Buried pipeline distribution recommendation method based on artificial intelligence

Abstract

The invention discloses a buried pipeline arrangement recommendation method based on artificial intelligence, and belongs to the technical field of intelligent recommendation, and the method comprises the steps: converting a laying environment of a buried pipeline, a construction purpose of the buried pipeline and specific parameters into input vectors, inputting the input vectors into a pre-trained buried pipeline arrangement recommendation model, and obtaining an initial recommendation arrangement scheme; mining historical newly-added problems of each historical management project in the management process and historical solution strategies for the historical newly-added problems to form a plurality of problem-strategy pairs, and performing clustering analysis on the problem-strategy pairs under all historical management projects by adopting a hierarchical clustering algorithm; and calculating the laying environment of the current buried pipeline and the similarity between the construction purpose of the buried pipeline and each historical pipeline distribution project based on a self-encoding similarity algorithm to obtain a problem-strategy pair needing to be reserved, and improving the initial recommended arrangement scheme according to the arrangement improvement type. And optimizing and improving the pipe arrangement scheme, and generating the pipe arrangement scheme which meets actual requirements and gives consideration to potential risk prevention and control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent recommendation, and in particular to a buried pipeline arrangement recommendation method based on artificial intelligence. BACKGROUND

[0002] As an important part of modern urban infrastructure, urban underground comprehensive buried pipelines bear the functions of centrally laying power, communication, gas, water supply and drainage, and other municipal pipelines, and have important significance for ensuring urban operation safety and improving urban space utilization. In the construction process of buried pipelines, the rationality of the pipeline arrangement scheme directly affects the operation and maintenance efficiency of the buried pipeline and the operation safety of the pipeline.

[0003] At present, the traditional buried pipeline arrangement scheme design relies on the experience and manual planning of engineers, and it is difficult to comprehensively and accurately consider the laying environment, construction purpose and specific parameters of various pipelines of the buried pipeline. At the same time, in the process of pipeline arrangement, due to the lack of systematic analysis and effective use of problems and solving strategies in historical pipeline arrangement projects, new pipeline arrangement schemes are prone to problems such as pipeline space conflict, high construction difficulty, and inconvenient maintenance in the actual construction and operation process. Moreover, the prior art is difficult to filter valuable information from historical experience according to the actual situation of the buried pipeline, so as to optimize and improve the pipeline arrangement scheme, so as to generate a pipeline arrangement scheme that meets the actual demand and takes into account the potential risk prevention and control. SUMMARY

[0004] In order to solve at least one of the above technical problems, the present application provides a buried pipeline arrangement recommendation method based on artificial intelligence.

[0005] In a first aspect, the present application provides a buried pipeline arrangement recommendation method based on artificial intelligence, which comprises:

[0006] Collecting the laying environment of the current buried pipeline, the construction purpose of the buried pipeline, and obtaining the specific parameters of a single type of pipeline applied to the current buried pipeline, and converting them into an input vector;

[0007] Inputting the input vector into a pre-trained buried pipeline arrangement recommendation model to obtain an initial recommended arrangement scheme;

[0008] Mining the historical newly added problems in the pipeline arrangement process of each historical pipeline arrangement project and the historical solving strategies for the historical newly added problems to form a plurality of problem-strategy pairs, and performing clustering analysis on the problem-strategy pairs under all historical pipeline arrangement projects using a hierarchical clustering algorithm;

[0009] Based on the self-encoding similarity algorithm, the similarity of the laying environment and the construction purpose of the buried pipeline of the current buried pipeline with each historical pipeline arrangement project is calculated.

[0010] reserve the problem-strategy pair of each historical pipe-laying project with a similarity greater than or equal to the preset degree;

[0011] determine each historical pipe-laying project with a similarity less than the preset degree based on a distribution probability in all clustering analysis results, and reserve a center cluster of a clustering analysis result corresponding to a maximum number of problem-strategy pairs involved in the historical pipe-laying project with a maximum probability in the distribution probability in each clustering analysis result;

[0012] improve the initial recommended arrangement scheme based on the arrangement improvement type of all the reserved results.

[0013] Preferably, the laying environment includes a topography of each individual pipe, a ground attachment, and an underground obstacle.

[0014] The specific parameters include a pipe specification, a pipe material, and a pipe weight.

[0015] The improved arrangement scheme includes a pipe-laying sequence, a starting pipe-laying position, and a pipe-laying auxiliary method for each individual pipe, wherein the pipe-laying auxiliary method includes a buried pipe channel carrying method, a hoisting equipment auxiliary method, a pulley block method, and / or a pipe jacking construction method.

[0016] Preferably, the conversion into the input vector includes:

[0017] numerical standardization processing of numerical data involved in the laying environment, the buried pipe construction purpose, and the specific parameters;

[0018] encoding processing of non-numerical data;

[0019] extracting conversion results for the laying environment, the buried pipe construction purpose, and the specific parameters from the numerical standardization processing results and the encoding processing results, respectively, and combining and sorting the results in order to obtain the input vector.

