Platform combined electric field prediction method and system for DC line adjacent L-shaped civil house
By constructing a platform-based synthetic electric field prediction method based on a fourth-order polynomial ridge regression model, the problem of low efficiency in modeling synthetic electric fields of L-shaped houses in existing technologies is solved, and rapid and accurate synthetic electric field prediction is achieved, supporting engineering design and demolition measures.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-09
- Publication Date
- 2026-03-24
AI Technical Summary
The existing technology lacks a modeling method for the three-dimensional synthetic electric field of buildings near DC transmission lines in typical residential buildings in actual engineering projects, which leads to slow engineering design progress and inability to effectively explore the distribution characteristics of the synthetic electric field.
An optimal platform synthetic electric field prediction model was constructed using a fourth-order polynomial ridge regression model. The key parameter values of the L-shaped houses were obtained and input into the pre-established model for prediction. The model was evaluated using the square of the correlation coefficient, the root mean square error, and the absolute error. The optimization objective was to minimize the expression of the ridge regression model.
It enables rapid prediction of the maximum value of the composite electric field on an L-shaped residential platform, improving prediction efficiency by several orders of magnitude, providing important technical support for engineering design, and meeting engineering accuracy requirements.
Smart Images
Figure CN121723754A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of platform synthetic electric field prediction, and more particularly, to a platform synthetic electric field prediction method and system for L-shaped residential buildings adjacent to a DC line. BACKGROUND
[0002] With the increasing density of DC transmission line laying, monitoring and evaluation of the synthetic electric field of the platform of residential buildings near the DC transmission line has become a problem to be solved. Currently, the literature on the three-dimensional synthetic electric field of buildings adjacent to the DC transmission line mainly discusses the calculation method, and lacks modeling methods and calculation research of the synthetic electric field of typical structure residential buildings in actual engineering. There are a large number of residential buildings along the actual UHV DC transmission line, with complex and diverse structures and varying size ranges. If detailed modeling and calculation are performed for each project by collecting data on residential buildings, on the one hand, a large amount of manpower and resources are consumed, and the progress of engineering design is difficult to guarantee, on the other hand, the distribution characteristics of the synthetic electric field are different, and more valuable data features cannot be extracted. Therefore, it is necessary to investigate the structure types of residential buildings along the existing UHV DC transmission line, statistically obtain the typical residential building structure types, the size of the residential building, the line parameters, and the variation range of the proximity distance between the residential building and the line, analyze the three-dimensional synthetic electric field of the typical structure residential building adjacent to the UHV DC transmission line in the range, summarize the distribution law of the three-dimensional synthetic electric field, obtain the distribution position and variation law of the maximum and minimum values of the synthetic electric field, and then develop the calculation results to obtain a synthetic electric field prediction model. Since the existing residential building structure is L-shaped, it is named as L-shaped residential building. For the DC transmission line designed in recent years, the residential buildings along each return DC transmission line are investigated, and the L-shaped residential building accounts for 44.0% of the total number. The L-shaped structure residential building is composed of a lower cuboid and an upper cuboid, and the length or width of the upper cuboid is consistent with that of the lower cuboid, and the position is at the long side or short side of the lower cuboid. The platform is located on the top surface of the lower cuboid. The distribution characteristics of the synthetic electric field are analyzed to obtain a synthetic electric field rapid prediction model, which has important reference value for engineering design. SUMMARY
[0003] In order to solve the technical problem that the existing literature on the three-dimensional synthetic electric field of buildings adjacent to the DC transmission line mainly discusses the calculation method, and lacks modeling methods and calculation research of the synthetic electric field of typical structure residential buildings in actual engineering, the present application provides a platform synthetic electric field prediction method and system for L-shaped residential buildings adjacent to a DC line.
