Intelligent path planning and construction navigation method for sediment elution

Abstract

The application discloses a kind of intelligent path planning and construction navigation method for bottom mud elution, belong to water treatment technical field.The technical problem to be solved is that the path planning before bottom mud elution is unreasonable, resulting in poor bottom mud elution effect.The technical solution points are that the method comprises the following steps: collecting data, establishing a three-dimensional model of the construction area;According to the knowledge graph and the three-dimensional model, an elution scene graph of graph structure is established;The path of the generated elution operation body in the elution scene graph is optimized by a first path optimization algorithm, and the elution operation body traverses the elution scene graph;The path of the elution operation body in the scene is optimized by a second path optimization algorithm, and the optimal bottom mud elution path is obtained.

Description

Technical Field

[0001] This invention relates to the field of water treatment technology, and in particular to an intelligent path planning and construction navigation method for sediment washing. Background Technology

[0002] The sediment elution technology used in habitat restoration primarily removes suspended solids from water bodies through a "washing" process, thereby improving water transparency. This technology can promote the germination and growth of submerged plants, ultimately achieving ecological integrity restoration driven by solar energy.

[0003] For complex and variable soft silty terrain, various conditions often exist within the same construction area, such as loose sediment, compacted sediment, and severe anaerobic sediment. Furthermore, even sediment of the same type may require different disturbance intensities due to factors such as water depth and sediment thickness. As disclosed in Chinese Patent CN120794274A, strong disturbance can cause the aggregates to disintegrate, leading to a large release of pollutants and resulting in the opposite effect. Therefore, fixing the path planning and disturbance parameters before sediment washing cannot achieve good washing results in complex and variable soft silty terrain. Summary of the Invention

[0004] The purpose of this invention is to provide: A smart path planning and construction navigation method for sediment washing is proposed to solve the technical problem of poor sediment washing effect caused by unreasonable path planning before sediment washing.

[0005] Terminology Explanation: Unless otherwise defined, all technical terms used herein have the same meanings as commonly understood by one of ordinary skill in the art. Unless otherwise stated, all patents, patent inventions, and publications cited in this document are incorporated herein by reference in their entirety. If multiple definitions exist for terms, the definition provided in this chapter shall prevail.

[0006] It should be understood that the above brief description and the following detailed description are exemplary and for illustrative purposes only, and do not limit the subject matter of the invention in any way. In this invention, the singular is used in conjunction with the plural unless otherwise specifically stated. It should also be noted that, unless otherwise stated, the use of “or” or “or” means “and / or”. Furthermore, the use of the term “comprising” and other forms such as “including,” “containing,” and “contains” are not limiting.

[0007] In a first aspect, the present invention provides: an intelligent path planning and construction navigation method for sediment washing, comprising the following steps: Collect data and create a 3D model of the construction area; Based on the knowledge graph and 3D model, a graph-structured elution scenario diagram is constructed. The path of the elution operation body generated by the first path optimization algorithm is optimized in the elution scene graph, and the elution operation body traverses the elution scene graph. The optimal sediment elution path is obtained by optimizing the path of the elution operation in the scene using the second path optimization algorithm.

[0008] Furthermore, the specific steps for establishing a graph-structured washout scenario diagram are as follows: using changes in knowledge in the knowledge graph as connections and generated washout scenarios as nodes, a graph-structured washout scenario diagram is generated. By controlling variables, only one piece of knowledge in the washout scenario is changed each time. When generating a elution scenario, compare the risk coverage rate of the current elution scenario diagram with the preset risk coverage threshold: if the risk coverage rate is greater than or equal to the risk coverage threshold, it means that the generated elution scenario diagram has covered all possible risks, and the generation stops; otherwise, continue generating elution scenarios.

[0009] Furthermore, the risk coverage rate is the ratio of the possible situations, or combinations of situations, that may occur during the sediment elution process in the elution scenario diagram that lead to a decrease or no improvement in the sediment elution effect, to all possible combinations of the same situation in the knowledge graph.

[0010] Furthermore, when the first path optimization algorithm optimizes the path of the elution operation body in the elution scenario graph, it generates a path with the most risky situations faced by the elution operation body. After the elution operation body completes one walk, the walk path is removed from the elution scenario graph, and a new walk path is planned from the remaining nodes until all nodes are traversed.

