Method, system and equipment for predicting temporary occupied area of power transmission line construction

Abstract

The invention discloses a method, system and equipment for predicting the temporary occupied area of power transmission line construction, and the method comprises the following steps: S1, constructing a construction type input model: classifying the power transmission line construction into foundation construction X1, tower construction X2, stringing construction X3 and transportation road construction X4, aiming at each construction type, respectively constructing an input model for predicting the temporary occupied area of different construction types; s2, constructing a data processing prediction model: respectively constructing construction temporary occupied area prediction models of particle swarm optimization BP neural networks of different construction types according to different construction classifications, training the particle swarm optimization BP neural networks of different construction types by using previous construction data to obtain the construction temporary occupied area prediction models, and constructing the construction temporary occupied area prediction models of the particle swarm optimization BP neural networks of different construction types; and utilizing the trained model to obtain a construction temporary occupied area prediction value. The design not only adapts to the huge and jumbled requirement of the temporary occupied area index prediction of the overhead line construction under the mechanical construction, but also can better converge the complicated influence factors.

Description

Technical Field

[0001] The invention relates to prediction of temporary occupied area for power transmission line construction, and in particular to a method, system and equipment for predicting temporary occupied area for power transmission line construction. Background Art

[0002] With the vigorous promotion of new technologies such as mechanized construction technology, traditional temporary area prediction methods cannot meet the demand. Compared with conventional construction, the data generated by different topography, voltage levels, basic tower types, etc. in mechanized construction are more complex, and problems such as uneven data distribution and large deviations in a small part of the data are more prominent.

[0003] There is a big difference between the engineering quantity obtained in the initial feasibility study stage of the power grid line project and the actual compensation, and the accuracy of the engineering cost is insufficient. The accuracy of the engineering quantity of temporary land occupation during the construction of the line project is an important factor affecting the compensation cost. The temporary land occupation area of ​​the construction is affected by multiple factors such as topography, voltage level, foundation type, tower type and tensioning field layout. With the vigorous promotion of new technologies such as mechanized construction technology, there is a lack of a method for predicting the engineering quantity of temporary land occupation that comprehensively considers mechanized construction. At present, the engineering quantity of temporary land occupation under mechanized construction is only determined subjectively or according to the area prediction method that is not suitable for mechanized construction. The rationality and accuracy of the area calculation results are lacking and cannot meet the actual needs on site.

[0004] With the promotion of new technologies such as mechanized construction technology, the data generated in different environments is more complex and the prediction rules are unclear. The traditional temporary land area prediction method is suitable for situations where the data volume is small and the prediction rules are clear. It is obviously unable to meet the needs of the prediction of temporary land area indicators for overhead line construction under mechanized construction.

[0005] At present, the influencing factors considered in the research results of temporary land occupation prediction are single, and the prediction results are not accurate. Especially for the introduction of new technologies such as mechanized construction technology, the influencing factors in the construction process are more complex, and the data parameters are unevenly distributed. The traditional calculation method can no longer meet the needs. Summary of the invention

[0006] The purpose of the present invention is to overcome the problems of single influencing factors and low prediction accuracy in the prior art, and to provide a method, system and device for predicting the temporary area occupied by power transmission line construction taking into account multiple influencing factors.

[0007] To achieve the above objectives, the technical solution of the present invention is:

[0008] A method for predicting temporary land occupation area for power transmission line construction comprises the following steps:

[0009] S1, construct the construction type input model: classify the power transmission line construction into: foundation construction X1, tower construction X2, line construction X3 and transportation road construction X4, determine the main influencing factors of the temporary land area for each type of construction, and construct the input model for predicting the temporary land area of ​​different construction types;

[0010] S2, constructing a data processing prediction model: for different construction classifications, respectively construct prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, use past construction data to form training sets of particle swarm optimization BP neural networks of different construction types, use the training sets to train the particle swarm optimization BP neural networks of the corresponding construction types, and obtain the trained prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, and use the above trained models to obtain the prediction values ​​of temporary construction area occupied.

