Water and soil anisotropy bank collapse calculation method and device based on machine learning

Abstract

The invention relates to the technical field of water conservancy and hydropower, and discloses a water and soil anisotropy bank collapse calculation method and device based on machine learning, and the method comprises the steps: building a soil and water distribution prediction model based on a supervised machine learning model; collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil and water distribution prediction model to obtain a virtual image of the underwater bank slope; and calculating the average slope angle of the underwater bank slope according to the virtual image, and judging whether bank collapse occurs or not according to the average slope angle. A bank slope soil-water distribution prediction model is obtained based on a machine learning model by utilizing a relatively large difference between thermal parameters of soil and water, so that quantitative evaluation of the bank collapse susceptibility of the underwater bank slope is realized, and the method is a direction of intelligent development of bank slope stability analysis in the future.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy and hydropower, and in particular to a method and device for calculating water and soil anisotropic bank collapse based on machine learning. Background Art

[0002] The stability analysis of reservoir bank slope is one of the important links to ensure the safe operation of reservoir dam. In the existing research on bank slope stability analysis, most of them are based on data derivation of calculation formulas and establishment of analysis models for calculation. These methods are based on theory, and the established formulas and calculation models are too idealized, ignoring the influence of the actual environment, and therefore are not universal. Summary of the invention

[0003] In view of this, the present invention provides a method and device for calculating water-soil anisotropic bank collapse based on machine learning, so as to solve the problem that the existing research on slope stability analysis ignores the influence of the actual environment, resulting in the problem of lack of versatility.

[0004] In a first aspect, the present invention provides a method for calculating anisotropic soil and water bank collapse based on machine learning, the method comprising:

[0005] Construct soil-water distribution prediction model based on supervised machine learning model;

[0006] Collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater slope;

[0007] The average slope angle of the underwater slope is calculated according to the virtual image, and whether the bank collapse occurs is determined according to the average slope angle.

[0008] The present invention provides a method for calculating anisotropic soil and water bank collapse based on machine learning, including: constructing a soil-water distribution prediction model based on a supervised machine learning model; collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater bank slope; calculating the average slope angle of the underwater bank slope according to the virtual image, and judging whether bank collapse occurs according to the average slope angle. By utilizing the large difference in thermal parameters between soil and water and obtaining a bank slope soil-water distribution prediction model based on a machine learning model, a quantitative evaluation of the susceptibility of underwater bank collapse is achieved, which is the direction of future intelligent development of bank slope stability analysis.

[0009] In an optional implementation, the soil-water distribution prediction model is constructed based on a supervised machine learning model, including:

[0010] Obtain historical specific heat capacity data of underwater slope soil and water materials, and establish a specific heat capacity database;

[0011] Dividing the specific heat capacity database into a training set and a test set;

[0012] The training set is input into a supervised machine learning model for analysis to construct a soil and water distribution prediction model.

[0013] Since color images contain too much information, when performing image recognition, it is actually sufficient to use the information in grayscale images. Therefore, the color images are processed into grayscale images through a supervised machine learning model, thereby simplifying the matrix and increasing the calculation speed.

[0014] In an optional embodiment, the method further includes:

[0015] Detect the location of the bank slope;

[0016] Thermal sensors are arranged at different intervals along the longitudinal and transverse directions of the cross section, and are arranged at equal intervals along the width of the river bank;

[0017] Receive the specific heat capacity data of soil and water materials transmitted by the thermal sensor.

[0018] The image data formed by the specific heat capacity data is called the measured image. Considering the price and frequency of thermal sensor measurement, the image obtained by thermal sensor measurement can be machine learned and predicted to reduce the cost and detection frequency of thermal sensor measurement, and also predict future development trends.

[0019] In an optional embodiment, the thermal sensor points place the bank slope in a rectangular parallelepiped.

[0020] In an optional implementation, the average slope angle determines whether bank collapse occurs, including:

[0021] When the average slope angle is greater than the sediment dynamic water repose angle, it is determined that bank collapse will occur;

[0022] When the average slope angle is not greater than the sediment dynamic water repose angle, it is determined that bank collapse will not occur.

[0023] In an optional embodiment, the method further includes:

[0024] The test set is used to evaluate the performance and generalization ability of the soil-water distribution prediction model.

