to the difference between the factor class 303 and the first sea state class 203 .

[0127] The linear conversion model used in the embodiment of the present invention is:

[0128]

[0129] Where SC is the evaluation result of the linear transformation model on the sea conditions, w cm is the cm-th second coefficient, AF cm is the cm-th element of the input vector, cmMax is the total number of input vector elements, and b1 is the first bias coefficient.

[0130] In terms of classification deviation, one application scenario is to count the factor data records that do not belong to the corresponding category, find the category to which it should belong, and perform vector difference operation with the center of the category to which it belongs, or vector element difference operation. If there are multiple factor data records that do not belong to this category, these element differences are summed to obtain the total element difference, which is the classification deviation.

[0131] In terms of adjusting the linear conversion model according to the classification bias, the embodiment of the present invention applies the third formula:

[0132]

[0133] In the formula, is the i-th coefficient of the adjusted linear transformation model, is the i-th coefficient of the linear conversion model before adjustment, k is the adjustment ratio, Bias is the classification bias, cmMax is the total number of elements in the third vector, and b2 is the second bias coefficient.

[0134] When, after several iterations, the factor class obtained by classifying the first result output by the linear conversion model is consistent with the first sea condition class, the linear conversion model can be used as a sea condition assessment model.

[0135] In step 104, multiple alternative water intake points are evaluated based on the historical extreme factor data and the multiple sea condition evaluation models, and a target water intake point is selected from the multiple alternative water intake points based on the sea condition estimation result.

[0136] In some embodiments, the step of evaluating multiple alternative water selection points based on historical extreme factor data and the multiple sea condition assessment models includes:

[0137] For each alternative water selection point, perform the following steps:

[0138] Inputting the historical extreme factor data into a sea condition assessment model for alternative water selection points to obtain a second result;

[0139] Find a first result closest to the second result from the multiple first results as the third result;

[0140] Finding a first result closest to a target difference from the multiple first results as the fourth result, wherein the target difference is a difference between the second result and the third result;

[0141] Extracting the class center of the sea condition class corresponding to the third result and the class center of the sea condition class corresponding to the fourth result as the first reference sea condition and the second reference sea condition;

[0142] The extreme sea conditions of the alternative water selection points are determined according to the first reference sea condition and the second reference sea condition.

[0143] Exemplarily, after the model is built, extreme factor data can be obtained, such as historical extreme weather and some other data. After dimensionality conversion, it is input into the sea condition assessment model to obtain an assessment result (second result). Since the input data is extreme data, the sea condition mapping cannot usually be completed directly through the assessment result. However, because the model is a linear model, the assessment result can be split into the closest first result (for example, the assessment result value is 1300, and the first result is scattered in the range of 100 to 50000. At this time, a first result close to 1300 is found, for example, 1100). As the third result, there may still be a large difference between the assessment result and the first result. At this time, the closest first result will be found from the first result again according to the difference (the difference is 1300-1100=200) as the fourth result. Then, according to the sea condition corresponding to the third result and the sea condition corresponding to the fourth result (refer to Figure 3, the interval of the first result 302 corresponds to the classification of the factor data record 202: factor class 303, refer to Figure 4 , factor class 303 corresponds to sea condition class 203, and the class center of sea condition class 203 is taken as the sea condition corresponding to the result), and the sea condition when the extreme factor occurs is determined, usually by adding the sea condition corresponding to the third result and the sea condition corresponding to the fourth result to obtain the extreme sea condition.

[0144] In this way, the extreme sea condition assessment results of each alternative watering point are obtained, and based on the assessment results, an alternative watering point with better sea conditions is determined from the alternative watering points as the water intake point in the target sea area.

[0145] The implementation method of the sea area water intake point determination method of the present invention first obtains multiple sea condition data sets, wherein each sea condition data set corresponds to an alternative water intake point, the sea condition data set includes multiple sea condition records and multiple groups of factor data records, and each sea condition record corresponds to a group of factor data records; then for each alternative water intake point, the multiple sea condition records are clustered into multiple sea condition classes according to similarity; then, according to the correspondence between the factor data records and the sea condition classes, multiple sea condition assessment models are constructed using the factor data records extracted from the sea condition data set, wherein each sea condition assessment model corresponds to an alternative water intake point, and the sea condition assessment model outputs a sea condition estimation according to the factor data; finally, according to the historical extreme factor data and the multiple sea condition assessment models, the multiple alternative water intake points are evaluated, and a target water intake point is selected from the multiple alternative water intake points according to the sea condition estimation result. The implementation mode of the present invention completes the construction of the sea condition assessment model based on the clustering of sea condition records and the evaluation value output by the linear model according to the factor data records. The construction process requires a small amount of preliminary data and does not require a large amount of data calculation or training to obtain relatively accurate extreme sea condition assessment results. It is suitable for obtaining relatively accurate sea area water intake point selection scenarios with less resource investment.