[0011] In S1, the main influencing factors of the foundation construction X1 include: voltage level x 11 , Line loop x 12 、Construction method x 13 , Terrain x 14 、Basic type x 15 ;

[0012] The main factors affecting tower construction X2 include: voltage level x 21 , Line loop x 22 、Tower assembly method x 23 、Construction method x 24 , Terrain x 25 ;

[0013] The main factors affecting the wiring construction X3 include: voltage level x 31 , Line loop x 32 , number of ground wire reels x 33 , Construction plan layout x 34 、The object being crossed x 35 ;

[0014] The main factors affecting the transport road construction X4 include: voltage level x 41 , Terrain x 42 , Construction organization design x 43 .

[0015] Construction plan layoutx 34 Including: the layout of construction sites and working surfaces, production and living auxiliary facilities;

[0016] Object being crossed x 35 Includes: trees, farmland, buildings, railways, highways, roads, rivers, and lakes.

[0017] In S2, for different construction classifications, construction temporary area prediction models of particle swarm optimization BP neural network for different construction types are constructed respectively:

[0018] Input layer construction: During the model construction process, the main influencing factors XJ corresponding to the models of different construction types, where J = 1, 2, 3 or 4, are used as the input layer;

[0019] Hidden layer construction: The number of hidden neurons should be between the size of the input layer and the size of the output layer; the number of hidden neurons should be 2 / 3 of the input layer size plus 2 / 3 of the output layer size; the number of hidden neurons should be less than twice the size of the input layer;

[0020] Output layer construction: Taking the temporary area occupied by construction as the only indicator, the output of temporary area occupied by different construction types is constructed.

[0021] The particle swarm optimization BP neural network construction process is as follows:

[0022] a. Construct BP neural network, initialize it, and set particle swarm parameters;

[0023] b. Initialize the speed and position of all particles;

[0024] c. Calculate the fitness function value of each particle;

[0025] d. Determine whether the fitness function value is greater than the historical optimal value and the global optimal value. If yes, proceed to the next step; otherwise, return to step 3 to continue the calculation;

[0026] e. Update individual extreme values, global optimal values ​​and the position of each particle velocity;

[0027] f. Training samples and calculating errors;

[0028] g. Error accuracy judgment;

[0029] h. Determine whether the number of iterations has reached the maximum. If yes, terminate the output. If no, return to step 3 to continue the calculation.

[0030] When making predictions, attention should be paid to the overlap between the areas occupied by foundation construction and tower construction. The final temporary construction area can be obtained by deducting the area after overlap from the sum of the areas occupied by foundation construction or tower construction.

[0031] A system for predicting temporary land occupation area for power transmission line construction, comprising:

[0032] Constructing a construction type input module: This module is used to determine the main influencing factors of the temporary land area for each type of construction, and to construct input models for predicting the temporary land area for different types of construction;

[0033] The construction type input module is used to perform the following steps:

[0034] S1. Constructing the input model of construction type: Classifying the power transmission line construction into: foundation construction X1, tower construction X2, line construction X3 and transportation road construction X4, determining the main influencing factors of the temporary land area for each construction classification, and constructing the input model for predicting the temporary land area for different construction types respectively;

[0035] In S1, the main influencing factors of the foundation construction X1 include: voltage level x 11 , Line loop x 12 、Construction method x 13 , Terrain x 14 、Basic type x 15 ;

[0036] The main factors affecting tower construction X2 include: voltage level x 21 , Line loop x 22 、Tower assembly method x 23 、Construction method x 24 , Terrain x 25 ;

[0037] The main factors affecting the wiring construction X3 include: voltage level x 31 , Line loop x 32 , number of ground wire reels x 33 , Construction plan layout x 34 、The object being crossed x 35 ;

[0038] The main factors affecting the transport road construction X4 include: voltage level x 41 , Terrain x 42 , Construction organization design x 43 .