[0020] Preferably, the similarity between the laying environment and the buried pipe construction purpose of the current buried pipe and each historical pipe-laying project is calculated based on a self-encoding similarity algorithm, including:

[0021] obtaining a first representation and a second representation of the laying environment and the buried pipe construction purpose of the current buried pipe, respectively, while obtaining a standard combined representation and a result combined representation of the historical pipe-laying project after implementation of the project;

[0022] calculating a first Euclidean distance between the first representation and the second representation and the standard combined representation;

[0023] calculating a second Euclidean distance between the first representation and the second representation and the result combined representation.

[0024] Meanwhile, a third Euclidean distance between the standard combination representation and the result combination representation is calculated;

[0025] If the distance absolute difference of the first Euclidean distance and the second Euclidean distance is less than the third Euclidean distance, the average value of the third Euclidean distance and the distance absolute difference is determined, and the result of 1 minus the ratio of the average value to the maximum preset distance is taken as the similarity;

[0026] Otherwise, the result of 1 minus the ratio of the average distance of the first Euclidean distance and the second Euclidean distance to the maximum preset distance is taken as the similarity.

[0027] Preferably, before determining the distribution probability of the historical cabling project with the similarity less than the preset degree in all clustering analysis results, the method further comprises:

[0028] The problem-strategy pair under each historical cabling project with the similarity less than the preset degree is marked as significant in the clustering analysis result, and the first number in each clustering analysis result is counted;

[0029] The first ratio of the first number to the total number of the problem-strategy pair involved in the corresponding clustering analysis result is calculated;

[0030] The sum of all the first ratios is calculated, and the maximum ratio is extracted from all the first ratios;

[0031] The sum and the maximum ratio of all the historical cabling projects with the similarity less than the preset degree are respectively sorted from large to small to construct a two-dimensional array, wherein each value occupies a cell;

[0032] The first average value of the absolute difference of the adjacent two sums in the row array related to the sum in the second array is calculated, and the second ratio of the first average value to the average value of all the first numbers of the corresponding historical cabling project involved is calculated as the second average value;

[0033] The third average value of the absolute difference of the adjacent two maximum ratios in the row array related to the maximum ratio in the second array is calculated;

[0034] If the second average value is greater than or equal to the third average value, the third ratio of the second average value to the third average value is determined, and the fourth ratio of the absolute difference of the adjacent two sums to the second average value is determined;

[0035] The product result of the third ratio and the fourth ratio is rounded down, and a blank cell consistent with the rounding down result is inserted between the corresponding adjacent two sums;

[0036] The row array with the inserted blank cell is updated in sequence number;

[0037] The total number of inserted blank spaces in the row array updated according to the serial numbers is inserted into the blank space, and the row array corresponding to the maximum ratio is inserted into the blank space from the middle of the adjacent maximum ratio, based on 1 blank space, until the inserted number is consistent with the total number, the insertion is stopped, and the serial number is updated;

[0038] Otherwise, the two-dimensional array remains unchanged.

[0039] Preferably, the distribution probability of each historical pipe arrangement project with a similarity less than a preset degree in all clustering analysis results is determined, including:

[0040] The first serial number based on the first row and the second serial number based on the second row of each historical pipe arrangement project with a similarity less than a preset degree are extracted from the final array;

[0041] The calculation result of 1-(first serial number+second serial number) / (2*total serial number) is taken as the corresponding distribution probability.

[0042] Preferably, based on the arrangement improvement type of all retained results, the initial recommended arrangement scheme is improved, including:

[0043] The solution type of each problem-strategy pair in all retained results is mapped with the structure type of each single pipe in the initial recommended arrangement scheme to obtain a mapping pair of each single pipe.

[0044] The mapping pair is fused with the sub-recommended arrangement scheme of each single pipe based on a rule fusion algorithm to realize scheme improvement.

[0045] In a second aspect, the present application further provides an electronic device, comprising a processor and a memory, the memory is used to store computer program code, the computer program code comprises computer instructions, when the processor executes the computer instructions, the electronic device executes the artificial intelligence-based buried pipe arrangement recommendation method of the first aspect and any one of the possible implementation manners thereof.

[0046] In a third aspect, the present application further provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program comprises program instructions, when the program instructions are executed by the processor of an electronic device, the processor executes the artificial intelligence-based buried pipe arrangement recommendation method of the first aspect and any one of the possible implementation manners thereof.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] (1) By collecting the laying environment, construction purpose and specific parameters of the current buried pipeline and converting them into input vectors, inputting them into the pre-trained buried pipeline layout recommendation model, an initial recommended layout scheme based on actual conditions can be generated, fully considering various characteristics of buried pipelines and pipelines, making the pipeline layout scheme more in line with actual needs, and improving the rationality and scientificity of the scheme.

