Soil resistivity prediction method, system and equipment and storage medium

Abstract

The invention discloses a soil resistivity prediction method, system and device, and a storage medium. The method comprises the following steps: S1, acquiring soil information; s2, constructing an ELM (Extreme Learning Machine)-based prediction model; s3, performing parameter optimization on the prediction model of the ELM by adopting a Harlisia eagle algorithm; and S4, taking the soil information as an input vector of the optimized ELM prediction model, and outputting to obtain the predicted soil resistivity. Model prediction accuracy is used as a fitness function, and hyper-parameter optimization can be automatically and efficiently carried out by using a bionic optimization algorithm. A machine learning technology is used for fully learning a large amount of soil information, multiple factors influencing the soil resistivity are considered, and the influence of factors such as the soil structure, the water content and the ionization degree of pore water is comprehensively considered. By constructing the soil resistivity prediction model and considering the comprehensive prediction model of a plurality of environmental factors, the influence of various factors on the soil resistivity is considered more comprehensively.

Description

Technical Field

[0001] The invention belongs to the field of lightning protection and relates to a soil resistivity prediction method, system, equipment and storage medium. Background Art

[0002] Soil resistivity is an important parameter to measure the conductivity of soil and plays a key role in many engineering fields. With the advancement of science and technology, the application of soil resistivity detection technology is becoming more and more extensive, including grounding design of power systems, lightning protection measures for construction projects, soil pollution monitoring and remediation in environmental engineering, grounding systems and lightning protection facilities for transportation projects, etc. These applications all emphasize the importance of soil resistivity prediction, because accurate soil resistivity data can help optimize engineering design and reduce risks and costs.

[0003] The existing soil resistivity prediction methods have the following shortcomings: 1) Although the empirical formula obtained by fitting a large amount of experimental data is easy to use, it is often limited by region and soil type. The soil composition and structure of different regions are different, so the empirical formula may not be able to accurately predict the soil resistivity of all regions. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a soil resistivity prediction method, system, device and storage medium, which can accurately predict soil resistivity.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A soil resistivity prediction method includes the following process: S1, obtain soil information; S2, construct a prediction model based on ELM; S3, Harris Eagle algorithm is used to optimize the parameters of the ELM prediction model; S4, taking the soil information as the input vector of the prediction model of the optimized ELM, and outputting the predicted soil resistivity.

[0006] Preferably, the soil information includes soil structure, soil water content and pore water ionization information.

[0007] Preferably, in S1, the acquired soil information is preprocessed, irrelevant information and erroneous information are removed, the label order is disrupted and reordered, and the data is divided into a training set and a test set in a ratio of 8:2.

[0008] Furthermore, in S3, the acquired soil data is used as the input value and the soil resistivity is used as the output value to train the ELM prediction model, iteratively update the model, use the test set to test the prediction ability of the trained model, adjust the model parameters according to the monitoring results, and finally realize the prediction of soil resistivity.

[0009] Preferably, in S3, the Harris Eagle algorithm uses the accuracy as the fitness function for optimization, and optimizes the number of hidden layer nodes and the regularization coefficient of the ELM prediction model.

[0010] Preferably, in S4, the predicted soil resistivity is corrected for soil temperature.

[0011] Further, the temperature correction coefficient K is expressed as:

[0012] in: is the soil grounding resistance at different temperatures, is the soil grounding resistance at 20°C.

[0013] A soil resistivity prediction system, comprising: A soil information acquisition module, used to acquire soil information; Prediction model building module, used to build ELM-based prediction models; Parameter optimization module, used to optimize the parameters of the ELM prediction model using the Harris Eagle algorithm; The prediction module is used to take soil information as the input vector of the prediction model of the optimized ELM and output the predicted soil resistivity.

[0014] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the soil resistivity prediction method when executing the computer program.

[0015] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the soil resistivity prediction method are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention uses the model prediction accuracy as the fitness function and uses the bionic optimization algorithm to realize automatic and efficient hyperparameter optimization. The machine learning technology is used to fully learn a large amount of soil information, taking into account the various factors affecting soil resistivity, and comprehensively considering the influence of factors such as soil structure, water content and ionization degree of pore water. By constructing a comprehensive prediction model of soil resistivity prediction model considering multiple environmental factors, the influence of various factors on soil resistivity is more comprehensively considered.