[0039] Construction plan layoutx 34 Including: the layout of construction sites and working surfaces, production and living auxiliary facilities;

[0040] Object being crossed x 35 Includes: trees, farmland, buildings, railways, highways, roads, rivers, and lakes.

[0041] Construct a data processing prediction module: It is used to predict the temporary construction area according to different construction classifications using particle swarm optimization BP neural network.

[0042] The data processing prediction module is constructed to perform the following steps:

[0043] S2. Construct a data processing prediction model: for different construction classifications, construct prediction models of temporary construction area of ​​particle swarm optimization BP neural network of different construction types respectively, use the previous construction data to form training sets of particle swarm optimization BP neural network of different construction types, use the training sets to train the particle swarm optimization BP neural network of the corresponding construction type, and obtain the trained prediction models of temporary construction area of ​​particle swarm optimization BP neural network of different construction types, and use the above trained models to obtain the prediction value of temporary construction area.

[0044] According to different construction classifications, the prediction models of temporary construction area occupied by different construction types based on particle swarm optimization BP neural network are constructed respectively:

[0045] Input layer construction: During the model construction process, the main influencing factors XJ corresponding to the models of different construction types, where J = 1, 2, 3 or 4, are used as the input layer;

[0046] Hidden layer construction: The number of hidden neurons should be between the size of the input layer and the size of the output layer; the number of hidden neurons should be 2 / 3 of the input layer size plus 2 / 3 of the output layer size; the number of hidden neurons should be less than twice the size of the input layer;

[0047] Output layer construction: Taking the temporary area occupied by construction as the only indicator, the output of temporary area occupied by different construction types is constructed.

[0048] The particle swarm optimization BP neural network construction process is as follows:

[0049] a. Construct BP neural network, initialize it, and set particle swarm parameters;

[0050] b. Initialize the speed and position of all particles;

[0051] c. Calculate the fitness function value of each particle;

[0052] d. Determine whether the fitness function value is greater than the historical optimal value and the global optimal value. If yes, proceed to the next step; otherwise, return to step 3 to continue the calculation;

[0053] e. Update individual extreme values, global optimal values ​​and the position of each particle velocity;

[0054] f. Training samples and calculating errors;

[0055] g. Error accuracy judgment;

[0056] h. Determine whether the number of iterations has reached the maximum. If yes, terminate the output. If no, return to step 3 to continue the calculation.

[0057] When making predictions, attention should be paid to the overlap between the areas occupied by foundation construction and tower construction. The final temporary construction area can be obtained by deducting the area after overlap from the sum of the areas occupied by foundation construction or tower construction.

[0058] A device for predicting temporary area occupied by power transmission line construction, comprising a memory and a processor, wherein the memory is used to store computer program codes and transmit the computer program codes to the processor;

[0059] The processor is used to execute the method for predicting the temporary area occupied by power transmission line construction according to the instructions in the computer program code.

[0060] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for predicting the temporary area occupied by power transmission line construction.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. In a method for predicting the temporary area occupied by power transmission line construction of the present invention, different construction scenes are classified, models are constructed according to different construction scenes, and main influencing factors of each model are set for different scenes. Input models for predicting the temporary area occupied by different construction types are constructed respectively, and the model inputs are classified and refined to obtain a more accurate prediction model, which meets the complex needs of predicting the temporary area occupied by overhead line construction under mechanized construction.

[0063] 2. The advantage of the BP neural network in the method for predicting the temporary area occupied by power transmission line construction of the present invention is that it can realize the function of any complex nonlinear mapping, which makes it particularly suitable for solving problems with complex internal mechanisms; although the BP neural network can meet the complex needs of predicting the temporary area occupied by overhead line construction under mechanized construction, there are problems such as slow convergence speed, local minimization, and contradiction between prediction ability and training ability in the prediction process. At present, particle swarm optimization is the main method to make up for the shortcomings of the BP neural network algorithm; the present application introduces a particle swarm optimization BP neural network algorithm. Compared with the traditional BP neural network, this calculation method can better converge complex influencing factors and can also better conduct in-depth analysis and prediction of the main influencing factors, thereby achieving the purpose of improving prediction accuracy and accelerating calculation speed.