[0004] According to one aspect of the present application, the present application provides a platform synthetic electric field prediction method for L-shaped residential buildings adjacent to a DC line, comprising:
[0005] acquire parameter values of a plurality of key parameters of the L-shaped house whose platform integrated electric field is to be predicted;
[0006] determine whether the parameter values are valid according to a set parameter value interval;
[0007] when the parameter values are determined to be valid, input the parameter values into a pre-established optimal platform integrated electric field prediction model, and an output value of the optimal platform integrated electric field prediction model is a platform integrated electric field prediction value of the L-shaped house whose platform integrated electric field is to be predicted, wherein the optimal platform integrated electric field prediction model is a 4th order polynomial ridge regression model constructed by taking all the key parameters as dependent variables and polynomials not higher than 4th order, and the model is trained by taking a minimum value of an expression of the 4th order polynomial ridge regression model as an optimization target.
[0008] According to another aspect of the present application, the present application provides a platform integrated electric field prediction system for an L-shaped house adjacent to a DC line, the system comprising:
[0009] a data acquisition module configured to acquire parameter values of a plurality of key parameters of the L-shaped house whose platform integrated electric field is to be predicted;
[0010] an effective determination module configured to determine whether the parameter values are valid according to a set parameter value interval;
[0011] an output module configured to, when the parameter values are determined to be valid, input the parameter values into a pre-established optimal platform integrated electric field prediction model, and an output value of the optimal platform integrated electric field prediction model is a platform integrated electric field prediction value of the L-shaped house whose platform integrated electric field is to be predicted, wherein the optimal platform integrated electric field prediction model is a 4th order polynomial ridge regression model constructed by taking all the key parameters as dependent variables and polynomials not higher than 4th order, and the model is trained by taking a minimum value of an expression of the 4th order polynomial ridge regression model as an optimization target.
[0012] According to still another aspect of the present application, the present application provides a computer readable storage medium, the storage medium storing a computer program, the program being executed by a processor to implement the method according to any one of the above aspects of the present application.
[0013] According to still another aspect of the present application, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; and the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method according to any one of the above aspects of the present application.
[0014] The method comprises: acquiring parameter values of a plurality of key parameters of an L-shaped house whose platform synthetic electric field is to be predicted; determining whether the parameter values are valid according to a set parameter value interval; when the parameter values are determined to be valid, inputting the parameter values into a pre-established optimal platform synthetic electric field prediction model, and the output value of the optimal platform synthetic electric field prediction model is a platform synthetic electric field prediction value of the L-shaped house whose platform synthetic electric field is to be predicted. The method and system are aimed at the most numerous L-shaped structure houses in engineering, fit a function relationship between the maximum platform synthetic electric field of the house and the key parameters based on a 4th-degree polynomial ridge regression model, propose a prediction model of the maximum platform synthetic electric field of the typical L-shaped structure house, can instantly obtain a calculation result, greatly improve the prediction efficiency of the maximum platform synthetic electric field of the house, and provide an important technical basis for formulating a house synthetic electric field control measure and house removal. BRIEF DESCRIPTION OF DRAWINGS
[0015] The exemplary embodiments of this application can be more fully understood with reference to the following drawings:
[0016] Figure 1 A flow chart of a platform synthetic electric field prediction method of an L-shaped house adjacent to a DC line according to a preferred embodiment of the application;
[0017] Figure 2 A schematic diagram of eight key parameters of an L-shaped house according to a preferred embodiment of the application;
[0018] Figure 3 A top view position schematic diagram of the maximum platform synthetic electric field of an L-shaped house according to a preferred embodiment of the application;
[0019] Figure 4 A structure schematic diagram of a platform synthetic electric field prediction system of an L-shaped house adjacent to a DC line according to a preferred embodiment of the application;
[0020] Figure 5 A structure schematic diagram of an electronic device according to a preferred embodiment of the application. DETAILED DESCRIPTION
[0021] Reference will now be made to the drawings to describe the exemplary embodiments of the present application in greater detail. The present application can, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the application to those skilled in the art. Like reference numerals refer to like elements throughout the specification. It will be understood that when an element or layer is referred to as being "on" another element or substrate, it can be directly on the element or substrate or intervening layers can also be present. In addition, it will also be understood that when an element is referred to as being "between" two elements, it can be directly between the two elements or intervening elements can also be present. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.
