Slag disposal site selection determination method and device, program product and electronic equipment

Abstract

The invention relates to a waste slag site selection determination method and device, a product and equipment, and relates to the technical field of engineering waste disposal, and the method comprises the steps: determining an initial search range according to the slag amount of a waste slag production point and a transportation mode, and determining a search range of a waste slag site; determining an evaluation index of each search range based on the plurality of evaluation dimensions, performing score assignment to determine a first score of the evaluation index, the type of the evaluation index being the first evaluation index, determining a second score of the first evaluation index based on a machine learning model, and determining a score of the first evaluation index according to the first score and the second score; the type of the evaluation index is a second evaluation index, and determining the score of the second evaluation index according to the first score of the second evaluation index; and fusing the score of each evaluation index with the corresponding index weight coefficient to obtain the score of each search range, and determining the site selection range of the waste slag field from the search ranges according to the scores. According to the invention, the site selection accuracy of the waste slag field can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of engineering waste treatment technology, and more specifically, to a method for determining the location of a waste disposal site, a device for determining the location of a waste disposal site, a computer program product, and an electronic device. Background Technology

[0002] The site selection for waste disposal sites in hydropower projects is usually centered on the key project and extends outward to a certain range. Designers select suitable ditches and sloping areas based on their experience, and determine the site after verifying that the waste storage capacity of the site meets the requirements.

[0003] In the aforementioned methods, spoil disposal site selection relies on the experience of designers. Currently, there are no unified standards or methods for selecting spoil disposal sites related to hydropower projects, and various influencing factors lack a reasonable evaluation system, which affects the results and reduces accuracy and reliability. Furthermore, the main considerations for spoil disposal site selection are relatively singular, focusing solely on capacity and transportation distance, which easily leads to repeated iterations in the site selection process. Summary of the Invention

[0004] The purpose of this disclosure is to provide a method, device, computer program, and electronic equipment for determining the location of a spoil disposal site, thereby overcoming, to at least a certain extent, the problem of low accuracy in spoil disposal site selection due to limitations and defects in related technologies.

[0005] According to one aspect of this disclosure, a method for determining the location of a spoil disposal site is provided, comprising: The initial search range is determined based on the amount of slag generated at the waste slag generation point and the transportation method. From the initial search range, at least one search range is determined for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. Evaluation metrics for each search range are determined based on multiple evaluation dimensions. For each evaluation metric, a score is assigned based on the metric status to determine the first score of the evaluation metric. The type of the evaluation metric is the first evaluation metric. A second score of the first evaluation metric is determined based on a machine learning model. The score of the first evaluation metric is determined based on at least one of the first and second scores. The type of the evaluation metric is the second evaluation metric. The score of the second evaluation metric is determined based on the first score of the second evaluation metric. This process is used to determine the score of each evaluation metric. The score of each evaluation indicator is combined with the corresponding indicator weight coefficient to obtain the score of each search range, and the site selection range of the spoil disposal site is determined from the search range based on the score.

[0006] In one exemplary embodiment of this disclosure, an initial search range is determined based on the amount of waste generated at the waste generation point and the transportation method. From the initial search range, at least one search range is determined for a waste disposal site to accommodate the waste generated at the waste generation point. This includes: Calculate transportation costs based on slag volume and transportation method, and determine the initial search range; The legal search range is obtained by removing prohibited areas from the initial search range; The legal search area is filtered based on terrain data to determine the feasible search area; The feasible search range is verified to determine the search range of the spoil disposal site.

[0007] In one exemplary embodiment of this disclosure, verifying the feasible search range to determine the search range of the spoil disposal site includes: Obtain preset type data within the feasible search range, identify outliers in the preset type data based on a machine learning model, and determine the probability of the existence of outliers; The search range for the spoil disposal site is determined by verifying the probability of outliers.

[0008] In one exemplary embodiment of this disclosure, the method further includes: determining the evaluation index as the first evaluation index if the rule feature of the evaluation index is that it does not have hard rules or the data feature is that the data is incomplete.

[0009] In one exemplary embodiment of this disclosure, a first score for each evaluation indicator is determined by assigning a score based on the indicator's status, including: The evaluation index is the land use type, and the land use score is determined based on the regional types included in the land use type. The evaluation index is the site's catchment area. The area score of the site's catchment area is determined based on the first comparison result between the site's catchment area and multiple area thresholds. The evaluation index is the transportation distance. The transportation distance score is determined based on the second comparison result between the transportation distance and multiple transportation distance boundary conditions. The evaluation index is geological conditions. The susceptibility level is determined based on the degree of susceptibility to debris flows, and the debris flow susceptibility score is determined based on the susceptibility level. The evaluation index is the terrain slope. The terrain score is determined by comparing the terrain slope parameter value of the site with the third comparison result of multiple slope thresholds.