[0011] Furthermore, the first path optimization algorithm generates the path of the elution operation body in the elution scenario graph through the following steps: The scene route map is represented as a directed graph. ,in This represents the set of nodes in the rinsing scene graph, where each node... All calculations were performed on the elution evaluation indicators of the elution operation body; It is a set of edges, representing the relationships between the washout scenarios; The scene roadmap is defined as a Hidden Markov Model, where the set of states... The set of nodes corresponding to the elution scene graph Initial state probability The set of state transition probability matrices represents the probability of starting from a certain scenario. The set of observation probability matrices represents the set of probabilities of transitioning from one scene to another. This represents a set of elution evaluation metrics in a specific scenario. Use the Viterbi algorithm to find the most likely path; Using penalty function Add nodes to the elution process path.

[0012] Furthermore, the Viterbi algorithm is used to find the most probable path as follows: set up Indicates in The state at time is The probability of finding the optimal path is given by the formula:

[0013] In the formula, N represents the total number of states, which is also the total number of nodes. , ; From state Transition to state The probability, that is, in the elution scenario diagram, is that the elution operation body starts from the first... The node travels to the first The probability of each node. ; It is in state At that time, elution evaluation indicators were observed. The probability, ; Using penalty function The specific steps to add nodes to the elution process path are as follows: Let the path length be The total number of nodes is The penalty function is then expressed as: .

[0014] In the Viterbi algorithm, a penalty function is added when updating the path probability, resulting in the following formula: .

[0015] Furthermore, the second path optimization algorithm is the genetic particle swarm optimization algorithm, which optimizes the path of the elution operation in the scene by the following steps: One elution operation is a particle; the initial population is generated and initialized. Selected particles undergo crossover and mutation to generate a new population; Update the particle's position and velocity; Through the formula: Calculate the current position of the particle, where, Indicates the first Individual particles Location at any given moment Indicates the first The particle in the first The speed of time Indicates the first The particle in the first The position at that moment; Further, through the formula: To calculate the current velocity of the particle, in the above formula, Indicates inertia weight, and The acceleration constant, and It is a random constant. Indicates the first The optimal position of each individual particle. This indicates the globally optimal position.

[0016] By continuously updating the position and velocity of the particles, the movement path and speed of the particles are optimized.

[0017] Furthermore, the multiple optimal sediment washing paths obtained are aggregated according to the actual needs of on-site construction.

[0018] Furthermore, the aggregation of multiple sediment washing paths is specifically as follows: according to the different work areas of the construction area, weights are set according to the adaptability evaluation index or the washing evaluation index; the optimal path is segmented, and according to the weights, the evaluation score of each segment of the optimal path in the work area is recalculated. The segment with the highest evaluation score is selected, and the first and second parts of the segments are spliced ​​together to form a complete washing path, thus obtaining the optimal washing path.

[0019] Furthermore, the second path optimization algorithm can be an ant colony algorithm, a hybrid genetic algorithm, or a genetic particle swarm algorithm.

[0020] The beneficial effects of this invention are as follows: 1. By generating a elution scenario map, the subjective factors of manual path design are overcome, all possible situations are fully considered, and the comprehensiveness of path planning is improved. Through the first path planning algorithm and the second path planning algorithm, the optimal path is planned under the full consideration of all possibilities, thereby improving the elution effect of bottom sediment.

[0021] 2. By aggregating multiple optimal paths, the optimal path suitable for the actual construction needs and circumstances can be formulated. Attached Figure Description

[0022] Figure 1 This is a flowchart of an intelligent path planning and construction navigation method for sediment washing. Detailed Implementation

[0023] The following non-limiting embodiments are intended to enable those skilled in the art to gain a more comprehensive understanding of the present invention, but do not limit the invention in any way. The following content is merely an exemplary description of the scope of protection claimed by the present invention, and those skilled in the art can make various changes and modifications to the present invention based on the disclosed content, and such changes should also fall within the scope of protection claimed by the present invention.

[0024] The present invention will be further described below by way of specific embodiments. Unless otherwise specified, all instruments, devices, equipment, reagents, products, etc., used in the embodiments of the present invention are obtained through conventional commercial means.

[0025] Reference Figure 1 The intelligent path planning and construction navigation method for sediment washing includes the following steps: S1: Collect data and build a three-dimensional model of the construction area.

[0026] Collect and analyze the bottom sediment of the construction area, and establish a three-dimensional model of the construction area based on the distribution of the bottom sediment.

[0027] S2, based on the knowledge graph and 3D model, establish a graph-structured elution scenario graph.