[0022] The terms used herein, including technical and scientific terms, have meanings commonly used in the art unless indicated otherwise. Furthermore, unless otherwise required by context, singular terms shall include pluralities and vice versa. In addition, unless indicated otherwise, terms used herein including technical and scientific terms have the meanings commonly understood by one of ordinary skill in the art to which this application belongs. Also, terms such as "first" and "second" are used herein only to describe a certain configuration, and do not imply the existence of a superiority or inferiority, or a high or low, but only to distinguish one element from another. Thus, the terms "first" and "second" can be interchanged with the terms "second" and "first", respectively.
[0023] Exemplary method
[0024] Figure 1 A flowchart of a method for predicting a platform combined electric field of an L-shaped residential building adjacent to a DC line according to a preferred embodiment of the present application. As shown in Figure 1 the method for predicting a platform combined electric field of an L-shaped residential building adjacent to a DC line according to the preferred embodiment of the present application starts from step 101.
[0025] In step 101, the parameter values of a plurality of key parameters of the L-shaped residential building whose platform combined electric field is to be predicted are obtained.
[0026] Preferably, before obtaining the parameter values of the key parameters of the L-shaped residential building whose platform combined electric field is to be predicted, an optimal platform combined electric field prediction model is established, including:
[0027] setting a plurality of key parameters that affect the platform combined electric field of the L-shaped residential building adjacent to the DC line, and a parameter value range of each key parameter;
[0028] for each key parameter, uniformly taking values in its parameter value range;
[0029] According to the values corresponding to the orthogonal changes of all the key parameters, the maximum value of the lower platform combined electric field and the maximum value of the upper platform combined electric field of the L-shaped residential building are calculated, and N groups of data sequences including the values of all the key parameters and the corresponding maximum values of the lower platform combined electric field and the upper platform combined electric field are generated as a training set;
[0030] The platform combined electric field prediction model of the L-shaped residential building is constructed, and its expression is:
[0031]
[0032] In the formula, E S1 and E S2 are the maximum values of the lower platform combined electric field and the upper platform combined electric field of the L-shaped residential building, respectively, f 1i and f 2i are polynomials with K key parameters as dependent variables and not higher than the fourth order, x k is the kth key parameter, a 1i and a 2i are f 1i and f 2iThe corresponding coefficients p1 and p2 are f 1i and f 2i The number of polynomial terms in f
[0033] A 4th order polynomial ridge regression model is constructed for the platform synthetic electric field prediction model, and the expression is as follows:
[0034]
[0035] In the formula, and The regularization term of the 4th order polynomial ridge regression model is the sum of squares of coefficients, and the ridge parameters α1 and α2 are obtained by ridge trace analysis in the candidate range [0.001, 0.01, 0.1, 1, 10, 100];
[0036] Based on the data in the training set, the values of the two expressions in the 4th order polynomial ridge regression model are minimized as the optimization objective, and the coefficients a 1i and a 2i are obtained to determine the candidate platform synthetic electric field prediction model;
[0037] In the set parameter value interval, all key parameters are randomly selected for non-training set values to generate a test set;
[0038] According to the test set data, the calculated values of the maximum values of the lower platform synthetic electric field and the upper platform synthetic electric field of the L-shaped civilian house are determined, and the predicted values of the maximum values of the lower platform synthetic electric field and the upper platform synthetic electric field of the L-shaped civilian house are determined by using the candidate platform synthetic electric field prediction model;
[0039] According to the corresponding calculation values and prediction values of each group of data in the test set, the parameter values corresponding to the evaluation parameters of the candidate platform synthetic electric field prediction model are calculated;
[0040] When the parameter values corresponding to the evaluation parameters meet the set model test criteria, the candidate platform synthetic electric field prediction model is determined as the optimal platform synthetic electric field prediction model.
[0041] In the preferred embodiment, the 4th order polynomial ridge regression model is used to establish the prediction model, which can effectively handle the multicollinearity problem, avoid overfitting, and ensure the prediction reliability of the model on the test set data.