[0010] In one exemplary embodiment of this disclosure, determining a second score for a first evaluation metric based on a machine learning model includes: Feature extraction is performed on the first evaluation index to obtain input features that are strongly correlated with the first evaluation index; The input features are fed into a multilayer perceptron, and the basic features are determined through the first hidden layer. Higher-order features are obtained by fitting the basic features based on the second hidden layer; The higher-order features are compressed into core features through the third hidden layer, and the core features are mapped to obtain the second score.

[0011] In one exemplary embodiment of this disclosure, the score of each evaluation indicator is fused with the corresponding indicator weight coefficient to obtain a score for each search range, including: The score for each evaluation indicator is obtained by weighting and summing the scores of each indicator with their corresponding weight coefficients.

[0012] According to one aspect of this disclosure, a spoil disposal site selection device is provided, comprising: The search range determination module is used to determine the initial search range based on the amount of slag at the waste slag generation point and the transportation method, and to determine at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. The score determination module is used to determine the evaluation indicators for each search range based on multiple evaluation dimensions. For each evaluation indicator, a score is assigned based on its indicator status to determine the first score. The type of evaluation indicator is a first evaluation indicator. A second score for the first evaluation indicator is determined based on a machine learning model, and the score of the first evaluation indicator is determined based on at least one of the first and second scores. Alternatively, if the type of evaluation indicator is a second evaluation indicator, the score of the second evaluation indicator is determined based on its first score, thus determining the score for each evaluation indicator. The site selection range determination module is used to integrate the score of each evaluation indicator with the corresponding indicator weight coefficient to obtain the score of each search range, and determine the site selection range of the spoil disposal site from the search range based on the score.

[0013] According to one aspect of this disclosure, a computer program product is provided, which, when executed by a processor, implements the spoil disposal site selection method described in any of the preceding claims.

[0014] According to one aspect of this disclosure, an electronic device is provided, comprising: processor; Memory for storing the executable instructions of the processor; The processor is configured to implement the waste disposal site location determination method described above by executing the executable instructions.

[0015] The technical solution provided in this disclosure, on the one hand, can automatically determine the site selection range of a spoil disposal site by determining the score of the search range, thus improving operational efficiency and accuracy. On the other hand, the factors on which the site selection range of spoil disposal sites related to hydropower projects depends form a unified site selection standard and method, improving universality. The site selection range of spoil disposal sites considers multiple evaluation indicators, improving the comprehensiveness and reliability of spoil disposal site selection. The entire site selection range of spoil disposal sites can be automatically stored for easy management.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] Figure 1 The schematic diagram illustrates a process flow chart of a spoil disposal site selection method according to an embodiment of this disclosure.

[0019] Figure 2 The flowchart illustrating the determination of a second score for a first evaluation index based on a machine learning model is shown in an embodiment of this disclosure.

[0020] Figure 3 The schematic diagram illustrates the specific process for determining the site selection range of the spoil disposal site in an embodiment of this disclosure.

[0021] Figure 4 The schematic diagram illustrates a block diagram of the spoil disposal site selection device in an embodiment of this disclosure.

[0022] Figure 5 A schematic block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0023] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0024] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0025] Figure 1 The diagram illustrates the method for determining the location of a spoil disposal site. (See reference) Figure 1 As shown, the method mainly includes the following steps: Step S110: Determine the initial search range based on the amount of slag at the waste slag generation point and the transportation method, and determine at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. Step S120: Determine the evaluation index for each search range based on multiple evaluation dimensions; assign a score to each evaluation index according to its index status to determine the first score of the evaluation index; the type of the evaluation index is a first evaluation index; determine the second score of the first evaluation index based on a machine learning model; and determine the score of the first evaluation index based on at least one of the first and second scores; the type of the evaluation index is a second evaluation index; determine the score of the second evaluation index based on the first score of the second evaluation index, thereby determining the score of each evaluation index. Step S130: The score of each evaluation indicator is fused with the corresponding indicator weight coefficient to obtain the score of each search range, and the site selection range of the waste disposal site is determined from the search range based on the score.

[0026] Next, the method for determining the location of spoil disposal sites in this disclosure will be specifically described in conjunction with the embodiments.

[0027] Step S110: Determine the initial search range based on the amount of slag generated at the waste slag generation point and the transportation method, and determine at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste slag generation point.

[0028] In this embodiment, the waste disposal site is used to contain and process the waste generated at the waste generation point. The waste here can be waste from hydropower projects, or waste from mining, highways, railways, water conservancy hubs, pipelines, nuclear power, and other projects. Here, we will use waste from hydropower projects as an example for explanation.