[0028] Using a pre-built knowledge graph and a 3D model, changes in knowledge within the knowledge graph are connected as lines, and generated washout scenarios are used as nodes to create a graph-structured washout scenario graph. As many washout scenarios as possible are generated based on the knowledge in the knowledge graph. When generating washout scenarios, a controlled variable approach is used, meaning only one piece of knowledge in the washout scenario is changed each time, and the generated washout scenarios cover as many combinations of knowledge in the knowledge graph as possible.

[0029] A risk coverage threshold is pre-set. When generating elution scenarios, the risk coverage rate of the current elution scenario diagram is compared with the risk coverage threshold. If the risk coverage rate is greater than or equal to the risk coverage threshold, it indicates that the generated elution scenario diagram has covered all possible risks, and generation can stop. Otherwise, elution scenarios need to be generated continuously. The risk coverage rate is the ratio of the possible situations, or combinations of situations, that may occur during sediment elution in the elution scenario diagram that lead to a decrease or no improvement in sediment elution effect, to all possible combinations of the same situation in sediment elution in the knowledge graph.

[0030] By using elution scenario diagrams to simulate all possible problems in the actual sediment elution process, it is possible to fully consider possible situations when planning the elution path in the future.

[0031] To make it easier to understand, the following is a simple example: Knowledge 1: For river sections with a width of 13m or more, the construction method with the construction route perpendicular to the shoreline is adopted. This method is suitable for wide rivers with large undulations in the riverbed. Its advantages are that the washing is thorough and not easy to miss, and it is highly adaptable to the bottom of the water body. For river sections with a width of less than 13m, a washing method with the construction route parallel to the shoreline is adopted. This method is suitable for narrower rivers with flat riverbeds. Its advantages include convenient navigation, high construction efficiency, and targeted washing.

[0032] Knowledge 2: When the bottom sediment particle size (D50) is <60μm, the moisture content is ≥40%, and the oxidation-reduction potential (ORP) is <-100mv, it is considered to be soft bottom sediment and aeration disturbance should be adopted. Mechanical disturbance is adopted when the bottom sediment particle size (D50) is ≥60μm, the moisture content is <40%, and the shear strength is ≥10kPa; Jet disturbance is selected based on the actual site conditions due to its strong adaptability.

[0033] Table 1 lists some of the scenarios generated based on the above knowledge.

[0034] Table 1

[0035] Compared to the traditional path planning approach, which involves adjusting the operating parameters of the sediment washing device after significant changes occur during construction, and is essentially a "trial and error" approach, this method utilizes a washing scenario diagram to exhaustively enumerate all possible combinations of risks such as changes in sediment properties, sudden hydrological changes, and disturbance failures. This effectively overcomes the significant involvement of subjective human factors in path planning, transforms passive response into proactive rehearsal, and enhances robustness to unexpected situations.

[0036] S3. Optimize the path of the elution operation body in the elution scene graph using the first path optimization algorithm, so that the elution operation body can traverse the elution scene graph.

[0037] The elution process involves traversing a elution operation module within a elution scenario graph. Each elution operation module represents a mapping of the elution device within this graph. A first path optimization algorithm optimizes the module's path to maximize its traversal of nodes, generating a path that minimizes the number of risky scenarios. The module then performs sediment elution within the scenario, and the elution results are evaluated. A second path optimization algorithm further refines the module's path within the scenario, achieving the optimal elution efficiency.

[0038] Specifically, the first path optimization algorithm plans the movement path of the elution workpiece using the following steps: 1. Construct a scenario roadmap.

[0039] The scene route map is represented as a directed graph. ,in This represents the set of nodes in the elution scenario graph, representing the evaluation scenario, with each node... All calculations were performed on the elution evaluation indicators of the elution operation body; It is an edge set, representing the relationships between elution scenarios. The elution evaluation index is used to determine the elution effect in sediment elution operations.

[0040] 2. Define the Hidden Markov Model.

[0041] Viewing the scene roadmap as a Hidden Markov Model (HMM), where the set of states... The set of nodes corresponding to the elution scene graph Initial state probability The set of state transition probability matrices represents the probability of starting from a certain scenario. This represents the set of probabilities of transitioning from one scene to another. It is also the set of observation probability matrices. This refers to a set of elution evaluation metrics for a specific scenario. Elution evaluation metrics include turbidity, dissolved oxygen, and organic matter concentration.

[0042] 3. Use the Viterbi algorithm to find the most likely path.

[0043] set up Indicates in The state at time is The probability of finding the optimal path is given by the formula:

[0044] In the formula, N represents the total number of states, which is also the total number of nodes. , ; From state Transition to state The probability, that is, in the elution scenario diagram, is that the elution operation body starts from the first... The node travels to the first The probability of each node. ; It is in state At that time, elution evaluation indicators were observed. The probability, .