[0049] (2) The problem-strategy pairs in historical pipeline layout projects are mined and clustered, and relevant information is selected according to the similarity between the current buried pipeline and the historical projects. In this way, past experiences and lessons can be learned to avoid similar problems from recurring, while providing optimization ideas for the current pipeline layout scheme, which helps to improve the quality and reliability of the pipeline layout scheme.

[0050] (3) The similarity is calculated based on the self-encoding similarity algorithm, which can accurately find similar historical pipeline layout projects to the current buried pipeline situation and retain relevant problem-strategy pairs. For projects with low similarity, representative clustering analysis result center clusters are found by determining the distribution probability, so as to obtain valuable problem-strategy pairs. This way can specifically solve potential problems that may be encountered in the current pipeline layout, improving the stability and feasibility of the scheme.

[0051] (4) The initial recommended layout scheme is improved by synthesizing the layout improvement types of all retained results, realizing the full-process intelligentization from data collection, model recommendation to optimization based on historical experience, reducing the influence of manual intervention and subjective factors, improving the efficiency and accuracy of pipeline layout scheme design, and generating a pipeline layout scheme that meets actual needs and takes into account potential risk prevention and control.

[0052] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the drawings needed to be used in the embodiments of the present application or the background art will be described below.

[0054] The drawings herein are incorporated into the specification and form part of the specification, which show embodiments consistent with the present disclosure, and together with the specification, serve to illustrate the technical solutions of the present disclosure.

[0055] Figure 1 The flowchart of the buried pipeline layout recommendation method based on artificial intelligence provided by the embodiments of the present application;

[0056] Figure 2 The hardware structure schematic diagram of an electronic device in the embodiments of the present application. DETAILED DESCRIPTION

[0057] In order to better understand the technical scheme of the present application, the technical scheme in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0058] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, rather than to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or device.

[0059] The term "and / or" herein is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0060] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various locations in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative embodiments to each other. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0061] In addition, in order to better illustrate the present application, numerous specific details are given in the specific embodiments below. Those skilled in the art should understand that the present application can be implemented without certain specific details. In some examples, methods, means, elements and circuits well known to those skilled in the art are not described in detail, in order to highlight the main idea of the present application.

[0062] The present application provides an artificial intelligence-based buried pipeline layout recommendation method, as shown in Figure 1 The method comprises:

[0063] Step 1: Collect the laying environment of the current buried pipeline, the construction purpose of the buried pipeline, and the specific parameters of the single type of pipeline applied to the current buried pipeline, and convert them into an input vector;

[0064] The current buried pipeline refers to a buried pipeline project that is being planned, constructed, or evaluated. For example, a new underground comprehensive buried pipeline in a city is used to lay multiple pipelines such as power, communication, and water supply.

[0065] The laying environment refers to the natural and artificial environmental conditions of the buried pipeline laying area, including:

[0066] Topography, such as mountainous area (slope 20°, elevation difference 100 meters), plain (average elevation 50 meters), and marshland (water content 80%).

[0067] The current status of ground attachments is the ground pipe gallery (such as concrete structure, foundation buried depth 2 meters, plane size 10m x 5m, protection requirement: mechanical excavation prohibited within 3 meters), buildings, and roads (two-way six-lane, traffic volume 2000 vehicles / hour).

[0068] Underground obstacle information is underground pipelines (such as DN300 cast iron water supply pipe, buried depth 1.5 meters), cable trench (width 1 meter, buried depth 0.8 meters), and underground structures (inspection well, diameter 2 meters, buried depth 3 meters).

[0069] The construction purpose is the core requirement of pipeline laying, such as:

[0070] New municipal sewage pipeline (serving a population of 100,000), old industrial area pipeline expansion (increasing oil transportation capacity by 20%), and emergency rescue pipeline replacement (repairing broken gas pipeline).

[0071] The specific parameters of the single type of pipeline are, for example, specifications: DN500 (pipe diameter 500mm), wall thickness 10mm; materials: PE (polyethylene), Q235B steel; weight: PE pipe 15kg per meter, steel pipe 40kg per meter; buried depth requirement: sewage pipe buried depth ≥3.5 meters (below frost layer), gas pipe buried depth ≥1.2 meters (specification requirement). The input vector is to convert the above data into a numerical vector recognizable by the model, and the implementation means is numerical standardization, which is to use Z-score standardization for terrain elevation (such as 50 meters): (50- average elevation 45) / standard deviation 2.5=2; and to normalize the buried depth (3.5 meters): 3.5 / maximum buried depth 5=0.7.

[0072] Non-numerical encoding is the type of ground pipe gallery "concrete structure" one-hot encoding as [1,0] (assuming two types: concrete / steel structure); and the crossing method "pipe jacking" encoding as [0,1,0] (assuming three types: pipe jacking / directional drilling / large excavation).