[0017] Furthermore, soil temperature usually has a significant impact on soil resistivity, so after obtaining the predicted value through the prediction model, it is necessary to correct the current soil temperature to meet the needs of the design project. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural block diagram of the soil resistivity prediction method of the present invention; Figure 2 is a diagram of the ELM structure of the present invention; Figure 3 It is the different attack strategies of the HHO of the present invention; Figure 4 It is a flow chart of constructing the HHO-ELM model of the present invention. DETAILED DESCRIPTION

[0019] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0020] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs. The terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0022] The disclosure below provides many different embodiments or examples to realize different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplicity and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific examples of processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0023] like Figure 1 As shown in FIG. 1 , the soil resistivity prediction method based on the extreme learning machine of the present invention includes the following process: Step 1: Get data Soil information, including soil structure, soil water content, and pore water ionization information, was obtained. The acquired data was preprocessed to remove irrelevant and erroneous information, the label order was disrupted and reordered, and the data was divided into a training set and a test set in a ratio of 8:2.

[0024] Step 2: Build a prediction model based on ELM like Figure 2 As shown in the figure, the extreme learning machine (ELM) is essentially a special feedforward neural network. Compared with traditional neural networks, ELM has faster convergence speed and higher learning efficiency, and is suitable as an algorithm for soil resistivity prediction.

[0025] For the training set T0={(xi, yi), i=1, 2, ..., N}, the input feature vector xi∈Rm and yi∈Rn are the output vectors obtained by the ELM network. Then the expressions of the input vector and the output vector are:

[0026]

[0027] For the ELM model with L hidden layer nodes, the target vector is Oi=[oi1,oi2,…,oim]∈Rm. If the error between the output vector yi and the target vector Oi is approximately 0, the ELM model can be expressed as:

[0028] Where: is the output weight vector of the jth hidden layer node; g(∙) is the activation function of the hidden layer; is the input weight vector of the jth hidden layer node; is the bias vector corresponding to the jth hidden node.

[0029] The above model can be expressed by the output matrix H as:

[0030] in:

[0031] The matrix form of the least squares solution to represent ELM is expressed as:

[0032] Where: H + is the Moore-Penrose generalized inverse matrix of the output layer matrix H.

[0033] Step 3: Hyperparameter optimization of the ELM prediction model combined with the Harris Eagle algorithm However, the extreme learning machine has many hyperparameters, and manual optimization of the model parameters requires a lot of time to obtain a higher prediction accuracy result. Therefore, the bionic optimization algorithm is combined to optimize the hyperparameters of the ELM algorithm.

[0034] The test accuracy is selected as the fitness function for optimization, and the number of hidden layer nodes and regularization coefficient of ELM are optimized in combination with the Harris Hawk algorithm. The algorithm simulates the predation process of the Harris Hawk and is divided into the exploration stage, the exploration and development transformation stage, and the development stage. Compared with the traditional optimization algorithm, the algorithm has the advantages of simple structure, few parameters, and easy program implementation.

[0035] (1) Exploration phase In this phase, Harris's hawk randomly perches at some locations and waits for and discovers prey according to two strategies. The initialization expression is:

[0036] Where: Xrabbit(t) is the position of the rabbit, X (t) is the current position vector of the eagle, r and q are internal random numbers with a value range of (0,1) and are updated at each iteration. LB and UB show the upper and lower bounds of the variables, Xrand (t) is a randomly selected eagle from the current population, and Xm is the average position of the current eagle population. The expression for the average position of the eagle is as follows:

[0037] Where Xi(t) represents the position of each eagle in iteration t, and N represents the total number of eagles.

[0038] (2) Exploration and development transformation stage In this stage, different predation behaviors are changed according to the escape energy of the prey. The energy of the prey is greatly consumed in the escape behavior, resulting in a significant reduction in energy. To simulate this step, the energy of the prey is modeled as:

[0039] Where: E is the escape energy of the prey, t is the current number of iterations, T is the maximum number of iterations, E0 is the initial state of its energy, and rand is a random number in the range (0,1).