[0042] Figure 2 Fig. 8 is a schematic diagram of 8 key parameters of an L-shaped civilian house according to the preferred embodiment of the present application. As shown in Fig. 8, the 8 key parameters of the L-shaped civilian house include the height of the lower layer of the L-shaped civilian house, the height of the upper layer of the L-shaped civilian house, the width of the lower layer of the L-shaped civilian house, the width of the upper layer of the L-shaped civilian house, the length of the lower layer of the L-shaped civilian house, the length of the upper layer of the L-shaped civilian house, the height of the lower layer of the L-shaped civilian house, and the height of the upper layer of the L-shaped civilian house. Figure 2As shown, there are eight key parameters set: the horizontal pole spacing PD of the DC transmission line pole conductors, the pole conductor height H, and the horizontal approach distance W between the DC transmission line and the residential buildings. BD The length L of the parallel side between the residential building and the DC transmission line B The length W of the lower side of the house perpendicular to the DC transmission line B1 The height H of the lower floor of the residential building B1 The length WB2 of the upper side of the house perpendicular to the DC transmission line, and the height H of the upper floor of the house. B2 .
[0043] The parameter value ranges for the eight key parameters are as follows:
[0044] The horizontal pole spacing PD of DC transmission line pole conductors ranges from 18 to 24 m.
[0045] The height H of the polar conductor ranges from 20 to 60 m.
[0046] The horizontal distance between the DC transmission line and the residential building is approximately W. BD Its value range is 7 to 60 m;
[0047] The length L of the parallel side between the residential building and the DC transmission line B Its value range is 10 to 28 m;
[0048] The length W of the lower side of the house perpendicular to the DC transmission line B1 Its value range is 10 to 24 m;
[0049] Height H of the lower floor of the residential building B1 Its value range is 3 to 11m;
[0050] The length W of the upper side of the house perpendicular to the DC transmission line B2 The value range is between W and B1 The ratio is in the range of 0.3 to 0.5;
[0051] Upper floor height H of residential building B2 The value range is between H B1 The ratio is in the range of 0.5 to 1.
[0052] The parameter value is considered valid if and only if the value of each key parameter satisfies the value range.
[0053] Preferably, for each key parameter, the values are uniformly distributed within its range, including:
[0054] For each key parameter, set a value interval;
[0055] For each key parameter, values are taken sequentially from the minimum value in the range according to the specified interval.
[0056] Preferably, the three-dimensional flux line method or the three-dimensional upward flow finite element method is used to calculate the maximum value of the combined electric field of the lower platform and the maximum value of the combined electric field of the upper platform of the L-shaped house based on the values corresponding to the orthogonal changes of all key parameters.
[0057] Preferably, based on the calculated value and the predicted value corresponding to each set of data in the test set, the parameter values corresponding to the evaluation parameters of the candidate platform synthetic electric field prediction model are calculated, wherein the evaluation parameters include the square of the correlation coefficient, the root mean square error, and the absolute error.
[0058] Preferably, when the parameter value corresponding to the evaluation parameter meets the set model test criteria, the candidate platform synthetic electric field prediction model is determined to be the optimal platform synthetic electric field prediction model. The model test criteria are that the square of the correlation coefficient is greater than a set first threshold, the root mean square error is less than a set second threshold, and the proportion of absolute errors greater than a set third threshold is less than a set proportion threshold.
[0059] In this preferred embodiment, according to Figure 2 The eight key parameters shown are uniformly distributed within their respective ranges, with PD intervals of 3m, H intervals of 5m, and W... BD The interval is 3m, L B The interval is 6m, W B1 The interval is 2m, H B1 The interval is 2m, W B2 (with W) B1 The intervals for the ratios are 0.2, H B2 (with H) B1 The interval for the ratio is 0.25.
