Detection method and device for underground drainage pipes

Abstract

The present invention provides a detection method and device for underground drainage pipes, belonging to the technical field of underground pipeline detection, the method comprising: identifying and randomly extracting a first number of first pipeline nodes and a second number of second pipeline nodes, updating particle positions and velocities based on a particle swarm algorithm, until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than a target threshold, obtaining the target pipeline node corresponding to each particle, and deploying sensors on the target pipeline nodes to detect drainage pipes. The detection method for underground drainage pipes of the present invention optimizes the sensor deployment scheme through a particle swarm algorithm, can fully consider the specific conditions of different management areas and different pipeline conditions under a limited number of sensors, maximize the monitoring effect of the underground pipeline network, and improve the reliability of underground drainage pipe detection.

Description

Technical Field

[0001] The present invention relates to the technical field of underground pipeline detection, and in particular to a detection method and device for underground drainage pipelines. Background Art

[0002] Urban underground sewer networks play a vital role in wastewater transportation, directly affecting public health and environmental protection. However, due to aging and lack of timely maintenance, many pipes have experienced severe structural degradation, such as corrosion and damage, leading to infiltration and inflow problems. Infiltration and inflow refer to water from the surrounding environment entering the sewer system through manholes, imperfect pipe joints and cracks. Infiltration and inflow reduce the effective capacity of the sewer system and reduce the efficiency of wastewater transportation. Excessive infiltration and inflow may lead to combined sewer overflows (CSOs), which discharge untreated wastewater into the environment. Infiltration and inflow increase the risk of basement and surface flooding during heavy rains. The additional water volume increases the load on wastewater treatment plants, resulting in higher pumping and treatment costs. In addition, overflows and floods caused by infiltration and inflow may cause environmental pollution and pose risks to public health.

[0003] In recent years, the rapid development of Internet of Things (IoT) technology has led to the widespread use of online sensors for monitoring leakage and intrusion in underground water supply networks. These sensors are usually used to monitor hydraulic variables such as water level or flow with high temporal resolution. The collected data can be processed by advanced analytical techniques, such as machine learning algorithms, to identify the occurrence and existence of leakage and intrusion in underground drainage pipe networks. Compared with traditional physical methods, the advantage of using sensors is that its leakage and intrusion analysis relies on the collected data and is therefore more efficient. However, due to the high cost of purchasing and maintaining sensors, it is impractical to place sensors at every node in the underground drainage pipe network. Therefore, how to maximize the reliability of pipeline detection with a limited number of sensors is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a detection method and device for underground drainage pipes, which are used to solve the defect in the prior art that it is difficult to achieve reliable coverage when a limited number of sensors are deployed in a huge underground pipe network, and achieve the effect of maximizing the reliability of pipe detection.

[0005] The present invention provides a method for detecting an underground drainage pipe, comprising:

[0006] Identify a first pipeline node and a second pipeline node of the underground drainage network, wherein the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node;

[0007] Randomly select a first number of first pipeline nodes and a second number of second pipeline nodes, use each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initialize the speed of each particle;

[0008] Based on the objective function configured by the particle swarm algorithm, the fitness value of each particle on the current node is calculated and the speed and position of each particle are iteratively updated;

[0009] In the case where each management area includes at least one first pipeline node and at least one second pipeline node, the total fitness value of the particle is calculated until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and the target pipeline node corresponding to each particle is obtained;

[0010] A sensor is deployed on the target pipeline node to detect the drainage pipeline.

[0011] According to a method for detecting underground drainage pipes provided by the present invention, the objective function is expressed as:

[0012] ;

[0013] f is the objective function value, S is the infiltration inflow sensitivity, which is determined based on at least one of the historical infiltration inflow data, pipeline material, service life and geographical location; I is the number of affected pipelines; α and β are weight coefficients used to balance the importance of infiltration inflow sensitivity and the number of affected pipelines in the objective function.

[0014] According to a method for detecting underground drainage pipes provided by the present invention, the step of calculating the total fitness value of particles includes:

[0015] Determine a first weight value corresponding to each management area and a second weight value corresponding to each particle;

[0016] The total fitness value of the particle is calculated based on the first weight value corresponding to the management area of ​​each particle, the second weight value corresponding to each particle, and the fitness value of each particle.