[0073] The vector combination is spliced in the order of "laying environment, construction purpose, and pipeline parameter", for example: [terrain slope standardization value, above-ground pipe gallery code, underground obstacle coordinate, construction purpose code, pipe diameter normalization value, material code, and buried depth standardization value].

[0074] Step 2: input the input vector into the pre-trained buried pipeline layout recommendation model to obtain an initial recommended layout scheme;

[0075] The pre-trained buried pipeline layout recommendation model is a model combining convolutional neural network and recurrent neural network, a large amount of historical buried pipeline layout data is used to adjust the model parameters through the back propagation algorithm to optimize the model performance, so that it can accurately output the initial scheme according to the input, and the input sample for training the model is: the laying environment of the historical buried pipeline, the construction purpose of the buried pipeline and the input vector converted from the specific parameters, and the output sample is the layout scheme set by the layout experts for the laying environment of the historical buried pipeline, the construction purpose of the buried pipeline and the specific parameter conversion,

[0076] The initial recommended layout scheme includes pipeline route (such as laying 2 meters outside the right red line along the road), layout sequence (sewage pipe below and water supply pipe above), preliminary crossing method (road crossing using large excavation), and buried depth suggestion (3.8 meters), for example, the initial scheme of the gas pipeline in an industrial park suggests that the route is laid along the east side of the main road, directional drilling is used for crossing the intersection, and the buried depth is 1.5 meters.

[0077] Step 3: excavate the historical new problems in the layout process of each historical layout project and the historical solution strategies for the historical new problems, form a plurality of problem-strategy pairs, and use hierarchical clustering algorithm to cluster and analyze the problem-strategy pairs under all historical layout projects;

[0078] The construction records, problem feedback documents and other materials of each historical layout project are extracted from the enterprise historical project database, the historical new problems and the corresponding historical solution strategies are sorted out to form the problem-strategy pairs. The hierarchical clustering algorithm is used to calculate the similarity between the problem-strategy pairs based on the text features or numerical features of the problem-strategy pairs, similar problem-strategy pairs are classified into one class, and clustering clusters are formed. The problem-strategy pair: in the layout project, the corresponding solution strategy proposed for the specific problem, and the two form a combination. For example, "insufficient pipeline space (problem) - use multi-layer layout method (strategy)".

[0079] The text information in the historical documents is segmented, tagged, and analyzed based on natural language processing technology to extract key problem and strategy information.

[0080] Based on the hierarchical clustering algorithm, the Euclidean distance between data points is calculated, and the clustering clusters are merged or split from bottom to top or from top to bottom, so as to mine the internal structure of the data and provide support for subsequent reference.

[0081] Step 4: Based on the self-encoding similarity algorithm, the laying environment and construction purpose of the current buried pipeline are calculated to be similar to each historical pipe laying project.

[0082] The self-encoder network is constructed, the laying environment and construction purpose data of the current buried pipeline and the data of each historical pipe laying project are input into the self-encoder respectively, and the low-dimensional feature vector is extracted. The similarity between the current buried pipeline and the historical pipe laying project feature vector is measured by the Euclidean distance calculation method.

[0083] The self-encoder is an unsupervised learning neural network, which learns the effective feature representation of data through encoding and decoding process, realizes feature extraction and dimension reduction, and the Euclidean distance reflects the spatial distance between vectors, which helps to quantify the similarity between the current buried pipeline and the historical project, and provides basis for screening valuable historical experience.

[0084] Step 5: The problem-strategy pair of the historical pipe laying project with similarity greater than or equal to the preset degree is reserved.

[0085] Simple numerical comparison logic, the comparison of similarity and preset degree and data screening are realized by conditional judgment statement in the program, and the value of preset degree is 0.6.

[0086] Step 6: Determine the distribution probability of each historical pipe laying project based on all clustering analysis results, and reserve the center cluster of the clustering analysis result corresponding to the maximum number of problem-strategy pairs involved in the historical pipe laying project under the maximum probability in the distribution probability.

[0087] Through probability calculation and statistical analysis, the "historical pipe laying project with similarity less than the preset degree" is processed, and the representative "center cluster of clustering analysis result" is screened out based on the "distribution probability", which supplements the reference information of the optimization scheme.

[0088] Step 7: Based on the arrangement improvement type of all reserved results, the initial recommended arrangement scheme is improved.

[0089] All the retained question-strategy pairs are analyzed to extract the arrangement improvement types involved, such as adjusting the arrangement sequence, changing the starting pipe laying position, and selecting a suitable pipe laying auxiliary method. According to these improvement types, the initial recommended arrangement scheme generated in step 2 is adjusted to form a final improved arrangement scheme. The rule-based scheme adjustment method modifies the pipe laying sequence, starting pipe laying position, and other parameters of the initial scheme by writing program rules according to the extracted arrangement improvement types. The "arrangement improvement types" are extracted from the retained question-strategy pairs and used to optimize the "initial recommended arrangement scheme" to form an improved arrangement scheme that includes the pipe laying sequence, starting pipe laying position for each individual pipe, and pipe laying auxiliary method for each pipe.