[0060] Figure 3 This is a top-view schematic diagram showing the maximum value of the combined electric field on an L-shaped residential platform according to a preferred embodiment of the present invention. Figure 3 As shown in this example, the maximum value of the composite electric field of the upper platform of the L-shaped house is located at the two corners near the DC transmission line within the effective monitoring range of the upper platform, 1.5m away from the edge of the platform; the maximum value of the composite electric field of the lower platform appears at the two corners near the DC transmission line within the effective monitoring range, also 1.5m away from the edge of the platform.
[0061] The maximum value of the combined electric field E of the lower platform of the L-shaped house was calculated using the three-dimensional flux line method when eight key parameters under orthogonal variations. S1 The maximum value of the combined electric field E of the upper platform S2, a total of 414720 groups of data as the training set data of the model, wherein the maximum value of the synthetic electric field of the lower platform E S1 and the maximum value of the synthetic electric field of the upper platform E S2 The expression is:
[0062]
[0063] According to the above formula, the maximum value of the synthetic electric field of the lower platform of the L-shaped house E S1 and the maximum value of the synthetic electric field of the upper platform E S2 are expressed as a polynomial of no more than 4 times composed of PD, H, W BD , L B , W B1 , H B1 , W B2 , H B2 , a total of 495 terms. Therefore, the maximum value of p1 and p2 is 495 terms.
[0064] The maximum value of the synthetic electric field of the lower platform E S1 and the maximum value of the synthetic electric field of the upper platform E S2 , an optimization objective function is established by using a 4th order polynomial ridge regression model, and the expression is:
[0065]
[0066] As shown in the expression of the optimization function, the regularization technique is used in the ridge regression model, thereby effectively avoiding overfitting of the model. The 414720 groups of data obtained are used to train the initial platform synthetic electric field prediction model based on the ridge regression model, and the candidate platform synthetic electric field prediction model that satisfies the optimization function is determined.
[0067] Further, non-training set data are randomly selected in the value range of the 8 key parameters, and the number is about 10% of the training set data, as test set data of the prediction model. The platform synthetic electric field prediction model is used to predict the platform synthetic electric field, and the calculation results of the three-dimensional flux line method or the three-dimensional upflow finite element method are compared, and the three key evaluation parameters of the candidate platform synthetic electric field prediction model are obtained, namely the correlation coefficient square R 2 , the root mean square error RMSE, and the absolute error comparison result, wherein R 2 is greater than the first threshold value 0.996, RMSE is less than the second threshold value 0.424kV / m, and the proportion of data whose absolute error exceeds the third threshold value 0.2kV / m is 0.160‰, which is less than the set proportion threshold value 1‰. The prediction accuracy meets the engineering requirements, and the candidate platform synthetic electric field prediction model is the optimal platform synthetic electric field prediction model.
[0068] At step 102, it is determined whether the parameter value is valid according to the set parameter value interval.
[0069] In the preferred embodiment, since the model for predicting the platform synthetic electric field is trained based on the value of each key parameter in its corresponding parameter value interval, in order to ensure the accuracy of the prediction result, it is necessary to ensure that the parameter value of the obtained key parameter is within the parameter value interval to perform the prediction of the platform synthetic electric field.
[0070] At step 103, when the parameter value is determined to be valid, the parameter value is input into the pre-established optimal platform synthetic electric field prediction model, and the output value of the optimal platform synthetic electric field prediction model is the predicted platform synthetic electric field prediction value of the L-shaped residential building.
[0071] In the preferred embodiment, the optimal platform synthetic electric field prediction model includes a polynomial for predicting the maximum value of the upper layer platform synthetic electric field and a polynomial for predicting the maximum value of the lower layer platform synthetic electric field, and therefore the output value of the optimal platform synthetic electric field prediction model includes the predicted value of the maximum value of the upper layer platform synthetic electric field and the predicted value of the maximum value of the lower layer platform synthetic electric field.