[0017] According to a method for detecting underground drainage pipes provided by the present invention, the size of the first weight value is inversely proportional to the size of the number of particles in the corresponding management area, and the size of the second weight value is directly proportional to the average size of the fitness values ​​of the particles in the corresponding management area.

[0018] According to a method for detecting underground drainage pipes provided by the present invention, the total fitness value of the particles is determined by the following formula:

[0019] ;

[0020] F is the total fitness value, n is the number of management areas, is the total weight of the ith region, is the fitness value of the particle in the i-th region; , is the first weight value, is the second weight value, Ni is the number of particles in each management area, Ai is the average value of the fitness value of the particles in each management area, The size of is inversely proportional to the size of Ni. The size of is proportional to Ai.

[0021] According to a method for detecting underground drainage pipes provided by the present invention, the speed update formula is: ; The position update formula is: ;

[0022] Among them, v i (t) is the velocity of particle i at time t, x i (t) is the position of particle i at time t, is the individual optimal position of particle i, is the global optimal position, r 1 and r 2 is a random number; c 1 and c 2 are acceleration factors, which respectively represent the influence of the particle's own experience and global experience on the velocity; ω is the inertia weight, which is used to indicate the influence of the velocity before the particle updates its position on the current velocity.

[0023] According to a method for detecting underground drainage pipes provided by the present invention, the first pipe node is identified based on at least one of historical infiltration inflow data, pipe material, service life and geographical location, and the second pipe node is identified based on underground pipe network topology structure.

[0024] The present invention also provides a detection device for an underground drainage pipe, comprising:

[0025] An identification module, used to identify a first pipeline node and a second pipeline node of the underground drainage network, wherein the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node;

[0026] an initialization module, used for randomly selecting a first number of first pipeline nodes and a second number of second pipeline nodes, taking each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initializing a speed of each particle;

[0027] An update module is used to calculate the fitness value of each particle on the current node based on the objective function configured by the particle swarm algorithm and iteratively update the speed and position of each particle;

[0028] A convergence module is used to calculate the total fitness value of the particle when each management area includes at least one first pipeline node and at least one second pipeline node, until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtain the target pipeline node corresponding to each particle;

[0029] A deployment module is used to deploy sensors on the target pipeline node to detect the drainage pipeline.

[0030] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a detection method for underground drainage pipes as described above is implemented.

[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting underground drainage pipes as described in any one of the above is implemented.

[0032] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned underground drainage pipe detection methods.

[0033] The underground drainage pipe detection method and device provided by the present invention optimize the sensor deployment plan through the particle swarm algorithm. With a limited number of sensors, it can fully consider the specific conditions of different management areas and different pipeline conditions, maximize the monitoring effect of the underground pipeline network, and improve the reliability of underground drainage pipe detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a schematic diagram of the flow of the underground drainage pipe detection method provided by the present invention;

[0036] Figure 2 It is a structural schematic diagram of the detection device for underground drainage pipes provided by the present invention;

[0037] Figure 3It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Combine the following Figure 1-Figure 3 The invention describes the detection method and device of underground drainage pipes.

[0040] like Figure 1 As shown, the underground drainage pipe detection method of the embodiment of the present invention mainly includes step 110, step 120, step 130, step 140 and step 150.

[0041] Step 110, identifying a first pipeline node and a second pipeline node of the underground drainage network.

[0042] The first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node.

[0043] The first pipeline node is identified based on at least one of historical infiltration inflow data, pipeline material, service life and geographical location, and the second pipeline node is identified based on underground pipeline network topology structure.

[0044] By analyzing the historical infiltration inflow data of the pipeline, such as the frequency and severity of infiltration events that occurred in the past, it is possible to identify which nodes are more likely to have infiltration inflow problems. For example, if a node has experienced multiple pipeline failures or maintenance records caused by infiltration inflow in the past, then this node can be identified as the first pipeline node.

[0045] Pipes made of different materials have different sensitivities to infiltration. For example, old concrete pipes may be more susceptible to infiltration due to material aging, cracks, and other issues, while new plastic pipes may be relatively more corrosion-resistant and infiltration-resistant. Therefore, nodes that are prone to infiltration can be identified based on the pipe material.