[0090] The arrangement improvement type is an optimization direction extracted from the retained question-strategy pairs, such as: crossing method adjustment (large excavation → pipe jacking), depth optimization (increase by 0.5 meters to avoid underground cables), and route offset (avoiding above-ground pipe gallery foundation). Type mapping is the association of the solution type of the question-strategy pair with the obstacle type of the current laying environment, such as:

[0091] The obstacle type of the above-ground pipe gallery foundation is mapped to the solution type of the non-excavation crossing, generating a mapping pair (pipe gallery foundation protection, micro-tunneling).

[0092] The rule fusion algorithm is based on engineering specifications (such as the "Buried Pipeline Construction Specification") to fuse the mapping pair with the initial scheme. The implementation method is as follows: if the initial scheme crosses the road using large excavation, and the mapping pair requires non-excavation, then according to the rule in the specification that a road traffic volume > 1000 vehicles / hour requires non-excavation, adjust it to pipe jacking crossing.

[0093] Through the complete process of steps 1-7, the initial recommended arrangement scheme is optimized. In the experimental project, the buried pipeline data is accurately obtained using three-dimensional laser scanning and data preprocessing technology to generate input vectors, and the initial scheme is generated by a deep learning model, and then optimized combined with historical experience. Finally, the spatial conflict problem is reduced by 80%, thanks to accurate similarity calculation and reasonable historical experience selection, the appropriate arrangement sequence and pipe laying auxiliary method are selected; the construction efficiency is improved by about 30%, the starting pipe laying position and pipe laying auxiliary method are optimized, and the construction obstacles are reduced; the construction period is shortened by an average of 10%, effectively verifying the effectiveness of the scheme in improving the rationality of the pipe laying scheme, reducing potential problems, improving construction efficiency, and reducing costs.

[0094] Preferably, the laying environment includes the topography, above-ground attachments, and underground obstacles of each individual pipe;

[0095] The specific parameters include: pipe specifications, pipe materials, and pipe weights;

[0096] The improved arrangement scheme includes the pipe arrangement sequence under each section of the individual pipe, the starting pipe arrangement position, and the pipe arrangement auxiliary mode of each pipe, wherein the pipe arrangement auxiliary mode includes a buried pipe channel carrying mode, a hoisting equipment auxiliary mode, a pulley block mode, and / or a pipe jacking construction mode.

[0097] In this embodiment, the buried pipe channel carrying is mainly achieved by moving the rail car, flat car and other transportation tools on the track or flat channel laid inside the buried pipe. First, select the appropriate transportation tool according to the size and weight of the pipe, fix the pipe on the transportation tool, and ensure that the pipe is stable during transportation. Then, by manual or electric traction, move the transportation tool along the planned route in the buried pipe channel to transport the pipe to the designated installation position. During the carrying process, a dedicated person needs to be arranged to monitor the pipe state and transportation path in real time to avoid collision with other facilities inside the buried pipe.

[0098] The hoisting equipment auxiliary mode often uses large hoisting machinery such as automobile hoist and crawler crane. Before construction, the hoisting site needs to be surveyed to determine the parking position and lifting radius of the hoisting equipment to ensure that the equipment can operate safely and stably. According to the weight, size and installation height of the pipe, select appropriate hoisting rigging and hooks to firmly connect the pipe with the rigging. When hoisting, the pipe is lifted by the lifting arm of the hoisting equipment, and slowly placed into the installation position in the buried pipe according to the predetermined hoisting path and height. During hoisting, professional signal commanders need to closely cooperate with hoisting operators to ensure the safety and accuracy of the hoisting process.

[0099] The pulley block mode is to use the principle of force saving of pulley block to pull and move the pipe inside the buried pipe. First, install the fixed pulley block support at a suitable position in the buried pipe, install the pulley block on the support, and configure the corresponding number of fixed pulleys and movable pulleys according to the weight and moving direction of the pipe. Then, connect the pipe with the pulley block through the steel wire rope, pull the steel wire rope by manpower or small electric winch, and slowly move the pipe along the preset track or path by the action of the pulley block. During the movement, the tension of the steel wire rope and the position of the pulley block need to be adjusted constantly to ensure the smooth movement of the pipe.