[0064] 3. A system for predicting the temporary area occupied by power transmission line construction of the present invention includes: constructing a construction type input module: for determining the main influencing factors of the temporary area occupied by each type of construction, and constructing input models for predicting the temporary area occupied by different construction types; constructing a data processing prediction module: for predicting the temporary area occupied by construction using a particle swarm optimization BP neural network for different construction classifications. The system is used to implement the steps of the method for predicting the temporary area occupied by power transmission line construction as provided in any of the above technical solutions. Therefore, the decoding system also includes all the beneficial effects of the method for predicting the temporary area occupied by power transmission line construction as provided in any of the above technical solutions, which will not be repeated here.

[0065] 4. A device for predicting temporary land occupation area for power transmission line construction of the present invention includes a processor and a memory, the memory is used to store computer program code and transmit the computer program code to the processor, and the processor is used to execute the method for temporary land occupation area for power transmission line construction provided in any of the above technical solutions according to the instructions in the computer program code. Therefore, the device also includes all the beneficial effects of the method for temporary land occupation area for power transmission line construction provided in any of the above technical solutions, which will not be repeated here.

[0066] 5. The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for predicting the temporary area occupied by power transmission line construction provided in any of the above technical solutions. Therefore, the computer-readable storage medium also includes all the beneficial effects of the method for predicting the temporary area occupied by power transmission line construction provided in any of the above technical solutions, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a flow chart of the method of the present invention.

[0068] Figure 2 It is a system diagram of the present invention.

[0069] Figure 3 It is a schematic diagram of the basic construction plan layout in an embodiment of the present invention.

[0070] Figure 4 It is a schematic diagram of the plane layout of the tower construction in an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0072] Embodiment 1:

[0073] See also Figures 1 to 4 , a method for predicting temporary area occupied by power transmission line construction, comprising the following steps:

[0074] S1, construct the construction type input model: classify the power transmission line construction into: foundation construction X1, tower construction X2, line construction X3 and transportation road construction X4, determine the main influencing factors of the temporary land area for each construction classification, and construct the input model for predicting the temporary land area of ​​different construction types;

[0075] S2, constructing a data processing prediction model: for different construction classifications, respectively construct prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, use past construction data to form training sets of particle swarm optimization BP neural networks of different construction types, use the training sets to train the particle swarm optimization BP neural networks of the corresponding construction types, and obtain the trained prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, and use the above trained models to obtain the prediction values ​​of temporary construction area occupied.

[0076] In S1, the main influencing factors of the foundation construction X1 include: voltage level x 11 , Line loop x 12 、Construction method x 13 , Terrain x 14 、Basic type x 15 ;

[0077] The main factors affecting tower construction X2 include: voltage level x 21 , Line loop x 22 、Tower assembly method x 23 、Construction method x 24 , Terrain x 25 ;

[0078] The main factors affecting the wiring construction X3 include: voltage level x 31 , Line loop x 32 , number of ground wire reels x 33 , Construction plan layout x 34 、The object being crossed x 35 ;

[0079] The main factors affecting the transport road construction X4 include: voltage level x 41 , Terrain x 42 , Construction organization design x 43 .

[0080] Construction plan layoutx 34 Including: the layout of construction sites and working surfaces, production and living auxiliary facilities;

[0081] Object being crossed x 35Includes: trees, farmland, buildings, railways, highways, roads, rivers, and lakes.

[0082] In S2, for different construction classifications, construction temporary area prediction models of particle swarm optimization BP neural network for different construction types are constructed respectively:

[0083] Input layer construction: During the model construction process, the main influencing factors XJ corresponding to the models of different construction types, where J = 1, 2, 3 or 4, are used as the input layer;

[0084] Hidden layer construction: The number of hidden neurons should be between the size of the input layer and the size of the output layer; the number of hidden neurons should be 2 / 3 of the input layer size plus 2 / 3 of the output layer size; the number of hidden neurons should be less than twice the size of the input layer;

[0085] Output layer construction: Taking the temporary area occupied by construction as the only indicator, the output of temporary area occupied by different construction types is constructed.