[0046] The age of the pipeline is also an important factor. As the service time increases, the pipeline may experience aging, wear and other problems, thereby increasing the risk of infiltration. Therefore, the pipeline nodes with a longer service life need to be more easily identified as the first pipeline node.

[0047] The geographical location of the pipeline will also affect its sensitivity to infiltration inflow. For example, pipeline nodes located in areas with high groundwater levels are more susceptible to infiltration inflow due to high groundwater pressure, while pipeline nodes located in high or dry areas are relatively less at risk. Therefore, nodes that are prone to infiltration inflow can be identified based on their geographical location.

[0048] The second pipeline node is obtained based on the topological structure of the underground pipeline network. The topological structure of the underground pipeline network refers to the connection relationship and layout form between pipelines. By analyzing the topological structure of the pipeline network, the upstream and downstream connection relationship of each pipeline node can be determined. For example, in a tree-like pipeline network, the nodes of the trunk pipeline are usually located upstream, while the nodes of the branch pipeline are located downstream. By identifying these upstream and downstream connection relationships, the second pipeline node, that is, the upstream and downstream connection node, can be determined.

[0049] Exemplarily, the first and second pipeline nodes may be identified first. Infiltration inflow sensitive nodes refer to nodes that are prone to infiltration or inflow problems, such as old pipelines, areas with known cracks, or locations with historical problems. Upstream and downstream connection nodes refer to connection points of pipelines, such as intersections or branch points.

[0050] Specifically, the first pipeline node may be screened according to historical maintenance records, a pipeline material database, topological data in a geographic information system (GIS), and the like.

[0051] For example, the screening criteria can be: old nodes where the pipeline age exceeds a threshold (such as 30 years), nodes located in areas with highly corrosive soil or high groundwater levels, nodes where leakage events have occurred in the past, and structural weak points such as pipeline joints (such as elbows and tees).

[0052] On this basis, a list of sensitive nodes can be generated and marked as the first pipeline nodes.

[0053] Based on the pipeline network topology, key connection points can be extracted to screen the second pipeline nodes (upstream and downstream connection nodes).

[0054] Specifically, graph theory algorithms (such as breadth-first search) can be used to identify the intersection of the main pipeline and the branch pipeline, and select nodes with significant flow changes (such as the dividing point where the upstream merges into the downstream), and then generate a list of connected nodes and mark them as second pipeline nodes.

[0055] Step 120 , randomly selecting a first number of first pipeline nodes and a second number of second pipeline nodes, taking each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initializing the speed of each particle.

[0056] Exemplarily, nodes may be randomly selected and particles in the particle swarm algorithm may be initialized. The first number and the second number may be determined according to actual conditions, such as the size of the pipe network or the budget of the sensor.

[0057] Assume that the total number of sensors is N, randomly select N1 nodes from the first type of nodes and N2 nodes from the second type of nodes, satisfying In one example, if the total number of sensors N=10, N1=6 and N2=4 can be set.

[0058] Each particle represents a deployment plan for a sensor, and its position vector is the selected node ID combination. When the position is initialized, N nodes are randomly assigned to the candidate node set. When the speed is initialized, it is set to a random small value (such as 0~1) to control the search step size.

[0059] Step 130 , based on the objective function configured by the particle swarm algorithm, the fitness value of each particle on the current node is calculated and the speed and position of each particle are iteratively updated.

[0060] The particle swarm algorithm can be used to calculate the fitness value and update the speed and position. The design of the objective function is the key.

[0061] In one example, the objective function may consider factors such as coverage, detection reliability, cost, etc. The calculation of the fitness value involves the importance of each node, such as a higher detection probability for a sensitive node or a wider coverage for a connected node.

[0062] In this case, the fitness value f needs to take into account both detection coverage and cost-effectiveness, for example:

[0063] ;

[0064] The coverage Cov is used to indicate the proportion of potential leakage paths that can be monitored by sensors, the redundancy R is used to indicate the proportion of key nodes covered by multiple sensors to improve fault tolerance, and the cost Cost is used to indicate the number of sensors and the difficulty of maintenance (for example, the cost of deploying in deeply buried nodes is higher). The coefficients α, β, and γ need to be adjusted according to actual needs, for example, they can be determined by the hierarchical analysis method.