[0100] Pipe jacking construction is a non-excavation construction technology. In the pipe arrangement of buried pipe, first, set up a working well and a receiving well at the starting end and the terminal end of the buried pipe respectively. Install the pipe jacking machine and jacking equipment in the working well, put the prefabricated pipe into the working well, and then push the pipe into the soil layer along the designed axis direction by the jacking equipment, while excavating and transporting the earth inside the pipe, so that the pipe continuously advances forward until the pipe reaches the receiving well and completes the installation. During the jacking process, the axis deviation and jacking pressure of the pipe need to be monitored in real time to ensure the jacking accuracy and construction safety of the pipe by adjusting the jacking equipment and excavation method.

[0101] The beneficial effects produced by the above steps 1 to step 7 are as follows:

[0102] (1) By collecting the laying environment of the current buried pipeline, the construction purpose and the specific parameters of the pipeline and converting them into input vectors, inputting them into the pre-trained buried pipeline layout recommendation model, an initial recommended layout scheme based on the actual situation can be generated, which fully considers the various characteristics of the buried pipeline and the pipeline, makes the pipeline layout scheme more in line with the actual demand, and improves the rationality and scientificity of the scheme.

[0103] (2) The problem-strategy pairs in the historical pipeline layout projects are mined and clustered, and then relevant information is selected according to the similarity between the current buried pipeline and the historical projects. In this way, the past experiences and lessons can be learned to avoid similar problems from recurring, and at the same time, optimization ideas are provided for the current pipeline layout scheme, which helps to improve the quality and reliability of the pipeline layout scheme.

[0104] (3) The similarity is calculated based on the self-encoding similarity algorithm, which can accurately find the historical pipeline layout projects similar to the current buried pipeline situation and retain the relevant problem-strategy pairs. For projects with low similarity, representative clustering analysis result center clusters are found by determining the distribution probability, so as to obtain valuable problem-strategy pairs. This way can specifically solve the potential problems that may be encountered in the current pipeline layout, and improve the stability and feasibility of the scheme.

[0105] (4) The initial recommended layout scheme is improved by synthesizing the layout improvement types of all retained results, realizing the whole process intelligentization from data collection, model recommendation to optimization based on historical experience, reducing the influence of manual intervention and subjective factors, improving the efficiency and accuracy of the pipeline layout scheme design, and generating a pipeline layout scheme that meets the actual demand and takes into account the potential risk prevention and control.

[0106] The present application provides a buried pipeline layout recommendation method based on artificial intelligence, which is converted into an input vector, including:

[0107] The numerical data involved in the laying environment, the construction purpose of the buried pipeline and the specific parameters are subjected to numerical standardization processing;

[0108] The non-numerical data is subjected to coding processing;

[0109] The conversion results for the laying environment, the construction purpose of the buried pipeline and the specific parameters are extracted from the numerical standardization processing results and the coding processing results, respectively, and the input vector is obtained by combining and sorting in order.

[0110] The numerical data is a physical quantity or attribute that can be directly represented by a number, including:

[0111] Relevant to laying environment: terrain slope (e.g. 20°), altitude (50 meters), underground obstacle depth (1.5 meters), above-ground pipe gallery foundation size (10 meters long, 5 meters wide);

[0112] Relevant to pipeline parameters: pipe diameter (DN500, i.e. 500mm), wall thickness (10mm), pipeline weight (15kg per meter), designed burial depth (3.5 meters).

[0113] Non-numeric data cannot be directly represented by numbers or text information, including:

[0114] Relevant to laying environment: above-ground pipe gallery type (concrete / steel structure), underground obstacle material (cast iron / PE), terrain type (mountain / flat / marsh);

[0115] Relevant to construction purpose: pipeline purpose (sewage / gas / water supply), construction type (new construction / expansion / repair);

[0116] Relevant to pipeline parameters: material (Q235B steel / PE), crossing method (pipe jacking / directional drilling / large excavation).

[0117] Encoding is the process of converting non-numeric data into numerical vectors that can be calculated by the model, and the means are:

[0118] One-Hot Encoding is suitable for unordered categorical variables, and a binary vector is generated for each category. For example, the above-ground pipe gallery type is "concrete structure", assuming the categories are [concrete, steel structure], the One-Hot Encoding is [1,0]; if it is "steel structure", it is [0,1].

[0119] Label Encoding is suitable for ordered categorical variables, such as construction priority (high / medium / low) encoding [2,1,0], but note that the model may misjudge the order.

[0120] Word Embedding is suitable for text descriptions (such as "karst topography"), and a dense vector is generated through a pre-trained model (such as Word2Vec), but the structured categorical data is more focused in the steps.

[0121] The crossing method "pipe jacking" is encoded as [0,1,0] (assuming the categories are [large excavation, pipe jacking, directional drilling]);

[0122] The pipeline material "PE" is encoded as [0,1] (assuming the categories are [steel, PE]).