[0072] The test is performed on a random 50,000-group test set data within the parameter range, R 2 The R reaches 0.996 or above, the RMSE reaches 0.424 kV / m, the data proportion with a prediction error of more than 0.2 kV / m is 0.160‰, and the prediction accuracy meets the engineering requirements. After the model training is completed, the prediction of the platform synthetic electric field of the L-shaped residential building can be completed within a few milliseconds, while the three-dimensional flux line method usually takes several minutes to tens of minutes to complete the prediction, and the three-dimensional upflow finite element method usually takes several hours or even several days to complete the prediction, and the prediction speed is improved by several orders of magnitude, which has important value for the comparison and optimization of the design scheme of the ultra-high voltage direct current line.
[0073] The platform synthetic electric field prediction method for the L-shaped residential building adjacent to the direct current line according to the preferred embodiment of the present application is aimed at the L-shaped structure residential building with the largest number in the engineering, fits the functional relationship between the maximum value of the platform synthetic electric field of the residential building and the key parameters based on the 4th order polynomial ridge regression model, proposes the prediction model for the maximum value of the platform synthetic electric field of the typical L-shaped structure residential building, can instantly obtain the calculation result, greatly improves the prediction efficiency of the maximum value of the platform synthetic electric field of the L-shaped residential building, and provides an important technical basis for formulating the control measures of the synthetic electric field of the residential building and the demolition of the residential building.
[0074] Exemplary system
[0075] Figure 4 The structure diagram of the platform synthetic electric field prediction system for the L-shaped residential building adjacent to the direct current line according to the preferred embodiment of the present application is shown in FIG. 1. Figure 4As shown, the direct current line adjacent L-shaped residential building platform synthetic electric field prediction system 400 of the preferred embodiment comprises:
[0076] A data acquisition module 401 is configured to acquire parameter values of a plurality of key parameters of the L-shaped residential building whose platform synthetic electric field is to be predicted.
[0077] An effective judgment module 402 is configured to determine whether the parameter values are effective according to a set parameter value interval.
[0078] A result output module 403 is configured to input the parameter values into a pre-established optimal platform synthetic electric field prediction model when the parameter values are determined to be effective, and an output value of the optimal platform synthetic electric field prediction model is a platform synthetic electric field prediction value of the L-shaped residential building whose platform synthetic electric field is to be predicted.
[0079] The direct current line adjacent L-shaped residential building platform synthetic electric field prediction system of the preferred embodiment has the same steps and achieves the same technical effects as the direct current line adjacent L-shaped residential building platform synthetic electric field prediction method, and thus will not be described here again.
[0080] Exemplary electronic device
[0081] Figure 5 A structural schematic diagram of an electronic device according to the preferred embodiment of the present application is shown in FIG. 1. Figure 5 As shown, the electronic device comprises one or more processors 501 and a memory 502.
[0082] The processor 501 can be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.
[0083] The memory 502 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, and the processor 501 can run the program instructions to implement the disclosed platform-synthesized electric field prediction method for L-shaped residential building adjacent to DC line and / or other desired functions described above. In one example, the electronic device can further include an input device 503 and an output device 504, which are interconnected through a bus system and / or other forms of connection mechanism (not shown).
[0084] In addition, the input device 503 can further include, for example, a keyboard, a mouse, and / or the like.
[0085] The output device 504 can output various information to the outside. The output device 504 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.
[0086] Of course, in order to simplify, Figure 5 Only some of the components of the electronic device related to the present disclosure are shown in FIG. 5, and components such as a bus, an input / output interface, and / or the like are omitted. In addition, the electronic device can further include any other appropriate components according to a specific application.
[0087] Exemplary computer program product and computer readable storage medium
[0088] In addition to the above-mentioned method and device, embodiments of the present disclosure can also be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the platform-synthesized electric field prediction method for L-shaped residential building adjacent to DC line according to various embodiments of the present disclosure described in the above “Exemplary Method” section of the specification.
[0089] The computer program product can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, and / or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.
[0090] Furthermore, an embodiment of the present disclosure can also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps of the platform synthetic electric field prediction method for a DC line adjacent L-shaped residential building according to various embodiments of the present disclosure described in the above "Exemplary Method" section of the specification.