[0146] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0147] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0148] Figure 5 This is a functional block diagram of a device for determining a water intake point in a sea area provided by an embodiment of the present invention, referring to Figure 5 The device for determining a water intake point in a sea area includes: a sea condition record acquisition module 501, a sea condition clustering module 502, a sea condition assessment model construction module 503 and a water intake point determination module 504, wherein:

[0149] The sea state record acquisition module 501 is used to acquire multiple sea state data sets, wherein each sea state data set corresponds to an alternative water selection point, and the sea state data set includes multiple sea state records and multiple groups of factor data records, and each sea state record corresponds to a group of factor data records;

[0150] A sea state clustering module 502 is used to cluster multiple sea state records into multiple sea state classes according to similarity for each candidate water selection point;

[0151] A sea condition assessment model construction module 503 is used to construct multiple sea condition assessment models using factor data records extracted from the sea condition data set according to the correspondence between factor data records and sea condition classes, wherein each sea condition assessment model corresponds to an alternative water selection point, and the sea condition assessment model outputs a sea condition estimate according to the factor data;

[0152] The water intake point determination module 504 is used to evaluate multiple alternative water intake points based on the historical extreme factor data and the multiple sea condition assessment models, and select a target water intake point from the multiple alternative water intake points based on the sea condition estimation result.

[0153] Figure 6 is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 6 of this embodiment includes: a processor 600 and a memory 601, wherein the memory 601 stores a computer program 602 that can be run on the processor 600. When the processor 600 executes the computer program 602, the steps in the above-mentioned methods and embodiments for determining the water intake point in the sea area are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0154] Exemplarily, the computer program 602 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 601 and executed by the processor 600 to implement the present invention.

[0155] The electronic device 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 6 may include, but is not limited to, a processor 600 and a memory 601. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 6 and does not constitute a limitation of the electronic device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 6 may also include input and output devices, network access devices, buses, etc.

[0156] The processor 600 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0157] The memory 601 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. The memory 601 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Further, the memory 601 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 601 is used to store the computer program 602 and other programs and data required by the electronic device 6. The memory 601 may also be used to temporarily store data that has been output or is to be output.

[0158] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0159] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0161] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0163] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0164] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various methods and device implementation methods. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0165] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for determining a water intake point in a sea area, characterized in that: include: Acquire multiple sea state data sets, wherein each sea state data set corresponds to an alternative water selection point, the sea state data set includes multiple sea state records and multiple groups of factor data records, and each sea state record corresponds to a group of factor data records; For each alternative water selection point, multiple sea state records are clustered into multiple sea state classes based on similarity; According to the correspondence between the factor data records and the sea state classes, multiple sea state assessment models are constructed using the factor data records extracted from the sea state data set, wherein each sea state assessment model corresponds to an alternative water selection point, and the sea state assessment model outputs a sea state estimation according to the factor data; Based on the historical extreme factor data and the multiple sea condition assessment models, multiple alternative water intake points are evaluated, and a target water intake point is selected from the multiple alternative water intake points based on the sea condition estimation result.

2. The method for determining a sea area water intake point according to claim 1, characterized in that: For each alternative water selection point, the plurality of sea state records are clustered into a plurality of sea state classes according to similarity, including: Get the number of clusters; Randomly selecting the clustered number of sea state records from the plurality of sea state records as a plurality of target sea state records; Classifying each sea state record into the most similar target sea state record to obtain a plurality of first sea state classes; Extracting the class center of each first sea condition class to obtain multiple sea condition class centers; Calculate the similarity between each sea state class center and the target sea state record to obtain multiple first similarity values; If there is a value lower than the similarity threshold value among the multiple first similarity values, the multiple sea state class centers are used as the multiple target sea state records, and the process jumps to the step of classifying each sea state record into the most similar target sea state record to obtain multiple first sea state classes; Extracting the lowest similarity value of each first sea state class, wherein the lowest similarity value is the first similarity value of the sea state record with the lowest similarity to the sea state class center in the first sea state class; If there is a similarity value lower than the central similarity threshold among the lowest similarity values ​​of the multiple first sea condition classes, the number of clusters is adjusted, and the process jumps to the step of randomly selecting the sea condition records of the cluster number from the multiple sea condition records as the multiple target sea condition records.