[0025] In a second aspect, the present invention provides a device for calculating anisotropic soil and water bank collapse based on machine learning, the device comprising:

[0026] A building block for building a soil-water distribution prediction model based on a supervised machine learning model;

[0027] A processing module, used for collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater slope;

[0028] The judgment module is used to calculate the average slope angle of the underwater slope according to the virtual image, and judge whether the bank collapse occurs according to the average slope angle.

[0029] The present invention provides a device for calculating anisotropic soil and water bank collapse based on machine learning, including: a construction module for constructing a soil-water distribution prediction model based on a supervised machine learning model; a processing module for collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater bank slope; a judgment module for calculating the average slope angle of the underwater bank slope according to the virtual image, and judging whether bank collapse has occurred according to the average slope angle. By utilizing the large difference in thermal parameters between soil and water and obtaining a bank slope soil-water distribution prediction model based on a machine learning model, a quantitative evaluation of the susceptibility of underwater bank collapse is achieved, which is the direction of future intelligent development of bank slope stability analysis.

[0030] In an optional embodiment, the building block includes:

[0031] An acquisition unit is used to acquire historical specific heat capacity data of underwater slope soil and water materials and establish a specific heat capacity database;

[0032] A division unit, used for dividing the specific heat capacity database into a training set and a test set;

[0033] The analysis unit is used to input the training set into a supervised machine learning model for analysis and to construct a soil-water distribution prediction model.

[0034] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the machine learning-based method for calculating anisotropic soil and water bank collapse of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for calculating anisotropic soil and water bank collapse based on machine learning according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 is a flow chart of a method for calculating anisotropic soil and water bank collapse based on machine learning according to an embodiment of the present invention;

[0038] Figure 2 is a structural block diagram of a device for calculating anisotropic soil and water bank collapse based on machine learning according to an embodiment of the present invention;

[0039] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] The present invention provides a method for calculating bank collapse based on water-soil anisotropy, which calculates the critical angle of repose of the bank slope through the anisotropy of water and soil and evaluates the susceptibility of bank collapse.

[0042] According to an embodiment of the present invention, an embodiment of a method for calculating anisotropic soil and water collapse based on machine learning is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0043] In this embodiment, a method for calculating anisotropic soil and water bank collapse based on machine learning is provided. Figure 1 is a flow chart of a method for calculating anisotropic soil and water bank collapse based on machine learning according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0044] Step S11, constructing a soil water distribution prediction model based on a supervised machine learning model.

[0045] Specifically, the above step S11 includes:

[0046] Step S111, obtaining historical specific heat capacity data of underwater slope soil and water materials, and establishing a specific heat capacity database.

[0047] Step S112, dividing the specific heat capacity database into a training set and a test set.

[0048] Step S113, input the training set into the supervised machine learning model for analysis to build a soil water distribution prediction model.

[0049] In an embodiment of the present invention, a database is established using historical specific heat capacity data as samples. A model training set and a test set are constructed based on the collected data. After randomly shuffling the data in the database, 80% of the data is used as a training set for training; 20% of the data is used as a test set for testing. By observing and learning the sample data in the training set, the supervised machine learning model can obtain characteristics and rules. The supervised machine learning model is essentially a data-driven model. It mines potential information in a large amount of data through algorithms and establishes connections between data. When multiple image analysis data have certain rules to follow, it means that the imaging data is available. A soil and water distribution prediction model is then established based on the supervised machine learning model. Among them, the test set is used to evaluate the performance and generalization ability of the soil and water distribution prediction model.

[0050] Since color images contain too much information, when performing image recognition, it is actually sufficient to use the information in grayscale images. Therefore, the color images are processed into grayscale images through a supervised machine learning model, thereby simplifying the matrix and increasing the calculation speed.

[0051] Step S12, collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into a soil-water distribution prediction model to obtain a virtual image of the underwater slope.

[0052] Specifically, by inputting the current specific heat capacity data returned by the thermal sensor into the soil-water distribution prediction model, the soil-water two-phase distribution of the underwater slope can be obtained. In the three-dimensional space, it can be determined which areas are soil and which areas are water, so that a rough virtual image of the underwater slope can be established.

[0053] Step S13, calculating the average slope angle of the underwater slope according to the virtual image, and judging whether the bank collapse occurs according to the average slope angle.