[0065] In another example, the objective function is expressed as:

[0066] ;

[0067] f is the objective function value, S is the infiltration inflow sensitivity, which is determined based on at least one of the historical infiltration inflow data, pipeline material, service life and geographical location; I is the number of affected pipelines; α and β are weight coefficients used to balance the importance of infiltration inflow sensitivity and the number of affected pipelines in the objective function.

[0068] Infiltration inflow sensitivity reflects the possibility and severity of infiltration and inflow problems in pipeline nodes. For example, old concrete pipeline nodes and pipeline nodes located in areas with high groundwater levels have higher infiltration inflow sensitivity. In the objective function, the larger the S value, the more serious the infiltration inflow problem of the node, and a higher priority is required for monitoring.

[0069] The number of affected pipelines reflects the degree of influence of the location of the pipeline node on the entire pipeline network. For example, the node located upstream of the pipeline affects more pipelines and has a higher risk. In the objective function, the larger the I value, the greater the impact of the node on the entire pipeline network, and the higher the priority of monitoring is required.

[0070] The weight coefficients α and β are used to balance the importance of the infiltration inflow sensitivity (S) and the number of affected pipes (I) in the objective function. They can be determined based on actual needs and experience. For example, if the infiltration inflow sensitivity is more important, the value of α can be increased; if the number of affected pipes is more important, the value of β can be increased.

[0071] The fitness value reflects the quality of the sensor deployment scheme represented by the particle. The higher the fitness value, the more effectively the scheme can monitor the key pipeline nodes, that is, it can better balance the infiltration inflow sensitivity and the number of affected pipelines. In the particle swarm algorithm, the fitness value is used to guide the search direction and update speed of the particles, helping the algorithm to find the optimal sensor deployment plan.

[0072] According to the objective function, the fitness value of each particle on the current node is calculated. The fitness value reflects the quality of the sensor deployment scheme represented by the particle. According to the update rules of the particle swarm algorithm, the speed and position of each particle are iteratively updated.

[0073] In this process, the speed update formula can be expressed as: ;The position update formula can be expressed as: ;

[0074] Among them, v i (t) is the velocity of particle i at time t, x i (t) is the position of particle i at time t, is the individual optimal position of particle i, is the global optimal position, r 1 and r 2 is a random number; c 1 and c 2are acceleration factors, which respectively represent the influence of the particle's own experience and global experience on the velocity; ω is the inertia weight, which is used to indicate the influence of the velocity before the particle updates its position on the current velocity.

[0075] The inertia weight reflects the tendency of particles to maintain their original motion state during the search process, that is, the degree of influence of the velocity before the particle updates its position on the current velocity. The inertia weight is introduced to balance the global and local search capabilities of the algorithm. In practical applications, the inertia weight can be configured by selecting an appropriate inertia weight strategy based on the characteristics of the current scene.

[0076] c 1 and c 2 The value of needs to be set reasonably to balance the exploration and development capabilities of particles. 1 The larger the value of c, the particles will tend to move closer to their individual optimal positions, which is conducive to developing known high-quality solutions. 2 The larger the value of c, the particles will tend to move closer to the global optimal position, which is conducive to global search and exploration of new solutions. 1 and c 2 The value of has an important impact on the performance of the particle swarm algorithm. 1 and c 2 If the value of c is too small, the search ability of the particle will be weakened and it is easy to fall into the local optimum. 1 and c 2 If the value of is too large, the particle search process may be too intense, resulting in algorithm instability.

[0077] Step 140, when each management area includes at least one first pipeline node and at least one second pipeline node, calculate the total fitness value of the particle until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtain the target pipeline node corresponding to each particle.

[0078] It should be noted that the entire underground drainage network can be divided into multiple management areas. Each management area can be divided based on administrative divisions, geographical locations, pipeline structures, functional uses, etc. For example, a large city can divide the drainage network into different management areas such as the city center, suburbs, and industrial areas.