[0045] 4. Use a penalty function to make the washing operation traverse as many nodes as possible.

[0046] penalty function Penalize paths containing fewer nodes, assuming the path length is . The total number of nodes is The penalty function is then expressed as: .

[0047] In the Viterbi algorithm, a penalty function is added when updating the path probability, resulting in the following formula: .

[0048] Understandably, each time the first path planning algorithm completes a path planning iteration, it "prunes" the corresponding path in the washing scenario graph, that is, it removes the generated wandering path from the washing scenario graph. The next path planning is then performed from the remaining evaluation scenario graph, and this process is repeated until all nodes in the washing scenario graph have been traversed.

[0049] S4. The second path optimization algorithm is used to optimize the path of the elution body in the scene, thereby improving the elution effect of the bottom mud.

[0050] For ease of understanding, the genetic particle swarm optimization algorithm is used as an example of the second path optimization algorithm. In some other embodiments, it can be the ant colony algorithm, the hybrid genetic algorithm, etc.

[0051] 1. Treat a elution operation as a particle, and generate and initialize the initial population randomly or based on experience.

[0052] 2. Select particles with high fitness for crossover and mutation to generate a new population. Particle selection methods can include roulette wheel selection, tournament selection, etc., while crossover methods can include single-point crossover, multi-point crossover, etc. This embodiment will further illustrate this using tournament selection as an example: Each time a random draw Particles ( Alternatively, 3) select the most fit individuals to enter the next generation, repeating this process until the population size is full. This method is simple and maintains selection pressure.

[0053] The fitness is the effect of the elution operation on the sediment in the scenario. The fitness evaluation indicators include sediment elution time, elution depth, and elution index achievement rate.

[0054] When the elution operation is traversed in the elution scenario graph, the effectiveness of the elution operation is comprehensively evaluated based on the predicted and actual values ​​of the elution evaluation indicators. This facilitates the second path optimization algorithm in optimizing the path of the elution operation. Specifically: During the elution process, after observing a elution evaluation index, a predicted value for that index is obtained for the current scenario. This predicted value is compared to a pre-set index value. If the predicted value does not meet the index requirement, the elution effect is unsatisfactory; if it does, the elution effect is satisfactory. The more ideal the predicted value, the higher the evaluation. After evaluating each elution evaluation index, the indices are dimensionless and aggregated for a comprehensive assessment of the sediment elution effect.

[0055] 3. Update the position and velocity of the particles.

[0056] 4. Using the formula: Calculate the current position of the particle, where, Indicates the first Individual particles Location at any given moment Indicates the first The particle in the first The speed of time, Indicates the first The particle in the first The position at any given moment.

[0057] Further, through the formula: To calculate the current velocity of the particle, in the above formula, Indicates inertia weight, and The acceleration constant, and It is a random constant. Indicates the first The optimal position of each individual particle. This indicates the globally optimal position.

[0058] By continuously updating the position and velocity of particles, and optimizing their movement paths and speeds, the sediment elution effect and efficiency are improved, resulting in the theoretically optimal sediment elution path. The sediment elution path obtained in this way is the optimal path.

[0059] S5, Optimal Path Aggregation.

[0060] Since step S3 involves a complete traversal path, step S4 generates the optimal path for the entire construction area. As more traversal paths are generated in S3, S4 will generate multiple optimal paths adapted to different conditions within the construction area. These multiple optimal paths may have significant differences, thus allowing the optimal paths to be aggregated according to the actual needs of on-site construction. Specifically: Based on the different work zones within the construction area, weights are set according to either fitness evaluation indicators or elution evaluation indicators, giving them different weights in different work zones. The optimal path is segmented according to different work zones. Based on the weights, the evaluation score of each segment of the optimal path within the work zone is recalculated. The segment with the highest evaluation score is selected, and the first and second parts of the segments are concatenated to form a complete elution path, thus obtaining the optimal elution path.

[0061] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, and is not intended to limit the scope of protection of the present invention. Simple modifications or equivalent substitutions made by those skilled in the art to the technical solution of the present invention do not depart from the essence and scope of the technical solution of the present invention.

Claims

1. A smart path planning and construction navigation method for sediment washing, characterized in that: Includes the following steps: Collect data and create a 3D model of the construction area; Based on the knowledge graph and 3D model, a graph-structured elution scenario diagram is constructed. The path of the elution operation body generated by the first path optimization algorithm is optimized in the elution scene graph, and the elution operation body traverses the elution scene graph. The optimal sediment elution path is obtained by optimizing the path of the elution operation in the scene using the second path optimization algorithm.

2. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: The specific steps for creating a graph-structured washout scenario diagram are as follows: using changes in knowledge in the knowledge graph as connections and generated washout scenarios as nodes, a graph-structured washout scenario diagram is generated. By controlling variables, only one piece of knowledge in the washout scenario is changed each time. When generating a elution scenario, compare the risk coverage rate of the current elution scenario diagram with the preset risk coverage threshold: if the risk coverage rate is greater than or equal to the risk coverage threshold, it means that the generated elution scenario diagram has covered all possible risks, and the generation stops; otherwise, continue generating elution scenarios.

3. The intelligent path planning and construction navigation method for sediment washing according to claim 2, characterized in that: Risk coverage is the ratio of the possible situations, or combinations of situations, that may occur during sediment elution in the elution scenario diagram that lead to a decrease or no improvement in sediment elution effect, to all possible combinations of the same situation in the knowledge graph.

4. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: When optimizing the path of the elution operation in the elution scenario graph, the first path optimization algorithm generates the path with the most risky situations faced by the elution operation. After the elution operation completes one walk, the walk path is removed from the elution scenario graph, and a new walk path is planned from the remaining nodes until all nodes have been traversed.

5. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: The first path optimization algorithm generates the path of the elution operation body in the elution scenario graph through the following steps: The scene route map is represented as a directed graph. ,in This represents the set of nodes in the rinsing scene graph, where each node... All calculations were performed on the elution evaluation indicators of the elution operation body; It is a set of edges, representing the relationships between the washout scenarios; The scene roadmap is defined as a Hidden Markov Model, where the set of states... The set of nodes corresponding to the elution scene graph Initial state probability The set of state transition probability matrices represents the probability of starting from a certain scenario. The set of observation probability matrices represents the set of probabilities of transitioning from one scene to another. This represents a set of elution evaluation metrics in a specific scenario. Use the Viterbi algorithm to find the most likely path; Using penalty function Add nodes to the elution process path.

6. The intelligent path planning and construction navigation method for sediment washing according to claim 5, characterized in that: The Viterbi algorithm is used to find the most probable path as follows: set up Indicates in The state at time is The probability of finding the optimal path is given by the formula: In the formula, N represents the total number of states, which is also the total number of nodes. , ; From state Transition to state The probability, that is, in the elution scenario diagram, is that the elution operation body starts from the first... The node travels to the first The probability of each node. ; It is in state At that time, elution evaluation indicators were observed. The probability, ; Using penalty function The specific steps to add nodes to the elution process path are as follows: Let the path length be The total number of nodes is The penalty function is then expressed as: ; In the Viterbi algorithm, a penalty function is added when updating the path probability, resulting in the following formula: 。 7. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: The second path optimization algorithm is the genetic particle swarm optimization algorithm, which optimizes the path of the elution workpiece in the scene by the following steps: One elution operation is a particle; the initial population is generated and initialized. Selected particles undergo crossover and mutation to generate a new population; Update the particle's position and velocity; Through the formula: Calculate the current position of the particle, where, Indicates the first Individual particles Location at any given moment Indicates the first The particle in the first The speed of time, Indicates the first The particle in the first The position at that moment; Further, through the formula: To calculate the current velocity of the particle, in the above formula, Indicates inertia weight, and The acceleration constant, and It is a random constant. Indicates the first The optimal position of each individual particle. Indicates the globally optimal position; By continuously updating the position and velocity of the particles, the movement path and speed of the particles are optimized.

8. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: The multiple optimal sediment washing paths obtained will be aggregated according to the actual needs of on-site construction.

9. The intelligent path planning and construction navigation method for sediment washing according to claim 7, characterized in that: The specific method for aggregating multiple sediment washing paths is as follows: according to the different work areas of the construction area, weights are set according to the adaptability evaluation index or the washing evaluation index; the optimal path is segmented, and according to the weights, the evaluation score of each segment of the optimal path within the work area is recalculated. The segment with the highest evaluation score is selected, and the first and second parts of the segments are spliced ​​together to form a complete washing path, thus obtaining the optimal washing path.

10. The intelligent path planning and construction navigation method for sediment washing according to claim 1, characterized in that: The second path optimization algorithm can be ant colony algorithm, hybrid genetic algorithm, or genetic particle swarm algorithm.

Images