[0086] The particle swarm optimization BP neural network construction process is as follows:

[0087] a. Construct BP neural network, initialize it, and set particle swarm parameters;

[0088] b. Initialize the speed and position of all particles;

[0089] c. Calculate the fitness function value of each particle;

[0090] d. Determine whether the fitness function value is greater than the historical optimal value and the global optimal value. If yes, proceed to the next step; otherwise, return to step 3 to continue the calculation;

[0091] e. Update individual extreme values, global optimal values ​​and the position of each particle velocity;

[0092] f. Training samples and calculating errors;

[0093] g. Error accuracy judgment;

[0094] h. Determine whether the number of iterations has reached the maximum. If yes, terminate the output. If not, return to step 3 to continue the calculation.

[0095] When making predictions, attention should be paid to the overlap between the areas occupied by foundation construction and tower construction. The final temporary construction area can be obtained by deducting the area after overlap from the sum of the areas occupied by foundation construction or tower construction.

[0096] Embodiment 2:

[0097] A method for predicting temporary land occupation area for power transmission line construction comprises the following steps:

[0098] S1, construct the construction type input model: classify the power transmission line construction into: foundation construction X1, tower construction X2, line construction X3 and transportation road construction X4, determine the main influencing factors of the temporary land area for each construction classification, and construct the input model for predicting the temporary land area of ​​different construction types;

[0099] In S1, the main influencing factors of the foundation construction X1 include: voltage level x 11 , Line loop x 12 、Construction method x 13 , Terrain x 14 、Basic type x 15 ;

[0100] The main factors affecting tower construction X2 include: voltage level x 21 , Line loop x 22 、Tower assembly method x 23 、Construction method x 24 , Terrain x 25 ;

[0101] The main factors affecting the wiring construction X3 include: voltage level x 31 , Line loop x 32 , number of ground wire reels x 33 , Construction plan layout x 34 、The object being crossed x 35 ;

[0102] The main factors affecting the transport road construction X4 include: voltage level x 41 , Terrain x 42 , Construction organization design x 43 .

[0103] Construction plan layoutx 34 Including: the layout of construction sites and working surfaces, production and living auxiliary facilities;

[0104] Object being crossed x 35 Includes: trees, farmland, buildings, railways, highways, roads, rivers, and lakes.

[0105] Construction organization designx 43 Includes: selected technical solutions, progress identification table and various control and limitation conditions.

[0106] By setting up the construction type input model, it is possible to assign data to the main influencing factors of different construction classifications respectively, and use the assigned main influencing factors as input to complete the calculation.

[0107] S2, constructing a data processing prediction model: for different construction classifications, respectively construct prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, use past construction data to form training sets of particle swarm optimization BP neural networks of different construction types, use the training sets to train the particle swarm optimization BP neural networks of the corresponding construction types, and obtain the trained prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, and use the above trained models to obtain the prediction values ​​of temporary construction area occupied.

[0108] The particle swarm optimization BP neural network construction process is as follows:

[0109] This paper adopts a 3-layer BP neural network model: the input layer neurons are set to 5 for the tower and foundation, which are the 5 influencing factors selected in Chapter 2 of this paper, such as: X1 = (x11, x12, x13, x14, x15); the hidden layer is determined by trial and error, and finally the tower and foundation are determined to be 9 and 11 neurons respectively. The number of output layers is 1, which is the temporary area occupied by each foundation. When predicting, it should be noted that there is an overlap between the area occupied by foundation construction and tower construction. The temporary area occupied by each foundation is calculated according to the larger value of foundation construction or tower construction.