[0079] In the case where each management area includes at least one first pipeline node and at least one second pipeline node, the total fitness value of each particle is calculated. The total fitness value can be the sum of the fitness values ​​of each particle on each node, or a weighted sum according to the importance of each node.

[0080] Determine whether the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold. If the condition is met, stop the iteration and get the target pipeline node corresponding to each particle.

[0081] The iteration stops when the change in the total fitness value is less than the target threshold. The target threshold needs to be set reasonably to ensure that the algorithm converges in a reasonable time while avoiding premature stopping. In addition, each management area requires at least one first and second node condition to ensure comprehensive coverage of each area.

[0082] Step 150: deploy sensors on target pipeline nodes to detect drainage pipelines.

[0083] Deploy sensors on the determined target pipeline nodes to detect the drainage pipeline. The deployment of sensors can be wired or wireless, and the appropriate sensor type and communication protocol can be selected according to the actual situation.

[0084] According to the underground drainage pipe detection method provided by the embodiment of the present invention, the sensor deployment plan is optimized by the particle swarm algorithm. With a limited number of sensors, it is possible to fully consider the specific circumstances of different management areas and different pipeline conditions, maximize the monitoring effect of the underground pipeline network, and improve the reliability of underground drainage pipe detection.

[0085] In some embodiments, calculating the total fitness value of a particle includes: determining a first weight value corresponding to each management area and a second weight value corresponding to each particle; and calculating the total fitness value of the particle based on the first weight value corresponding to the management area of ​​each particle, the second weight value corresponding to each particle, and the fitness value of each particle.

[0086] Each management area corresponds to a first weight value, and the weight value reflects the importance or priority of the management area in the entire drainage network.

[0087] In one example, the management area of ​​the city center may be assigned a higher first weight value due to factors such as dense population, dense buildings, and large drainage demand, while the management area of ​​the suburbs may be assigned a lower first weight value due to factors such as small population, small buildings, and relatively small drainage demand. The first weight value can be set according to actual needs and experience, or determined through data analysis and evaluation.

[0088] Each particle corresponds to a second weight value, which reflects the importance or contribution of the sensor deployment scheme represented by the particle in the entire algorithm search process. The second weight value can be determined according to the fitness value of the particle. For example, the higher the fitness value of the particle, the larger its second weight value, indicating that the particle is more likely to find a high-quality solution during the search process.

[0089] The total fitness value comprehensively considers the importance of the management area and the fitness value of the particle, reflecting the exploration ability and contribution of the entire particle group to the high-quality solution during the search process. By calculating the total fitness value, different sensor deployment schemes can be better evaluated and compared to find the optimal deployment scheme.

[0090] In another example, the first weight value is inversely proportional to the number of particles in the corresponding management area, and the second weight value is proportional to the average value of the fitness values ​​of the particles in the corresponding management area.

[0091] The size of the first weight value is inversely proportional to the size of the number of particles in the corresponding management area. If there are more particles in a management area, the first weight value of the area will be relatively small; conversely, if there are fewer particles in a management area, the first weight value of the area will be relatively large. This setting can prevent particles from being too concentrated in a certain management area, resulting in an imbalance in the search space. By reducing the weight of management areas with a large number of particles, the algorithm can be prompted to pay more attention to areas with fewer particles but may have more potential, thereby improving the diversity and globality of the search.

[0092] The size of the second weight value is proportional to the average value of the fitness value of the particles in the corresponding management area. If the fitness value of the particles in a management area is higher on average, then the second weight value of the area will be relatively large; conversely, if the fitness value of the particles in a management area is lower on average, then the second weight value of the area will be relatively small. This setting can encourage the algorithm to pay more attention to those management areas that have shown better fitness values, because these areas may be closer to the optimal solution. By increasing the weights of management areas with higher fitness values, the algorithm can strengthen its search in these areas and accelerate convergence.

[0093] In some embodiments, the overall fitness value of a particle is determined using the following formula:

[0094] ;

[0095] F is the total fitness value, n is the number of management areas, is the total weight of the ith region, is the fitness value of the particle in the i-th region; , is the first weight value, is the second weight value, Ni is the number of particles in each management area, Ai is the average fitness value of particles in each management area, The size of is inversely proportional to the size of Ni. The size of is proportional to Ai.