[0040] (3) Development stage During this phase, Harris's Hawks perform surprise attacks by attacking the expected prey that they spotted during the previous phase. However, prey may escape during the pursuit. Therefore, Harris's Hawks have different pursuit methods in real situations. Figure 3 As shown in the figure, according to the prey escape behavior and pursuit strategy of Harris's Hawk, four possible strategies are proposed in HHO to simulate the attack phase, including soft siege strategy, hard siege strategy, soft siege strategy with gradual rapid pounce, and hard siege strategy with gradual rapid pounce.

[0041] Assume that r is the probability of the prey escaping before a sudden attack, and the value range is [0,1]. When r < 0.5, it means that the probability of the prey escaping successfully is very high, and r ≥ 0.5 means that the probability of the prey escaping successfully is very low. Regardless of whether the prey escapes successfully or not, the eagle will use the remaining energy of the prey to softly or hard siege the prey. In reality, the eagle will get closer and closer to the intended prey.

[0042] ①Soft siege When 0.5≤|Er|≤1 and r≥0.5, the prey has sufficient physical strength, but the probability of escaping the Harris Hawk is very small. The prey's position is updated as follows:

[0043]

[0044] Where: ∆X(t) is the difference between the position vector of the rabbit in iteration t and the current position. The value of J changes randomly in each iteration to simulate the nature of the rabbit's movement.

[0045] ②Hard siege When 0.5≤|Er|≤1 and r≥0.5, the prey's physical strength is relatively scarce, and the probability of escaping the Harris Hawk's pursuit is very small. The prey's position is updated as follows:

[0046] ③ Soft siege with gradual and rapid raids When 0.5≤|E|≤1 and r<0.5, the prey is physically strong and has a greater chance of escaping the pursuit. At this time, the Harris Hawk will adopt a further soft siege strategy to prevent the prey from escaping. At this time, the expression for the hawk to evaluate the next action is:

[0047] Assume that a Harris hawk approaches prey based on the Levy flight function:

[0048]

[0049]

[0050] Where: D is the dimension, S(·) is the fitness function, LF is the levy flight function, u and v are random numbers in the range of (0,1), Is a constant, default is 1.5.

[0051] The final policy expression for updating the eagle's position during the soft siege phase is as follows:

[0052] Where: Y, Z are obtained from equations (4.22)-(4.23).

[0053] ④ Hard siege with progressive rapid assault When |E|<0.5 and r<0.5, the prey is exhausted but still has a great chance of escaping. The Harris Hawk position update expression is as follows:

[0054] like Figure 4As shown in the figure, the collected soil data is used as the input value and the soil resistivity is used as the output value to train the ELM, and the soil resistivity prediction model is obtained by iteratively updating the model. The prediction ability of the trained model is tested using the test set, and the model parameters are adjusted according to the monitoring results to finally realize the prediction of soil resistivity.

[0055] Step 4: Result Correction The soil resistivity predicted by the above steps only considers soil-related information and does not analyze soil temperature. Therefore, the predicted soil resistivity needs to be adjusted through result correction.

[0056] The temperature correction coefficient K is expressed as:

[0057] in: is the soil grounding resistance at different temperatures, is the soil grounding resistance at 20°C.

[0058] Although the empirical formula obtained by fitting a large amount of experimental data in the prior art is easy to use, such formulas are usually fitted based on soil data of a specific region or a specific type, and therefore may not accurately reflect the soil characteristics of other regions. The present invention considers the influence of various factors on soil resistivity by constructing a comprehensive prediction model of soil resistivity prediction model taking into account multiple environmental factors, and more comprehensively considers the influence of various factors on soil resistivity.

[0059] The traditional ELM model hyperparameter optimization workload is huge. Setting hyperparameters based on experience can easily cause the optimization results to fall into a local optimal solution, resulting in poor model performance. The present invention uses the model prediction accuracy as the fitness function and uses a bionic optimization algorithm to achieve automatic and efficient hyperparameter optimization.

[0060] Generally, soil temperature has a great influence on soil resistivity. Therefore, after obtaining the predicted value through the prediction model, it is necessary to correct the current soil temperature in the present invention to meet the design engineering requirements.