[0091] The computer readable storage medium can take the form of one or more combinations of any type of computer readable medium. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0092] The above describes the basic principles of the present disclosure in combination with specific embodiments, but it should be noted that the advantages, benefits, effects and the like mentioned in the present disclosure are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as necessary for each embodiment of the present disclosure. In addition, the above specific details are only for the purpose of example and for the purpose of understanding, and the above details do not limit the present disclosure to be necessarily implemented with the above specific details.
[0093] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between each embodiment can be mutually referred to. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.
[0094] The block diagrams of the devices, apparatuses, equipment, systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be as shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have", and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.
[0095] The apparatus and methods of the present disclosure can be implemented in numerous ways. For example, the apparatus and methods of the present disclosure can be implemented using software, hardware, firmware, or any combination of software, hardware, and firmware. The order of any steps of the methods described above is merely exemplary and the steps of the methods of the present disclosure need not be performed in the order described unless otherwise specified. Furthermore, in some embodiments, the present disclosure can also be implemented as a program for use with a computer-based system, the program including a machine-readable instruction for implementing the methods according to the present disclosure. Thus, the present disclosure also covers record media storing the program for implementing the methods according to the present disclosure.
[0096] It is also noted that the apparatus, devices, and methods of the present disclosure can be embodied in a variety of other forms. These are to be considered as equivalents of the described aspects. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
[0097] The above description has been presented for the purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although several example aspects and embodiments have been discussed, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.
Claims
1. A method for predicting the composite electric field of a platform near an L-shaped residential building connected to a DC line, characterized in that, The method includes: Obtain the parameter values of several key parameters of the L-shaped house in the target prediction platform's synthetic electric field; Determine whether the parameter value is valid based on the set parameter value range; When the parameter value is determined to be valid, the parameter value is input into the pre-established optimal platform synthetic electric field prediction model. The output value of the optimal platform synthetic electric field prediction model is the predicted value of the platform synthetic electric field of the L-shaped house to be predicted. The optimal platform synthetic electric field prediction model is a fourth-order polynomial ridge regression model constructed with all key parameters as dependent variables and a polynomial of degree no higher than fourth. The model is trained and verified with the minimum value of the expression of the fourth-order polynomial ridge regression model as the optimization objective.
2. The method according to claim 1, characterized in that, Before obtaining the parameter values of the key parameters of the L-shaped house for which the synthetic electric field of the platform to be predicted is to be obtained, it is also necessary to establish an optimal platform synthetic electric field prediction model, including: Several key parameters affecting the platform composite electric field of the L-shaped residential buildings near the DC line are set, along with the range of values for each key parameter. For each key parameter, the value is taken evenly within its parameter range; Based on the values corresponding to the orthogonal changes of all key parameters, calculate the maximum value of the composite electric field of the lower platform and the maximum value of the composite electric field of the upper platform of the L-shaped house, and generate N sets of data sequences including the values of all key parameters and the corresponding maximum values of the composite electric field of the lower platform and the upper platform as training sets; A platform-based synthetic electric field prediction model for an L-shaped residential building is constructed, and its expression is as follows: In the formula, E S1 and E S2 These represent the maximum combined electric field values for the lower platform and upper platform of the L-shaped residential building, respectively. 1i and f 2i It is a polynomial with K key parameters as dependent variables and no higher than the fourth degree, x k For the k-th key parameter, a 1i and a 2i It is f 1i and f 2i The corresponding coefficients, p1 and p2, are f 1i and f 2i The number of polynomial terms in the expression; The fourth-order polynomial ridge regression model for constructing the synthetic electric field prediction model of the platform is expressed as follows: In the formula, and The regularization term of the fourth-order polynomial ridge regression model is the sum of squares of the coefficients. α1 and α2 are ridge parameters, whose values are obtained through ridge trace plot analysis within the candidate range [0.001, 0.01, 0.1, 1, 10, 100]. Based on the data in the training set, and with the optimization objective of minimizing the value of each expression in the fourth-order polynomial ridge regression model, the platform synthetic electric field prediction model is trained to obtain the coefficients a. 1i and a 2i The value of is used to determine the synthetic electric field prediction model for candidate platforms; Within the set parameter value range, randomly select non-training set values for all key parameters to generate the test set; Based on the test set data, the calculated values of the maximum combined electric field of the lower platform and the maximum combined electric field of the upper platform of the L-shaped house are determined, and the predicted values of the maximum combined electric field of the lower platform and the maximum combined electric field of the upper platform of the L-shaped house are determined using the candidate platform combined electric field prediction model. Based on the calculated value and the predicted value corresponding to each set of data in the test set, calculate the parameter values corresponding to the evaluation parameters of the candidate platform synthetic electric field prediction model; When the parameter values corresponding to the evaluation parameters meet the set model test criteria, the candidate platform synthetic electric field prediction model is determined to be the optimal platform synthetic electric field prediction model.