[0029] The initial search area can be determined by calculating the transportation cost based on the amount of waste generated at the waste generation point and the transportation method. Transportation methods can include road, rail, and water transport, etc. For example, the center coordinates are determined with the waste generation point as the center and the adjusted maximum transport distance as the radius, and the initial search area is determined based on these center coordinates. The waste generation point can be a construction site or a mining area. If the terrain is flat, such as a plain, a circular area can be directly determined with the center as the origin; this circular area is the initial search area. If the terrain is complex, such as a mountainous area with mountains or rivers obstructing the path, inaccessible areas can be avoided, and the radius can be extended along the existing path to obtain the initial search area.

[0030] The legal search area is obtained by removing prohibited areas from the initial search area. Prohibited areas can be identified based on regulations and documents, such as nature reserves, security zones, and other areas where construction is prohibited.

[0031] The legal search area is filtered based on terrain data to determine the feasible search area. For example, based on terrain data, slope, and area, areas that satisfy both slope and area conditions are extracted as feasible search areas. The slope condition can be a slope less than a slope threshold, and the area condition can be an area greater than an area threshold.

[0032] Next, the feasible search area can be verified to obtain the search area for the spoil disposal site. For example, preset type data for the feasible search area is obtained, and anomaly identification is performed on the preset type data using a machine learning model to determine the probability of anomalies. Based on the probability of anomalies, the feasible search area is verified to determine the search area for the spoil disposal site. Here, anomalies can be unlabeled sensitive points, such as building clusters, hidden water bodies, and underground pipelines. The preset type data can be one or more of the following: high-resolution remote sensing imagery, historical data, terrain anomaly data, and personnel trajectory data.

[0033] For example, deep learning semantic segmentation models can be used to perform pixel-level classification of remote sensing images, identifying the probability of unmarked building clusters on planning maps. Random forests or gradient boosting trees can be used, inputting terrain anomaly data, to predict the probability of hidden water bodies. By combining graph neural networks with known pipeline routes and other data as constraints, predictions can be made for unmarked areas, outputting the probability of high-risk road sections or areas.

[0034] After determining the probability of anomalies, areas with probabilities greater than a threshold are designated as key areas for multi-source verification; areas with probabilities less than or equal to the threshold are designated as non-key areas, and anomaly identification is performed using drone images (e.g., taken by drones) to determine if anomalies exist. If no anomalies are found, the feasible search area is defined as the search area for the spoil disposal site.

[0035] In step S120, evaluation indicators for each search range are determined based on multiple evaluation dimensions. For each evaluation indicator, a score is assigned based on the indicator status to determine the first score of the evaluation indicator. The type of the evaluation indicator is a first evaluation indicator. A second score of the first evaluation indicator is determined based on a machine learning model. The score of the first evaluation indicator is determined based on at least one of the first and second scores. The type of the evaluation indicator is a second evaluation indicator. The score of the second evaluation indicator is determined based on the first score of the second evaluation indicator, thereby determining the score of each evaluation indicator.

[0036] In this embodiment of the disclosure, evaluation indicators for each search scope can be determined based on multiple evaluation dimensions, such as safety, compliance, environment, economy, and engineering. Each evaluation dimension can be characterized by different evaluation indicators; for example, the compliance dimension can be the land use type, and the environmental dimension can be the geological conditions.

[0037] Evaluation indicators may include land use type Site catchment area Transport distance Geological conditions Topographic slope To simplify, they are represented by D, S, L, N, and J respectively. Among them, the transport distance can be the distance close to the ground, and the geological conditions can be the degree of susceptibility to debris flows.

[0038] Next, we can determine the types of evaluation indicators and assign a score to each indicator based on its type. Specifically, evaluation indicators with no hard rules or incomplete data can be designated as the first evaluation indicator; those with hard rules and complete data can be designated as the second evaluation indicator. Hard rules refer to evaluation indicators with explicit constraints, such as land use type. Indicators without hard rules refer to those without explicit constraints, such as debris flow susceptibility or terrain slope; incomplete data could be transportation distance or site catchment area.

[0039] For the first evaluation indicator, in addition to assigning a score based on the indicator's status, a second score for the first evaluation indicator can also be determined based on a machine learning model. For the second evaluation indicator, its score can be obtained simply by assigning a score based on the indicator's status.

[0040] First, the process of assigning scores to each evaluation indicator to determine its initial score will be explained. Assigning scores to evaluation indicators refers to converting indicators that cannot be described numerically into scores based on their indicator status and according to scoring rules. The indicator status can be used to represent the range in which the evaluation indicator falls.