[0061] The following are device embodiments of the present invention, which can be used to perform method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0062] In yet another embodiment of the present invention, a soil resistivity prediction system is provided, which can be used to implement the above-mentioned soil resistivity prediction method. Specifically, the soil resistivity prediction system includes a soil information acquisition module, a prediction model construction module, a parameter optimization module and a prediction module.

[0063] Among them, the soil information acquisition module is used to obtain soil information.

[0064] The prediction model building module is used to build a prediction model based on ELM.

[0065] The parameter optimization module is used to optimize the parameters of the ELM prediction model using the Harris Eagle algorithm.

[0066] The prediction module is used to take soil information as the input vector of the prediction model of the optimized ELM and output the predicted soil resistivity.

[0067] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the soil resistivity prediction method, including: S1, obtaining soil information; S2, constructing a prediction model based on ELM; S3, using the Harris Eagle algorithm to optimize the parameters of the ELM prediction model; S4, using the soil information as the input vector of the optimized ELM prediction model, and outputting the predicted soil resistivity.

[0068] In another embodiment, the present invention further provides a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory.

[0069] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the soil resistivity prediction method in the above embodiment; one or more instructions in the computer-readable storage medium are loaded by the processor and the following steps are executed: S1, obtaining soil information; S2, building a prediction model based on ELM; S3, using the Harris Eagle algorithm to optimize the parameters of the ELM prediction model; S4, using the soil information as the input vector of the optimized ELM prediction model, and outputting the predicted soil resistivity.

[0070] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0071] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0075] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0078] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

[0079] It should be understood that the above description is for illustration and not for limitation. Many embodiments and many applications beyond the examples provided will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this patent should not be determined with reference to the above description, but rather with reference to the preceding claims and the full scope of equivalents to which such claims are entitled. For the purpose of comprehensiveness, all articles and references, including disclosures of patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the preceding claims is not intended to be a waiver of such subject matter, nor should it be considered that the applicant has not considered such subject matter to be part of the disclosed inventive subject matter.

Claims

1. A soil resistivity prediction method, characterized in that: The process includes: S1, obtain soil information; S2, construct a prediction model based on ELM; S3, Harris Eagle algorithm is used to optimize the parameters of the ELM prediction model; S4, taking the soil information as the input vector of the prediction model of the optimized ELM, and outputting the predicted soil resistivity.

2. The soil resistivity prediction method according to claim 1, characterized in that: Soil information includes soil structure, soil moisture content and pore water ionization information.

3. The soil resistivity prediction method according to claim 1, characterized in that: In S1, the acquired soil information is preprocessed to remove irrelevant and erroneous information, the label order is disrupted and reordered, and the data is divided into a training set and a test set in a ratio of 8:

2.

4. The soil resistivity prediction method according to claim 3, characterized in that: In S3, the acquired soil data is used as the input value and the soil resistivity is used as the output value to train the ELM prediction model, iteratively update the model, use the test set to test the prediction ability of the trained model, adjust the model parameters according to the monitoring results, and finally realize the prediction of soil resistivity.

5. The soil resistivity prediction method according to claim 1, characterized in that: In S3, the Harris Eagle algorithm uses the accuracy as the fitness function for optimization and optimizes the number of hidden layer nodes and the regularization coefficient of the ELM prediction model.

6. The soil resistivity prediction method according to claim 1, characterized in that: In S4, the predicted soil resistivity is corrected for soil temperature.

7. The soil resistivity prediction method according to claim 6, characterized in that: The temperature correction coefficient K is expressed as: in: is the soil grounding resistance at different temperatures, is the soil grounding resistance at 20°C.

8. A soil resistivity prediction system, characterized in that: include: A soil information acquisition module, used to acquire soil information; Prediction model building module, used to build ELM-based prediction models; Parameter optimization module, used to optimize the parameters of the ELM prediction model using the Harris Eagle algorithm; The prediction module is used to take soil information as the input vector of the prediction model of the optimized ELM and output the predicted soil resistivity.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the soil resistivity prediction method according to any one of claims 1 to 7 are implemented.

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

Images