[0096] It can be understood that the total fitness value can be calculated in this way to determine the target pipeline node.

[0097] The detection device for the underground drainage pipe provided by the present invention is described below. The detection device for the underground drainage pipe described below and the detection method for the underground drainage pipe described above can be referred to each other.

[0098] like Figure 2 As shown, the underground drainage pipe detection device according to the embodiment of the present invention mainly includes an identification module 210 , an initialization module 220 , an update module 230 , a convergence module 240 and a deployment module 250 .

[0099] The identification module 210 is used to identify a first pipeline node and a second pipeline node of the underground drainage network, the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node;

[0100] The initialization module 220 is used to randomly select a first number of first pipeline nodes and a second number of second pipeline nodes, use each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initialize the speed of each particle;

[0101] The updating module 230 is used to calculate the fitness value of each particle at the current node based on the objective function configured by the particle swarm algorithm and iteratively update the speed and position of each particle;

[0102] The convergence module 240 is used to calculate the total fitness value of the particle when each management area includes at least one first pipeline node and at least one second pipeline node, until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtain the target pipeline node corresponding to each particle;

[0103] The deployment module 250 is used to deploy sensors on target pipeline nodes to detect the drainage pipeline.

[0104] The underground drainage pipe detection device provided in the embodiment of the present invention optimizes the sensor deployment plan through the particle swarm algorithm. With a limited number of sensors, it can fully consider the specific circumstances of different management areas and different pipeline conditions, maximize the monitoring effect of the underground pipeline network, and improve the reliability of underground drainage pipe detection.

[0105] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310 , a communications interface 320 , a memory 330 and a communication bus 340 , wherein the processor 310 , the communications interface 320 , and the memory 330 communicate with each other via the communication bus 340 . The processor 310 can call the logic instructions in the memory 330 to execute the detection method of the underground drainage pipeline, which includes: identifying the first pipeline node and the second pipeline node of the underground drainage network, the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node; randomly extracting a first number of first pipeline nodes and a second number of second pipeline nodes, taking each node in the first number of first pipeline nodes and the second number of second pipeline nodes as the initial starting point of a single target particle, and initializing the speed of each particle; calculating the fitness value of each particle at the current node based on the objective function configured by the particle swarm algorithm and iteratively updating the speed and position of each particle; in the case where each management area includes at least one first pipeline node and at least one second pipeline node, calculating the total fitness value of the particle until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtaining the target pipeline node corresponding to each particle; deploying sensors on the target pipeline nodes to detect the drainage pipeline.

[0106] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0107] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the underground drainage pipe detection method provided by the above methods, which includes: identifying a first pipe node and a second pipe node of the underground drainage pipe network, the first pipe node is a permeation inflow sensitive node, and the second pipe node is an upstream and downstream connection node; randomly extracting a first number of first pipe nodes and a second number of second pipe nodes, taking each node in the first number of first pipe nodes and the second number of second pipe nodes as the initial starting point of a single target particle, and initializing the speed of each particle; calculating the fitness value of each particle at the current node based on the objective function configured by the particle swarm algorithm and iteratively updating the speed and position of each particle; in the case where each management area includes at least one first pipe node and at least one second pipe node, calculating the total fitness value of the particle until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtaining the target pipe node corresponding to each particle; deploying sensors on the target pipe nodes to detect the drainage pipe.

[0108] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the underground drainage pipe detection method provided by the above methods, the method comprising: identifying a first pipe node and a second pipe node of the underground drainage pipe network, the first pipe node being an infiltration inflow sensitive node, and the second pipe node being an upstream and downstream connection node; randomly selecting a first number of first pipe nodes and a second number of second pipe nodes, taking each of the first number of first pipe nodes and the second number of second pipe nodes as the initial starting point of a single target particle, and initializing the speed of each particle; calculating the fitness value of each particle at the current node based on the objective function configured by the particle swarm algorithm and iteratively updating the speed and position of each particle; in the case where each management area includes at least one first pipe node and at least one second pipe node, calculating the total fitness value of the particle until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtaining the target pipe node corresponding to each particle; and deploying sensors on the target pipe nodes to detect the drainage pipe.