[0041] Specifically, the evaluation indicators are as follows: Land occupation type: land occupation level is determined based on the regional types included in the land occupation type, and a land occupation score is assigned to the land occupation type; Site catchment area: site catchment area level is determined based on a first comparison of the site catchment area with multiple area thresholds, and an area score is assigned to the site catchment area; Transport distance: transport distance level is determined based on a second comparison of the transport distance with multiple transport distance boundary conditions, and a transport distance score is assigned to the transport distance; Geological conditions: debris flow susceptibility level is determined based on the degree of debris flow susceptibility, and a debris flow susceptibility score is assigned based on the degree of susceptibility; Topographic slope: topographic slope level is determined based on a third comparison of the topographic slope parameter values ​​of the search range with multiple slope thresholds, and a topographic slope score is assigned to the topographic slope.

[0042] Specifically, regarding the land use type, in accordance with the provisions and requirements in the soil and water conservation code that "the site of the spoil disposal site should be selected in the hilly area, such as barren gullies, depressions, and tributary ditches, and in the plain area, such as depressions and barren land" and "the temporary land use of spoil disposal sites should avoid occupying cultivated (orchard) land, forest land, and grassland", the land use of spoil disposal sites should be based on the principle of occupying as little high-value land as possible, and cultivated land, orchard land, forest land, grassland, and other land use types should be used as the scoring boundary conditions.

[0043] Hydropower project spoil heaps are mostly located in hilly areas, and the best land type should be wasteland. The scoring process is as follows: If other types of land are occupied (D = D other), the corresponding land level is Level I, with a score of 1 point; if cultivated land, orchard land, or forest land are not occupied (D ≠ D cultivated, forest, or orchard), the corresponding land level is Level II, with a score of 0.8 points; if cultivated land and forest land are not occupied (D ≠ D cultivated, forest), the corresponding land level is Level III, with a score of 0.6 points; if cultivated land is not occupied (D ≠ D cultivated), the corresponding land level is Level IV, with a score of 0.4 points; if cultivated land, orchard land, or forest land are occupied (D = D cultivated, forest, orchard), the corresponding land level is Level V, with a score of 0.2 points.

[0044] Regarding the catchment area of ​​the site, according to the provisions of the soil and water conservation code that "spoil disposal sites should not be located in ditches with large catchment areas and large flow rates," and also referring to the suggestion in the soil and water conservation consultation and review that "if the upstream catchment area of ​​the spoil disposal site exceeds 1 km²", 2 In accordance with the requirement that "at the same time, the spoil disposal site must also undergo a special assessment to ensure that it does not cause any impact or harm," and based on the statistical analysis of the catchment area of ​​spoil disposal sites from multiple hydropower projects, and using historical data, multiple area thresholds of 0.5 km² corresponding to the catchment area S were established. 2 1.0 km 2 2.0 km 2 5.0 km 2 As a boundary condition for scoring, the scoring process is as follows, based on the classification: The area level of the site's catchment area is determined by comparing it with multiple area thresholds, thereby determining the area score for the site's catchment area. If... The corresponding area level is Level I, with an area score of 1 point; if The corresponding area level is Level II, with an area score of 0.8 points; if The corresponding area level is Grade III, with a score of 0.6 points; if The corresponding area level is IV, with an area score of 0.4 points; if The corresponding area level is V, and the area score is 0.2 points.

[0045] Regarding transport distance, based on the conclusions of "consumption and control distance of slag transported by 10t trucks on different roads: economic transport distance"... The newly constructed access road has a transportation distance of "Based on the results and statistics of haul distances from multiple hydropower project spoil disposal sites, multiple haul distance boundary conditions of 0.8km, 1.5km, 2.8km, and 5.0km corresponding to haul distance L were used as scoring boundary conditions. Considering that the haul distance needs to utilize the construction layout results, but spoil disposal site selection often precedes the overall construction layout, the haul distance was adjusted to the ground-level distance from the center of the key project to the center of the spoil disposal site, combined with manual correction. The scoring process is as follows, according to the classification: If..." The corresponding transport distance level is Level I, with a transport distance score of 1 point; if The transport distance level is Level II, and the transport distance score is 0.8 points; if The transport distance level is Level III, and the transport distance score is 0.6 points; if The corresponding transport distance level is IV, with a transport distance score of 0.4 points; if The corresponding distance level is V, and the distance score is 0.2 points.