[0110] a. Construct BP neural network, initialize it, and set particle swarm parameters;

[0111] According to different construction classifications, the prediction models of temporary construction area occupied by different construction types based on particle swarm optimization BP neural network are constructed respectively:

[0112] Input layer construction: During the model construction process, the main influencing factors XJ corresponding to the models of different construction types, where J = 1, 2, 3 or 4, are used as the input layer;

[0113] Hidden layer construction: The number of hidden neurons should be between the size of the input layer and the size of the output layer; the number of hidden neurons should be 2 / 3 of the input layer size plus 2 / 3 of the output layer size; the number of hidden neurons should be less than twice the size of the input layer;

[0114] Output layer construction: Taking the temporary area occupied by construction as the only indicator, the output of temporary area occupied by different construction types is constructed.

[0115] Set the input vector, hidden layer output variable, output layer variable and expected output vector to be X, Y, O and D respectively, and the weight matrices from input layer to hidden layer and from hidden layer to output layer to be V and W respectively;

[0116] For the output layer, according to the BP neural network operation rules:

[0117] o k=f(net k ),k=1,2,…,l

[0118]

[0119] For the hidden layer, then:

[0120] y j =f(net j ),j=1,2,…,m

[0121]

[0122] The output error E is defined as follows:

[0123]

[0124] Further expansion and substitution, we finally get:

[0125]

[0126]

[0127] Based on the final result, the BP neural network weights can be continuously updated online until the result meets the set error requirement.

[0128] b. Initialize the speed and position of all particles;

[0129] Particle Swarm Optimization (PSO) is a random search method that simulates the foraging behavior of bird flocks. It optimizes the entire group through mutual cooperation between individuals and has the characteristics of evolutionary computing and swarm intelligence.

[0130] The algorithm regards each particle as a particle without mass and volume in multidimensional space, combines the information of the individual's best historical position and the group's best historical position, and approaches the target value at the corresponding speed. Suppose the position of particle i in n-dimensional space is x i =(x i1 ,x i2 ,…,x in ), flight speed v i =(v i1 ,v i2 ,…,v in ), which sets the direction and distance of particle movement, and measures the quality of particles by calculating the fitness value of particle position conversion. During this operation, particles constantly memorize and update their own optimal position pi and the optimal position p of all particles. g , and the corresponding optimal solution, are constantly tracked and updated.

[0131] c. Calculate the fitness function value of each particle;

[0132] The i-th particle evolves from the k-th generation to the k+1-th generation and is updated by the following formula:

[0133]

[0134]

[0135] Among them, v in is the nth component of the velocity of the ith particle, x in is the nth component of the position of the ith particle, p in is the nth component of the optimal position of the ith particle, p gn is the nth component of the optimal position of the population, ω is the inertia weight, whose size determines the particle's inheritance level of the current velocity, c1 and c2 are learning factors, which are positive constants, ξ and η are random numbers between (0, 1), and the velocity v is limited to v max Within value.

[0136] d. Determine whether the fitness function value is greater than the historical optimal value and the global optimal value. If yes, proceed to the next step; otherwise, return to step 3 to continue the calculation;

[0137] e. Update individual extreme values, global optimal values ​​and the position of each particle velocity;

[0138] f. Training samples and calculating errors;

[0139] g. Error accuracy judgment;

[0140] h. Determine whether the number of iterations has reached the maximum. If yes, terminate the output. If not, return to step 3 to continue the calculation.

[0141] When making predictions, attention should be paid to the overlap between the areas occupied by foundation construction and tower construction. The final temporary construction area can be obtained by deducting the area after overlap from the sum of the areas occupied by foundation construction or tower construction.

[0142] In order to verify the effectiveness of PSO-BP in predicting the temporary area occupied by transmission lines, this paper predicts and analyzes the temporary area occupied by transmission line towers (including foundations) during construction. 59 groups of 110 kV and 220 kV transmission line projects in a certain province are selected, 38 towers are selected as training samples, and the remaining 12 groups are selected as test samples. The BP algorithm and PSO-BP are used for prediction, and a comparative analysis is performed as shown in Table 1.