[0109] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting underground drainage pipes, characterized in that: include: Identify a first pipeline node and a second pipeline node of an underground drainage network, wherein the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node; the first pipeline node is identified based on at least one of historical permeation inflow data, pipeline material, service life, and geographical location, and the second pipeline node is identified based on the topological structure of the underground pipeline network; Randomly select a first number of first pipeline nodes and a second number of second pipeline nodes, use each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initialize the speed of each particle; Based on the objective function configured by the particle swarm algorithm, the fitness value of each particle on the current node is calculated and the speed and position of each particle are iteratively updated; In the case where each management area includes at least one first pipeline node and at least one second pipeline node, the total fitness value of the particle is calculated until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and the target pipeline node corresponding to each particle is obtained; The calculating of the total fitness value of the particle includes: determining a first weight value corresponding to each management area and a second weight value corresponding to each particle; calculating the total fitness value of the particle based on the first weight value corresponding to the management area of ​​each particle, the second weight value corresponding to each particle, and the fitness value of each particle; the size of the first weight value is inversely proportional to the size of the number of particles in the corresponding management area, and the size of the second weight value is proportional to the average value of the fitness values ​​of the particles in the corresponding management area; A sensor is deployed on the target pipeline node to detect the drainage pipeline.

2. The underground drainage pipe detection method according to claim 1, characterized in that: The objective function is expressed as: f = α·S + β·I; f is the objective function value, S is the infiltration inflow sensitivity, which is determined based on at least one of the historical infiltration inflow data, pipeline material, service life and geographical location; I is the number of affected pipelines; α and β are weight coefficients used to balance the importance of infiltration inflow sensitivity and the number of affected pipelines in the objective function.

3. The underground drainage pipe detection method according to claim 1, characterized in that: The total fitness value of a particle is determined using the following formula: F is the total fitness value, n is the number of management areas, w i is the total weight of the ith region, F i is the fitness value of the particle in the ith region; w i =w Ni ·w Ai , w Ni is the first weight value, w Ai is the second weight value, Ni is the number of particles in each management area, Ai is the average fitness value of particles in each management area, and w Ni The size of w is inversely proportional to the size of Ni. Ai The size of is proportional to Ai.

4. The underground drainage pipe detection method according to claim 1, characterized in that: The speed update formula is: i (t+1)=ω·v i (t)+c1·r1·[p besti -x i (t)]+c2·r2·[g best -x i (t)]; the position update formula is: x i (t+1)=x i (t)+v i (t+1); Among them, v i (t) is the velocity of particle i at time t, x i (t) is the position of particle i at time t, p besti is the individual optimal position of particle i, g best is the global optimal position, r1 and r2 are random numbers; c1 and c2 are acceleration factors, which respectively represent the influence of the particle's own experience and global experience on the velocity; ω is the inertia weight, which is used to indicate the influence of the velocity before the particle updates its position on the current velocity.

5. A detection device for underground drainage pipes, characterized in that: The underground drainage pipe detection device uses the underground drainage pipe detection method according to any one of claims 1 to 4 to deploy sensors on the target pipe node to detect the drainage pipe, and the device includes: An identification module, used to identify a first pipeline node and a second pipeline node of the underground drainage network, wherein the first pipeline node is a permeation inflow sensitive node, and the second pipeline node is an upstream and downstream connection node; an initialization module, used for randomly selecting a first number of first pipeline nodes and a second number of second pipeline nodes, taking each of the first number of first pipeline nodes and the second number of second pipeline nodes as an initial starting point of a single target particle, and initializing a speed of each particle; An update module is used to calculate the fitness value of each particle on the current node based on the objective function configured by the particle swarm algorithm and iteratively update the speed and position of each particle; A convergence module is used to calculate the total fitness value of the particle when each management area includes at least one first pipeline node and at least one second pipeline node, until the absolute value of the difference between the updated total fitness value and the total fitness value obtained in the previous process is less than the target threshold, and obtain the target pipeline node corresponding to each particle; A deployment module is used to deploy sensors on the target pipeline node to detect the drainage pipeline.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the underground drainage pipe detection method according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting underground drainage pipes according to any one of claims 1 to 4 is implemented.

Images