[0046] Regarding geological conditions, in accordance with the provisions of the Soil and Water Conservation Code that "spoil disposal sites should not be set up in areas prone to debris flows, and if it is necessary to set them up, the stability and safety of the spoil disposal site should be ensured," the geological conditions of the spoil disposal site are assigned the boundary condition based on the degree of debris flow susceptibility. According to the classification, the scoring process is as follows: No debris flow in the site, corresponding to a risk level of I, debris flow risk score is 1 point; Debris flow risk level in the site is unlikely to occur (N=D), corresponding to a risk level of II, debris flow risk score is 0.8 points; Debris flow risk level in the site is slightly risky (N=C), corresponding to a risk level of III, debris flow risk score is 0.6 points; Debris flow risk level in the site is moderately risky (N=B), corresponding to a risk level of IV, debris flow risk score is 0.4 points; Debris flow risk level in the site is risky (N=A), corresponding to a risk level of V, debris flow risk score is 0.2 points.

[0047] Regarding topographic slope, based on the provisions and requirements in the soil and water conservation code that "spoil disposal sites should not be located in gullies with steep longitudinal slopes and difficult-to-intercept outlets" and "the slope of flat spoil disposal sites should not exceed 3°, and the slope of sloping spoil disposal sites should be between 3° and 25°", and combined with the slope statistics of spoil disposal sites in multiple hydropower projects, the topographic slope parameter value is used as the ground or gully slope J or inclination as the boundary condition for scoring. The topographic slope parameter values ​​correspond to 5°, 10°, 18°, and 25° (converted to inclination J). (Represented by) as the slope threshold. The scoring process, according to the classification, is as follows: The terrain slope level is determined based on a third comparison of the terrain slope parameter values ​​within the search range with multiple slope thresholds; the terrain score for the terrain gradient is then determined based on the determined terrain slope level. If... (Including depressions) (Including concave areas), the corresponding terrain slope level is I, and the terrain score is 1 point; if , The corresponding terrain slope level is II, and the terrain score is 0.8 points; if , The terrain slope level is Class III, and the terrain score is 0.6 points; if , The terrain slope level is IV, and the terrain score is 0.4 points; if , The terrain slope level is V, and the terrain score is 0.2 points.

[0048] When the evaluation indicator lacks mandatory rules or has incomplete data, it can be designated as the primary evaluation indicator. For this primary indicator, in addition to assigning a score, a secondary score can be determined based on a machine learning model. Mandatory rules refer to evaluation indicators with clearly defined constraints, such as land use type. Indicators lacking mandatory rules refer to those without clearly defined constraints, such as debris flow susceptibility or terrain slope. Primary evaluation indicators with incomplete data could include transport distance or site catchment area.

[0049] Figure 2 This diagram illustrates a flowchart of determining a second score for a first evaluation metric based on a machine learning model. (Refer to...) Figure 2 As shown, the main steps include: Step S210: Extract features from the first evaluation index to obtain input features that are strongly correlated with the first evaluation index; Step S220: Input the input features into the multilayer perceptron and determine the basic features through the first hidden layer; Step S230: Fit the basic features based on the second hidden layer to obtain higher-order features; Step S240: Compress the high-order features into core features through the third hidden layer, and map the core features to obtain the second score.

[0050] In this embodiment, the machine learning model can be a multilayer perceptron. The correlation degree of all features of the first evaluation index can be calculated, and features with a correlation greater than a correlation threshold are used as input features strongly correlated with the first evaluation index. Further, the basic correlations between input features are determined through the first hidden layer of the multilayer perceptron, such as the individual influence or simple combined influence of input features, generating basic features. Based on the second hidden layer, the basic features are integrated to construct higher-order interaction relationships, obtaining higher-order features. Higher-order interaction relationships can be obtained through feature multiplication or nonlinear coupling. For example, the superimposed influence of steep slopes and large runoff on debris flows can be extracted. Next, based on the third hidden layer, core influencing factors are extracted from the higher-order features as core features. Core features refer to the combined dimensions of the input features, such as (slope × rainfall) - (vegetation coverage × rock stability), etc. The core features are mapped to a second score related to the second evaluation index to improve the accuracy of the second score.

[0051] For interpretable core features, a reference score is determined using a linear function. This can be defined based on domain knowledge or statistical analysis, showing the linear function of the interpretable core feature on the second score. The reference score is obtained by linearly mapping the interpretable core feature to the linear function. For complex core features, the complex core features can be input into a convolutional neural network (CNN) for feature extraction, predicting their reference scores. The reference scores of the interpretable core features and the complex core features are then weighted and fused to obtain the second score. Interpretable core features refer to those whose relationship with the second evaluation metric can be clearly described through domain knowledge. Complex core features refer to those whose relationship with the second evaluation metric is complex and cannot be defined by simple rules.