[0054] Specifically, the above step S13 includes:

[0055] Step S131, when the average slope angle is greater than the sediment dynamic water repose angle, it is determined that bank collapse may occur.

[0056] Step S132: when the average slope angle is not greater than the sediment dynamic water repose angle, it is determined that bank collapse will not occur.

[0057] In an embodiment of the present invention, the average slope of the underwater slope can be calculated based on the obtained virtual image of the underwater slope, so as to determine whether a bank collapse occurs. When the average slope angle is greater than the dynamic water repose angle of the sediment, the slope will be eroded, and the slope of the slope after the collapse is close to the underwater repose angle of the sediment, and the underwater repose angle can be obtained by various existing calculation formulas. Among them, the angle of repose refers to the angle between the surface of the deposit formed by the particles or the particle deposit in the equilibrium state and the horizontal plane. It describes the stacking characteristics of the particles in a static state, or in other words, it is the slope at which the particles maintain the maximum stacking characteristics.

[0058] The present invention provides a method for calculating anisotropic soil and water bank collapse based on machine learning, including: constructing a soil-water distribution prediction model based on a supervised machine learning model; collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater bank slope; calculating the average slope angle of the underwater bank slope according to the virtual image, and judging whether bank collapse occurs according to the average slope angle. By utilizing the large difference in thermal parameters between soil and water and obtaining a bank slope soil-water distribution prediction model based on a machine learning model, a quantitative evaluation of the susceptibility of underwater bank collapse is achieved, which is the direction of future intelligent development of bank slope stability analysis.

[0059] In an optional embodiment, the method further includes:

[0060] Step S14, detecting the position of the bank slope.

[0061] Step S15, thermal sensors are arranged at different intervals along the longitudinal direction and the transverse direction of the cross section, and thermal sensors are arranged at equal intervals along the width direction of the river bank.

[0062] Step S16, receiving the specific heat capacity data of the soil and water materials transmitted by the thermal sensor.

[0063] Specifically, thermal sensors are placed at different points on the underwater bank slope to output the specific heat capacity of soil and water (the two materials are quite different, with the specific heat capacity of mud and water being about 0.92 and that of water being about 4.2, in units of W / (m*℃-1), so they can be distinguished intuitively). When placing thermal sensors, the approximate position of the bank slope is first detected, and thermal sensors are placed at different intervals along the longitudinal and transverse directions of the cross section (the smaller the interval at the slope angle, the more points there are), and at equal intervals along the width of the river bank. The thermal sensor points can place the bank slope in a rectangular parallelepiped.

[0064] After the thermal sensors are deployed in the above manner, the specific heat capacity data returned by the thermal sensors are received and recorded to establish a historical specific heat capacity database. When the historical specific heat capacity data is needed, it is directly called from the historical specific heat capacity database; when the current specific heat capacity data is needed, the specific heat capacity data returned by the thermal sensors is directly used.

[0065] This embodiment utilizes the difference in thermal parameters between soil and water, based on the detection results of thermal sensors, and accurately constructs the soil and water distribution through image pixel processing and supervised machine learning, which is then compared with the critical repose angle obtained from water and soil anisotropy to determine the area of ​​bank collapse and the probability of occurrence.

[0066] Among them, the image data formed by the specific heat capacity data is called the measured image. Considering the price and frequency of thermal sensor measurement, machine learning and prediction can be performed after the image obtained by thermal sensor measurement, which can reduce the cost and detection frequency of thermal sensor measurement and predict future development trends.

[0067] In this embodiment, a device for calculating anisotropic soil and water bank collapse based on machine learning is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0068] This embodiment provides a device for calculating water and soil anisotropy bank collapse based on machine learning, such as Figure 2 As shown, including:

[0069] Construction module 21 is used to construct a soil water distribution prediction model based on a supervised machine learning model.

[0070] The processing module 22 is used to collect the current specific heat capacity data of the soil and water materials, and input the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater slope.

[0071] The judgment module 23 is used to calculate the average slope angle of the underwater slope according to the virtual image, and judge whether the bank collapse occurs according to the average slope angle.

[0072] In an optional embodiment, the construction module 21 includes:

[0073] The acquisition unit 211 is used to acquire the historical specific heat capacity data of the underwater slope soil and water materials and establish a specific heat capacity database.