3. The method for determining a sea area water intake point according to claim 2, characterized in that: The calculating the similarity between each sea condition class center and the target sea condition record to obtain a plurality of first similarity values ​​comprises: Arranging multiple record values ​​of each target sea state record in a predetermined order to construct a first vector; The similarity between each sea condition class center and the target sea condition record is calculated according to the first formula to obtain multiple first similarity values, wherein the first formula is: Where E is the first similarity value, cnMax is the total number of elements in the first vector, and ARC is cn is the cnth element of the sea state class center, ARD cn It is the cnth element of the target sea state record.

4. The method for determining a sea area water intake point according to any one of claims 1 to 3, characterized in that: The method of constructing a plurality of sea condition assessment models by using factor data records extracted from a sea condition data set according to the correspondence between the factor data records and the sea condition classes includes: For each alternative water selection point, perform the following steps: constructing each group of factor data records into a second vector according to a predetermined factor arrangement order; Performing dimension increase on each second vector by means of polynomial regression to obtain a plurality of third vectors, wherein each third vector corresponds to a set of factor data records; Substituting the plurality of third vectors into a linear transformation model respectively to obtain a plurality of first results, wherein the linear transformation model includes a plurality of coefficients; Sorting the plurality of first results, and dividing the plurality of first results into a first number of intervals according to the sorting, wherein the first number is the number of the plurality of sea condition classes; According to the interval to which the first result belongs, the plurality of groups of factor data records are grouped into a plurality of factor classes; Verifying the classification deviations of the plurality of factor classes and the plurality of sea condition classes according to the correspondence between the factor data records and the sea condition records; If the classification deviation is greater than the classification deviation threshold, adjusting the multiple coefficients of the linear transformation model according to the classification deviation, and jumping to the step of substituting the multiple third vectors into the linear transformation model respectively to obtain multiple first result vectors; Otherwise, the linear transformation model is used as the sea state assessment model.

5. The method for determining a sea area water intake point according to claim 4, characterized in that: The step of performing dimension increase on each second vector by means of polynomial regression to obtain multiple third vectors includes: Each second vector is dimensionally increased according to the second formula to obtain multiple third vectors, wherein the second formula is: Where AF 3,cm is the cm-th element of the third vector, F 2,in is the inth element of the second vector, W in is the inth first coefficient, ckMax is the total number of elements in the second vector, mod() is the remainder function, and int() is the integer function; The linear transformation model is: Where SC is the evaluation result of the linear transformation model on the sea conditions, w cm is the cm-th second coefficient, AF cm is the cm-th element of the input vector, cmMax is the total number of input vector elements, and b1 is the first bias coefficient.

6. The method for determining a sea area water intake point according to claim 4, characterized in that: The adjusting the multiple coefficients of the linear conversion model according to the classification deviation comprises: The multiple coefficients of the linear conversion model are adjusted according to a third formula, wherein the third formula is: In the formula, is the i-th coefficient of the adjusted linear transformation model, is the i-th coefficient of the linear conversion model before adjustment, k is the adjustment ratio, Bias is the classification bias, cmMax is the total number of elements in the third vector, and b2 is the second bias coefficient.

7. The method for determining a sea area water intake point according to claim 4, characterized in that: The step of evaluating multiple alternative water selection points based on the historical extreme factor data and the multiple sea condition assessment models includes: For each alternative water selection point, perform the following steps: Inputting the historical extreme factor data into a sea condition assessment model for alternative water selection points to obtain a second result; Find a first result closest to the second result from the multiple first results as the third result; Finding a first result closest to a target difference from the multiple first results as the fourth result, wherein the target difference is a difference between the second result and the third result; Extracting the class center of the sea condition class corresponding to the third result and the class center of the sea condition class corresponding to the fourth result as the first reference sea condition and the second reference sea condition; The extreme sea conditions of the alternative water selection points are determined according to the first reference sea condition and the second reference sea condition.

8. A device for determining a water intake point in a sea area, characterized in that: Used to implement the method for determining a sea area water intake point according to any one of claims 1 to 7, the sea area water intake point determination device comprises: A sea state record acquisition module is used to acquire multiple sea state data sets, wherein each sea state data set corresponds to an alternative water selection point, and the sea state data set includes multiple sea state records and multiple groups of factor data records, and each sea state record corresponds to a group of factor data records; A sea state clustering module is used to cluster multiple sea state records into multiple sea state classes according to similarity for each alternative water selection point; A sea state assessment model building module is used to build multiple sea state assessment models using factor data records extracted from a sea state data set according to the correspondence between factor data records and sea state classes, wherein each sea state assessment model corresponds to an alternative water selection point, and the sea state assessment model outputs a sea state estimate according to the factor data; as well as, The water intake point determination module is used to evaluate multiple alternative water intake points based on historical extreme factor data and the multiple sea condition assessment models, and select a target water intake point from the multiple alternative water intake points based on the sea condition estimation result.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images