[0052] Based on this, for the first evaluation indicator, the score of the first evaluation indicator can be determined based on at least one of the first score and the second score. For example, if the difference between the first score and the second score is less than a difference threshold, the average of the first score and the second score is taken as the difference of the first evaluation indicator. If the difference between the first score and the second score is greater than or equal to the difference threshold, the first score is corrected based on the second score to obtain the difference. Specifically, core features are extracted, and the correlation coefficient between the first score and the core features is calculated. Based on this, the correlation coefficient can be used as a weight parameter for the first score, and the difference between 1 and the correlation coefficient can be used as a weight parameter for the second score. The first score and the second score are then weighted and summed according to their respective weight parameters to obtain the score of the first evaluation indicator.

[0053] For the second evaluation indicator, which is different from the first evaluation indicator, its score can be determined directly based on the first score.

[0054] By dividing the evaluation indicators into a first evaluation indicator or a second evaluation indicator, the score of each evaluation indicator in the search range can be determined based on the score of the first evaluation indicator or the score of the second evaluation indicator, thereby improving the accuracy and comprehensiveness of the score determination.

[0055] In step S130, the score of each evaluation index is fused with the corresponding index weight coefficient to obtain the score of each search range, and the site selection range of the waste disposal site is determined from the search range based on the score.

[0056] In this embodiment, the score of each evaluation indicator is weighted and summed with its corresponding weight coefficient to obtain the score for each search range. The magnitude of the weight coefficient for each evaluation indicator is determined based on the importance of the evaluation indicator to the waste disposal site; the higher the importance, the larger the weight coefficient. For example, the score for each search range can be determined based on... This determines the score for each search range representing the waste disposal site location.

[0057] After determining the score for each search range representing the waste disposal site location, the search range with the highest score can be determined as the waste disposal site location range.

[0058] Figure 3 The diagram illustrates the overall process for determining the site selection area of ​​a spoil disposal site. (See reference) Figure 3 As shown, firstly, at least one search range for the spoil disposal site is determined, for example, search range 1 to search range N. Evaluation indicators are determined for each search range, and these indicators are divided into a first evaluation indicator and a second evaluation indicator. For the first evaluation indicator, a first score is determined based on assigned scores, and a second score is determined based on a machine learning model. The score of the first evaluation indicator is determined based on the first and second scores. For the second evaluation indicator, the score of the second evaluation indicator is determined based on the first score. The scores of all evaluation indicators are weighted and summed to obtain the score for each search range. The search range corresponding to the maximum score is taken as the site selection range for the spoil disposal site.

[0059] The technical solution in this disclosure can automatically determine the site selection range of a spoil disposal site by determining the score of the search range, thus improving operational efficiency and accuracy. The factors upon which the site selection range of spoil disposal sites related to hydropower projects depends form a unified site selection standard and method, improving versatility. The site selection range of spoil disposal sites considers multiple evaluation indicators, improving the comprehensiveness and reliability of spoil disposal site selection. The entire site selection range of the spoil disposal site can be automatically stored for easy management.

[0060] This disclosure also provides a device for determining the location of a spoil disposal site, with reference to... Figure 4 As shown, the spoil disposal site selection device 400 includes: The search range determination module 401 is used to determine an initial search range based on the amount of slag at the waste slag generation point and the transportation method, and to determine at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. The score determination module 402 is used to determine the evaluation index for each search range based on multiple evaluation dimensions, assign a score to each evaluation index according to its index status to determine the first score of the evaluation index, the type of the evaluation index is a first evaluation index, determine the second score of the first evaluation index based on a machine learning model, and determine the score of the first evaluation index based on at least one of the first score and the second score; the type of the evaluation index is a second evaluation index, and the score of the second evaluation index is determined based on the first score of the second evaluation index, thus determining the score of each evaluation index; The site selection range determination module 403 is used to integrate the score of each evaluation indicator with the corresponding indicator weight coefficient to obtain the score of each search range, and determine the site selection range of the spoil disposal site from the search range based on the score.

[0061] In one exemplary embodiment of this disclosure, an initial search range is determined based on the amount of waste generated at the waste generation point and the transportation method. From the initial search range, at least one search range is determined for a waste disposal site to accommodate the waste generated at the waste generation point. This includes: Calculate transportation costs based on slag volume and transportation method, and determine the initial search range; The legal search range is obtained by removing prohibited areas from the initial search range; The legal search area is filtered based on terrain data to determine the feasible search area; The feasible search range is verified to determine the search range of the spoil disposal site.