[0074] The division unit 212 is used to divide the specific heat capacity database into a training set and a test set.

[0075] The analysis unit 213 is used to input the training set into the supervised machine learning model for analysis and construct a soil-water distribution prediction model.

[0076] Since color images contain too much information, when performing image recognition, it is actually sufficient to use the information in grayscale images. Therefore, the color images are processed into grayscale images through a supervised machine learning model, thereby simplifying the matrix and increasing the calculation speed.

[0077] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0078] The water and soil anisotropy shore collapse calculation device based on machine learning in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0079] The present invention provides a device for calculating anisotropic soil and water bank collapse based on machine learning, including: a construction module for constructing a soil-water distribution prediction model based on a supervised machine learning model; a processing module for collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater bank slope; a judgment module for calculating the average slope angle of the underwater bank slope according to the virtual image, and judging whether bank collapse has occurred according to the average slope angle. By utilizing the large difference in thermal parameters between soil and water and obtaining a bank slope soil-water distribution prediction model based on a machine learning model, a quantitative evaluation of the susceptibility of underwater bank collapse is achieved, which is the direction of future intelligent development of bank slope stability analysis.

[0080] The embodiment of the present invention also provides a computer device having the above Figure 2 The device for calculating soil and water anisotropy bank collapse based on machine learning is shown.

[0081] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0082] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0083] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0084] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0085] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0086] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0087] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0088] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0089] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for calculating anisotropic soil and water bank collapse based on machine learning, characterized in that: The method comprises: Construct soil-water distribution prediction model based on supervised machine learning model; Collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater slope; The average slope angle of the underwater slope is calculated according to the virtual image, and whether the bank collapse occurs is determined according to the average slope angle.

2. The method for calculating anisotropic soil and water bank collapse based on machine learning according to claim 1 is characterized in that: The soil-water distribution prediction model is constructed based on the supervised machine learning model, including: Obtain historical specific heat capacity data of underwater slope soil and water materials, and establish a specific heat capacity database; Dividing the specific heat capacity database into a training set and a test set; The training set is input into a supervised machine learning model for analysis to construct a soil and water distribution prediction model.

3. The method for calculating anisotropic soil and water bank collapse based on machine learning according to claim 2 is characterized in that: The method further comprises: Detect the location of the bank slope; Thermal sensors are arranged at different intervals along the longitudinal and transverse directions of the cross section, and are arranged at equal intervals along the width of the river bank; Receive the specific heat capacity data of soil and water materials transmitted by the thermal sensor.

4. The method for calculating anisotropic soil and water bank collapse based on machine learning according to claim 3 is characterized in that: The thermal sensor points place the bank slope in a rectangular parallelepiped.

5. The method for calculating anisotropic soil and water bank collapse based on machine learning according to claim 1, characterized in that: The average slope angle determines whether bank collapse occurs, including: When the average slope angle is greater than the sediment dynamic water repose angle, it is determined that bank collapse will occur; When the average slope angle is not greater than the sediment dynamic water repose angle, it is determined that bank collapse will not occur.

6. The method for calculating anisotropic soil and water bank collapse based on machine learning according to claim 2, characterized in that: The method further comprises: The test set is used to evaluate the performance and generalization ability of the soil-water distribution prediction model.

7. A device for calculating anisotropic landslides based on machine learning, characterized in that: The device comprises: A building block for building a soil-water distribution prediction model based on a supervised machine learning model; A processing module, used for collecting current specific heat capacity data of soil and water materials, and inputting the current specific heat capacity data into the soil-water distribution prediction model to obtain a virtual image of the underwater slope; The judgment module is used to calculate the average slope angle of the underwater slope according to the virtual image, and judge whether the bank collapse occurs according to the average slope angle.

8. The device for calculating anisotropic soil and water bank collapse based on machine learning according to claim 7, characterized in that: The building blocks include: An acquisition unit is used to acquire historical specific heat capacity data of underwater slope soil and water materials and establish a specific heat capacity database; A division unit, used for dividing the specific heat capacity database into a training set and a test set; The analysis unit is used to input the training set into a supervised machine learning model for analysis and construct a soil-water distribution prediction model.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the water and soil anisotropic shore collapse calculation method based on machine learning as described in any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for calculating anisotropic soil and water collapse based on machine learning according to any one of claims 1 to 6.

Images