[0123] Feature extraction is to extract corresponding features according to dimensions from standardized and encoded data, including:

[0124] The laying environment is the standardization value of terrain slope, the standardization value of elevation, the above-ground pipe gallery coding vector, and the standardization value of buried depth of underground obstacles;

[0125] The construction purpose is the use coding vector (such as sewage pipe coding [1, 0, 0]) and the construction type coding (new construction coding 1);

[0126] The pipe parameter is the normalized value of pipe diameter, the material coding vector, the weight standardization value, and the design buried depth normalized value.

[0127] The sequential combination sorting is to splice the vectors in the logical order of “laying environment-construction purpose-pipe parameter” to form a one-dimensional feature vector of the input model, such as:

[0128] The laying environment part: [terrain slope Z value (2), elevation Z value (2), above-ground pipe gallery coding (1, 0), and obstacle buried depth normalized value (0.6)];

[0129] The construction purpose part: [use coding (1, 0, 0) and construction type label (1)];

[0130] The pipe parameter part: [pipe diameter normalized value (0.5), material coding (0, 1), weight Z value (1.2), and buried depth normalized value (0.4)];

[0131] The final input vector: [2, 2, 1, 0, 0.6, 1, 0, 0, 1, 0.5, 0, 1, 1.2, 0.4] (total of 14 dimensions).

[0132] For the above scheme, use the pandas library of Python to process data, use the sklearn.preprocessing module for standardization (StandardScaler) and one-hot encoding (OneHotEncoder), and splice the features of each dimension through numpy array to ensure consistency with the model training order.

[0133] After standardization, the values of terrain elevation (50 meters) and pipe diameter (500 mm) are at the same weight level, avoiding model bias due to "large number dominance". For example, if not standardized, pipe diameter 500 mm (value 500) may mask the impact of elevation 50 meters, leading to model misjudgment of the impact of terrain on pipe laying. The encoded non-numerical data enables the model to identify the differences between categories. For example, the encoding vector difference between the ground pipe gallery types "concrete" and "steel structure" helps the model learn the impact of different structures on pipe laying (such as the need for a larger safety distance for concrete foundations). The uniform format of the input vector ensures the stability of the model training and inference. For example, the input vector dimensions of all projects are the same, avoiding model errors caused by data format chaos and improving the accuracy of pipe laying scheme recommendations (such as reducing the error of buried depth recommendation from ±0.8 meters to ±0.3 meters). Through vector combination, the model can handle multiple dimensional features such as terrain, obstacles, and pipe parameters to generate more reasonable pipe laying schemes. For example, when laying PE pipes in mountainous areas, the model can combine the slope standardization value and material coding to recommend the "along contour line laying + anti-skid support" scheme, which improves the construction feasibility by 40% compared to traditional manual design.

[0134] The application provides a buried pipe laying recommendation method based on artificial intelligence, which respectively acquires a first representation and a second representation of a laying environment and a buried pipe construction purpose of the current buried pipe, and simultaneously acquires a standard combined representation and a result combined representation of a historical pipe laying project after project implementation.

[0135] The first Euclidean distance between the first representation and the second representation and the standard combined representation is calculated.

[0136] The second Euclidean distance between the first representation and the second representation and the result combined representation is calculated.

[0137] Meanwhile, the third Euclidean distance between the standard combined representation and the result combined representation is calculated.

[0138] If the absolute distance difference between the first Euclidean distance and the second Euclidean distance is less than the third Euclidean distance, the average value of the third Euclidean distance and the absolute distance difference is determined, and the result of 1-the average value divided by the maximum preset distance is taken as the similarity.

[0139] Otherwise, the result of 1-the average distance of the first Euclidean distance and the second Euclidean distance divided by the maximum preset distance is taken as the similarity.

[0140] The first representation of the current project (the laying environment representation) is a low-dimensional feature vector of the current buried pipeline laying environment extracted by the autoencoder, including terrain, above-ground attachments, underground obstacles, etc. For example, a current project laying environment is "mountain (slope 20°, elevation 500 meters), above-ground concrete pipe gallery (foundation buried depth 2 meters, size 10m x 5m), underground 1.5 meters DN300 water supply pipe", after encoding by the autoencoder, the feature vector [0.8, 0.1, 0.3, 0.2] is obtained (assuming 4 dimensions, corresponding to terrain, above-ground pipe gallery, underground obstacle, soil type respectively).

[0141] The second representation of the current project (the construction purpose representation) is a low-dimensional feature vector of the construction purpose, including pipeline purpose, construction type, etc. For example, the construction purpose is "newly built municipal sewage pipeline (serving a population of 100,000)", which is encoded as [0.9, 0.1] (assuming 2 dimensions, the first dimension corresponds to "newly built" and the second dimension corresponds to "sewage").

[0142] The standard combined representation of the historical project (the pre-construction planning representation) is a feature vector extracted by the autoencoder from the historical project's pre-construction planning data, reflecting the expected environment and target in the design stage. For example, a historical project pre-construction planning is "flat terrain, no pipe gallery above ground, laying DN500 gas pipeline (newly built)", the standard combined representation is [0.2, 0, 0.8] (3 dimensions, corresponding to terrain, above-ground attachments, pipeline purpose).