[0062] In one exemplary embodiment of this disclosure, verifying the feasible search range to determine the search range of the spoil disposal site includes: Obtain preset type data within the feasible search range, identify outliers in the preset type data based on a machine learning model, and determine the probability of the existence of outliers; The search range for the spoil disposal site is determined by verifying the probability of outliers.

[0063] In one exemplary embodiment of this disclosure, the apparatus is further configured to perform: determining the evaluation index as the first evaluation index if the rule feature of the evaluation index is that it does not have hard rules or the data feature is that the data is incomplete.

[0064] In one exemplary embodiment of this disclosure, a first score for each evaluation indicator is determined by assigning a score based on the indicator's status, including: The evaluation index is the land use type, and the land use score is determined based on the regional types included in the land use type. The evaluation index is the site's catchment area. The area score of the site's catchment area is determined based on the first comparison result between the site's catchment area and multiple area thresholds. The evaluation index is the transportation distance. The transportation distance score is determined based on the second comparison result between the transportation distance and multiple transportation distance boundary conditions. The evaluation index is geological conditions. The susceptibility level is determined based on the degree of susceptibility to debris flows, and the debris flow susceptibility score is determined based on the susceptibility level. The evaluation index is the terrain slope. The terrain score is determined by comparing the terrain slope parameter value of the site with the third comparison result of multiple slope thresholds.

[0065] In one exemplary embodiment of this disclosure, determining a second score for a first evaluation metric based on a machine learning model includes: Feature extraction is performed on the first evaluation index to obtain input features that are strongly correlated with the first evaluation index; The input features are fed into a multilayer perceptron, and the basic features are determined through the first hidden layer. Higher-order features are obtained by fitting the basic features based on the second hidden layer; The higher-order features are compressed into core features through the third hidden layer, and the core features are mapped to obtain the second score.

[0066] In one exemplary embodiment of this disclosure, the score of each evaluation indicator is fused with the corresponding indicator weight coefficient to obtain a score for each search range, including: The score for each evaluation indicator is obtained by weighting and summing the scores of each indicator with their corresponding weight coefficients.

[0067] It should be noted that the specific details of each module in the above-mentioned spoil disposal site location determination device have been described in detail in the corresponding spoil disposal site location determination method, and will not be repeated here.

[0068] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0069] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0070] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0071] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0072] The following reference Figure 5 To describe an electronic device 500 according to such an embodiment of the present disclosure. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0073] like Figure 5 As shown, the electronic device 500 is manifested in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one processing unit 510, at least one storage unit 520, a bus 530 connecting different system components (including storage unit 520 and processing unit 510), and a display unit 540.

[0074] The storage unit stores program code that can be executed by the processing unit 510, causing the processing unit 510 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 510 can perform actions such as... Figure 1 The steps are shown in the figure.

[0075] Storage unit 520 may include readable media in the form of volatile storage units, such as random access memory (RAM) 5201 and / or cache memory 5202, and may further include read-only memory (ROM) 5203.

[0076] Storage unit 520 may also include a program / utility 5204 having a set (at least one) program module 5205, such program module 5205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0077] Bus 530 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0078] Electronic device 500 can also communicate with one or more external devices 600 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 500, and / or with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through input / output (I / O) interface 550. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 560. Figure 5 As shown, network adapter 560 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0079] It should be noted that some embodiments of this disclosure also provide a computer program product, which includes a computer program that implements the above-described method when executed by a processor.

[0080] In one embodiment, the computer program product can be a tangible product containing a computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium can be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory, hard disk drive (HDD), solid-state drive (SSD), etc. For example, the computer program product can be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, NAND flash memory, etc. In one embodiment, the computer program product can be an intangible product containing a computer program. For example, the computer program product can be implemented as a virtual digital product, such as an executable file, installation package, or other digital file storing the computer program.

[0081] Computer program code can be written in one or more programming languages. Examples of programming languages ​​include C, Java, and C++. Program code can execute entirely on the user's computing device, partially on the user's computing device, or as a standalone software package. It can also execute partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via an internet connection provided by a mobile network operator).

[0082] Computer programs can be carried or transmitted via signals such as electrical, magnetic, optical, electromagnetic, and infrared rays. Electronic devices can convert signals carrying computer programs into digital signals, thereby running the computer programs. When a computer program runs on an electronic device, its code is used to cause the electronic device to execute (more specifically, to be executed by the processor of the electronic device) the method steps of various exemplary embodiments of this disclosure.