[0143] Table 1: Prediction and actual values ​​of basic BP and PSO-BP algorithms

[0144] (Unit: m 2 / base)

[0145]

[0146] A three-layer BP neural network model is used: the input layer neurons are set to 5, the tower and the foundation are set to 5, which are the 5 influencing factors selected in Chapter 2 of this article, such as: X1 = (x 11 , x 12 , x 13 , x 14 , x 15 ); The hidden layer is determined by trial and error. Finally, the tower and foundation are determined to be 9 and 11 neurons respectively. The number of output layers is 1, which is the temporary area occupied by each foundation. When predicting, it should be noted that there is overlap between the area occupied by foundation construction and tower construction. The temporary area occupied by each foundation is calculated according to the larger value of foundation construction or tower construction.

[0147] In order to compare the two prediction methods more intuitively, this paper selects the mean absolute percentage error MAPE to judge the prediction effect. The formula is as follows:

[0148]

[0149] Using the formula, the MAPE based on the BP neural network algorithm is 6.63%, and the MAPE based on the PSO-BP neural network algorithm is 3.91%, which is 41.03% higher than the prediction accuracy of the BP neural network algorithm. It can be concluded that the PSO-BP neural network algorithm model has significant advantages in predicting the accuracy of temporary occupied area.

[0150] (1) With the introduction of mechanized construction technology, the problem of traditional calculation methods being unable to meet complex needs has been solved, facing more complex environmental parameters, uneven distribution of corresponding data, and large deviations in a small part of the data.

[0151] (2) The average absolute percentage error of the PSO-BP hybrid algorithm is 3.91%, which is 41.03% higher than the prediction accuracy of the conventional BP neural network algorithm, greatly improving the prediction accuracy of the temporary area occupied by overhead line construction.

[0152] (3) In actual operation, since the PSO-BP hybrid algorithm combines the advantages of the PSO algorithm, namely, fast convergence speed and easy programming implementation, it will greatly simplify the operation frequency and shorten the prediction time in actual prediction.

[0153] (4) The present invention provides a calculation method for the feasibility study and preliminary estimate of subsequent power grid line projects in terms of the prediction of temporary construction area, and also provides an analysis basis for the reasons for the deviation of the actual settlement compensation cost level and the reasonable control of the line project compensation cost.

[0154] Embodiment 3:

[0155] A system for predicting temporary land occupation area for power transmission line construction, comprising:

[0156] Construct a construction type input module: for determining the main influencing factors of the temporary area occupied by each type of construction, and constructing input models for predicting the temporary area occupied by different types of construction respectively; for implementing step S1 described in Example 1.

[0157] Construct a data processing prediction module: for predicting the temporary construction area by using particle swarm optimization BP neural network for different construction classifications, and for implementing step S2 described in embodiment 1.

[0158] Embodiment 4:

[0159] A device for predicting temporary area occupied by power transmission line construction, comprising a memory and a processor, wherein the memory is used to store computer program codes and transmit the computer program codes to the processor;

[0160] The processor is used to execute the method for predicting the temporary area occupied by power transmission line construction described in Example 1 according to the instructions in the computer program code.

[0161] Embodiment 5:

[0162] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for predicting the temporary area occupied by power transmission line construction described in Example 1.

[0163] Generally speaking, the computer instructions for implementing the method of the present invention may be carried in any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media, except for the signal itself that is temporarily propagating.

[0164] Computer-readable storage media, for example, may be, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with a system, device or device for executing instructions.

[0165] One or more programming languages ​​or their combinations can be used to write computer program codes for performing the operation of the present invention. These programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and also include conventional procedural programming languages, such as C language or similar programming languages. In particular, Python language suitable for neural network calculations and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through various types of networks, including a local area network (LAN) or a wide area network (WAN), or an Internet connection is performed through an Internet service provider.