3. The method according to claim 1 or 2, characterized in that, There are 8 key parameters to set, namely: The horizontal pole spacing PD of DC transmission line pole conductors ranges from 18 to 24 m. The height H of the polar conductor ranges from 20 to 60 m. The horizontal distance between the DC transmission line and the residential building is approximately W. BD Its value range is 7 to 60 m; The length L of the parallel side between the residential building and the DC transmission line B Its value range is 10 to 28 m; The length W of the lower side of the house perpendicular to the DC transmission line B1 Its value range is 10 to 24 m; Height H of the lower floor of the residential building B1 Its value range is 3 to 11m; The length W of the upper side of the house perpendicular to the DC transmission line B2 With W B1 The ratio of , and its value ranges from 0.3 to 0.5; Upper floor height H of residential building B2 With H B1 The ratio of , and its value ranges from 0.5 to 1; When the value of each key parameter is within its range, the parameter value is confirmed to be valid.
4. The method according to claim 2, characterized in that, For each key parameter, values are taken evenly within its range, including: For each key parameter, set a value interval; For each key parameter, values are taken sequentially from the minimum value in the range according to the specified interval.
5. The method according to claim 2, characterized in that, Using the three-dimensional flux line method or the three-dimensional upward flow finite element method, the maximum values of the combined electric field on the lower platform and the upper platform of the L-shaped house are calculated based on the values corresponding to the orthogonal changes of all key parameters.
6. The method according to claim 2, characterized in that, Based on the calculated value and the predicted value corresponding to each set of data in the test set, the parameter values corresponding to the evaluation parameters of the candidate platform synthetic electric field prediction model are calculated, wherein the evaluation parameters include the square of the correlation coefficient, the root mean square error, and the absolute error.
7. The method according to claim 6, characterized in that, When the parameter values corresponding to the evaluation parameters meet the set model test criteria, the candidate platform synthetic electric field prediction model is determined to be the optimal platform synthetic electric field prediction model. The model test criteria are that the square of the correlation coefficient is greater than the set first threshold, the root mean square error is less than the set second threshold, and the proportion of absolute errors greater than the set third threshold is less than the set proportion threshold.
8. A platform-based synthetic electric field prediction system for a DC line adjacent to an L-shaped residential building, characterized in that, The system includes: The data acquisition module is used to acquire the parameter values of several key parameters of the L-shaped house in the synthesized electric field of the platform to be predicted; The validity determination module is used to determine whether the parameter value is valid based on the set parameter value range. The result output module is used to input the parameter value into the pre-established optimal platform synthetic electric field prediction model when the parameter value is determined to be valid. The output value of the optimal platform synthetic electric field prediction model is the predicted value of the platform synthetic electric field of the L-shaped house to be predicted. The optimal platform synthetic electric field prediction model is constructed by using a fourth-order polynomial ridge regression model with all key parameters as dependent variables and a polynomial of degree no higher than fourth. The model is trained and verified with the minimum value of the expression of the fourth-order polynomial ridge regression model as the optimization objective.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1-7.
10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the steps of the method according to any one of claims 1-7.