[0083] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0084] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0085] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0086] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0087] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining the location of a spoil disposal site, characterized in that, include: The initial search range is determined based on the amount of slag generated at the waste slag generation point and the transportation method. From the initial search range, at least one search range is determined for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. Evaluation metrics for each search range are determined based on multiple evaluation dimensions. A first score is assigned to each evaluation metric based on its status. The evaluation metric is classified as a first evaluation metric. A second score for the first evaluation metric is determined based on a machine learning model. The score of the first evaluation metric is determined based on at least one of the first and second scores. Alternatively, if the evaluation metric is classified as a second evaluation metric, its score is determined based on its first score, thus determining the score for each evaluation metric. The score of each evaluation indicator is combined with the corresponding indicator weight coefficient to obtain the score of each search range, and the site selection range of the spoil disposal site is determined from the search range based on the score.

2. The method for determining the location of a spoil disposal site according to claim 1, characterized in that, The step of determining an initial search range based on the amount of slag at the waste generation point and the transportation method, and then determining at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste generation point, includes: Based on the amount of slag and the transportation method, calculate the transportation cost and determine the initial search range; The legal search range is obtained by removing prohibited areas from the initial search range. The legal search range is filtered based on terrain data to determine the feasible search range; The feasible search range is verified to determine the search range of the spoil disposal site.

3. The method for determining the location of a spoil disposal site according to claim 2, characterized in that, The verification of the feasible search range to determine the search range of the spoil disposal site includes: Obtain preset type data within the feasible search range, identify outliers in the preset type data based on a machine learning model, and determine the probability of the existence of outliers; The feasible search range is verified based on the probability of anomalies to determine the search range of the spoil disposal site.

4. The method for determining the location of a spoil disposal site according to claim 1, characterized in that, The method further includes: The evaluation indicator is characterized by the absence of hard rules or the incompleteness of data; therefore, the evaluation indicator is determined as the first evaluation indicator.

5. The method for determining the location of a spoil disposal site according to claim 1, characterized in that, The step of assigning a score to each evaluation indicator based on its status to determine the first score of the evaluation indicator includes: The evaluation index is the land occupation type. The land occupation level is determined based on the regional types included in the land occupation type, and the land occupation score for the land occupation type is determined. The evaluation index is the site catchment area. Based on the first comparison result of the site catchment area and multiple area thresholds, the area score of the site catchment area is determined. The evaluation index is the transportation distance. The transportation distance score is determined based on the second comparison result between the transportation distance and multiple transportation distance boundary conditions. The evaluation index is geological conditions. The susceptibility level is determined based on the susceptibility of debris flows, and the debris flow susceptibility score is determined based on the susceptibility level. The evaluation index is the terrain slope. The terrain score of the terrain slope is determined based on the third comparison result of the terrain slope parameter value of the site and multiple slope thresholds.

6. The method for determining the location of a spoil disposal site according to claim 1, characterized in that, The step of determining the second score of the first evaluation index based on a machine learning model includes: Feature extraction is performed on the first evaluation index to obtain input features that are strongly correlated with the first evaluation index; The input features are fed into a multilayer perceptron, and the basic features are determined through the first hidden layer. The higher-order features are obtained by fitting the basic features based on the second hidden layer; The higher-order features are compressed into core features through the third hidden layer, and the core features are mapped to obtain the second score.

7. The method for determining the location of a spoil disposal site according to claim 1, characterized in that, The process of fusing the score of each evaluation indicator with its corresponding weight coefficient to obtain a score for each search range includes: The score for each evaluation indicator is obtained by weighting and summing the scores of each indicator with their corresponding weight coefficients.

8. A device for determining the location of a spoil disposal site, characterized in that, include: The search range determination module is used to determine an initial search range based on the amount of slag at the waste slag generation point and the transportation method, and to determine at least one search range from the initial search range for a waste disposal site to accommodate the waste slag generated at the waste slag generation point. The score determination module is used to determine the evaluation indicators for each search range based on multiple evaluation dimensions. For each evaluation indicator, a score is assigned based on its indicator status to determine the first score. The type of evaluation indicator is a first evaluation indicator. A second score for the first evaluation indicator is determined based on a machine learning model, and the score of the first evaluation indicator is determined based on at least one of the first and second scores. Alternatively, if the type of evaluation indicator is a second evaluation indicator, the score of the second evaluation indicator is determined based on its first score, thus determining the score for each evaluation indicator. The site selection range determination module is used to integrate the score of each evaluation indicator with the corresponding indicator weight coefficient to obtain the score of each search range, and determine the site selection range of the spoil disposal site from the search range based on the score.

9. A computer program product, characterized in that, When the computer program is executed by the processor, it implements the spoil disposal site selection method according to any one of claims 1-7.

10. An electronic device, characterized in that, include: processor; Memory for storing the executable instructions of the processor; The processor is configured to implement the spoil disposal site location determination method according to any one of claims 1-7 by executing the executable instructions.

Images