[0166] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for predicting temporary land occupation area for power transmission line construction, characterized in that: The steps include: S1, construct the construction type input model: classify the power transmission line construction into: foundation construction X1, tower construction X2, line construction X3 and transportation road construction X4, determine the main influencing factors of the temporary land area for each construction classification, and construct the input model for predicting the temporary land area of ​​different construction types; S2, constructing a data processing prediction model: for different construction classifications, respectively construct prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, use past construction data to form training sets of particle swarm optimization BP neural networks of different construction types, use the training sets to train the particle swarm optimization BP neural networks of the corresponding construction types, and obtain the trained prediction models of temporary construction area occupied by particle swarm optimization BP neural networks of different construction types, and use the above trained models to obtain the prediction values ​​of temporary construction area occupied.

2. A method for predicting temporary area occupied by power transmission line construction according to claim 1, characterized in that: In S1, the main influencing factors of the foundation construction X1 include: voltage level x 11 , Line loop x 12 、Construction method x 13 , Terrain x 14 、Basic type x 15 ; The main factors affecting tower construction X2 include: voltage level x 21 , Line loop x 22 、Tower assembly method x 23 、Construction method x 24 , Terrain x 25 ; The main factors affecting the wiring construction X3 include: voltage level x 31 , Line loop x 32 , number of ground wire reels x 33 , Construction plan layout x 34 、The object being crossed x 35 ; The main factors affecting the transport road construction X4 include: voltage level x 41 , Terrain x 42 , Construction organization design x 43 .

3. A method for predicting temporary area occupied by power transmission line construction according to claim 2, characterized in that ； Construction plan layoutx 34 Including: the layout of construction sites and working surfaces, production and living auxiliary facilities; Object being crossed x 35 Includes: trees, farmland, buildings, railways, highways, roads, rivers, and lakes.

4. A method for predicting temporary area occupied by power transmission line construction according to claim 1, 2 or 3, characterized in that: In S2, for different construction classifications, construction temporary area prediction models of particle swarm optimization BP neural network for different construction types are constructed respectively: Input layer construction: During the model construction process, the main influencing factors X corresponding to the models of different construction types are j , where j = 1, 2, 3 or 4, as the input layer; Hidden layer construction: The number of hidden neurons should be between the size of the input layer and the size of the output layer; the number of hidden neurons should be 2 / 3 of the input layer size plus 2 / 3 of the output layer size; the number of hidden neurons should be less than twice the size of the input layer; Output layer construction: Taking the temporary area occupied by construction as the only indicator, the output of temporary area occupied by different construction types is constructed.

5. A method for predicting temporary area occupied by power transmission line construction according to claim 4, characterized in that: The particle swarm optimization BP neural network construction process is as follows: a. Construct BP neural network, initialize it, and set particle swarm parameters; b. Initialize the speed and position of all particles; c. Calculate the fitness function value of each particle; d. Determine whether the fitness function value is greater than the historical optimal value and the global optimal value. If yes, proceed to the next step; otherwise, return to step 3 to continue the calculation; e. Update individual extreme values, global optimal values ​​and the position of each particle velocity; f. Training samples and calculating errors; g. Error accuracy judgment; h. Determine whether the number of iterations has reached the maximum. If yes, terminate the output. If not, return to step 3 to continue the calculation.

6. A method for predicting temporary area occupied by power transmission line construction according to claim 5, characterized in that: When making predictions, attention should be paid to the overlap between the areas occupied by foundation construction and tower construction. The final temporary construction area can be obtained by deducting the area after overlap from the sum of the areas occupied by foundation construction or tower construction.

7. A system for predicting temporary land occupation area for power transmission line construction, characterized by: include: Constructing a construction type input module: This module is used to determine the main influencing factors of the temporary land area for each type of construction, and to construct input models for predicting the temporary land area for different types of construction; Construct a data processing prediction module: It is used to predict the temporary construction area according to different construction classifications using particle swarm optimization BP neural network.

8. A device for predicting temporary land occupation area for power transmission line construction, characterized by: The method comprises a memory and a processor, wherein the memory is used to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method according to any one of claims 2 to 6 according to the instructions in the computer program code.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 2 to 6 is implemented.

Images