[0143] The result combined representation of the historical project (the post-construction actual representation) is a feature vector of the actual data after the implementation of the historical project, reflecting the real situation after construction (such as actual route deviation, buried depth adjustment, etc.). For example, the above historical project actually adjusted the route after construction due to underground obstacles, and the result combined representation is [0.25, 0.05, 0.75] (terrain feature changes slightly, new obstacle feature is added).

[0144] The first Euclidean distance (distance between current and historical planning) is the spatial distance between the first and second representations of the current project and the standard combined representation of the historical project, measuring the difference between the current planning and the historical planning. For example: current laying environment representation A = [0.8, 0.1, 0.3, 0.2], construction purpose representation B = [0.9, 0.1], historical standard combined representation C = [0.2, 0, 0.8, 0, 0.8] (assuming 5 dimensions, the first 4 dimensions are environment, the 5th dimension is construction purpose).

[0145] The second Euclidean distance (current and historical actual distance) is the distance between the current project representation and the historical project result combination representation, which measures the difference between the current plan and the historical actual execution result, for example: the historical result combination representation D=[0.25, 0.05, 0.8, 0, 0.75], and the current representation splicing vector AB=[0.8, 0.1, 0.3, 0.2, 0.9, 0.1].

[0146] The third Euclidean distance (historical planning and actual distance) is the distance between the historical project standard combination representation and the result combination representation, reflecting the deviation (such as design change, construction error) of the historical project before and after construction.

[0147] Example: historical standard representation C=[0.2, 0, 0.8, 0, 0.8], result representation D=[0.25, 0.05, 0.8, 0, 0.75].

[0148] It should be noted that the similarity between the current project and the historical project is 0.761, which means that the experience of the historical project has a high reference value for the current scheme (if the preset degree is 0.6, the problem-strategy pair is retained). Therefore, by calculating different Euclidean distances, the similarity between the current buried pipeline and the historical pipe laying project before construction and the result after construction is considered comprehensively, and the change of the historical project itself before and after construction is considered, so that the calculation of the similarity is more comprehensive and accurate. According to the difference between the first Euclidean distance and the second Euclidean distance, different similarity calculation methods are adopted, which can better adapt to different data characteristics and actual situations, and improve the rationality of similarity calculation. The calculated similarity can provide reference for the planning, design and construction of the current buried pipeline, help decision makers learn from the experience of historical projects, and optimize the construction scheme of the current buried pipeline.

[0149] The application provides a buried pipeline pipe laying recommendation method based on artificial intelligence, and before determining the distribution probability of the historical pipe laying project with a similarity less than a preset degree in all clustering analysis results, the method further comprises the following steps of:

[0150] Significantly marking the problem-strategy pair under each historical pipe laying project with a similarity less than a preset degree in the clustering analysis result, and counting the first number in each clustering analysis result;

[0151] Assuming that there are 10 problem-strategy pairs under historical management project C1, there are 4 clustering clusters after analysis based on hierarchical clustering algorithm, and the first clustering cluster involves 2 problem-strategy pairs in historical management project C1, the second clustering cluster involves 5 problem-strategy pairs in historical management project C1, the third clustering cluster involves 2 problem-strategy pairs in historical management project C1, and the fourth clustering cluster involves 1 problem-strategy pair in historical management project C1, and the significance marker is to mark the representation of the corresponding problem-strategy pair with color for easy viewing, and the first number obtained is: 2, 5, 2, and 1.

[0152] Calculate the first ratio of the first number to the total number of problem-strategy pairs involved in the corresponding clustering analysis result.

[0153] The first ratio is the first number of problem-strategy pairs involved in the corresponding clustering cluster / the total number of problem-strategy pairs involved in the corresponding clustering analysis result, for example, there are 20 problem-strategy pairs under the first clustering cluster, and the first ratio is 2 / 20.

[0154] Calculate the sum of all first ratios, and extract the maximum ratio from all first ratios.

[0155] Each historical management project has a sum and a maximum ratio.

[0156] Sort the sum and the maximum ratio of all historical management projects with a similarity less than a preset degree from large to small, respectively, to construct a two-dimensional array, wherein each value occupies a cell.

[0157] The cell is set to place the sum and the ratio.

[0158] For example, there are 3 historical management projects with a similarity less than a preset degree, which are project C1, project C6 and project C9, and the corresponding sums are 0.8, 0.6 and 0.9, respectively, and the corresponding maximum ratios are 0.1, 0.2 and 0.6, respectively, at this time, the two-dimensional array is: Each element in the two-dimensional array occupies a cell, and the element is the value and the serial number, wherein the sum is the first row and the maximum ratio is the second row.

[0159] Calculate the first average value of the absolute value of the difference between the adjacent two sums in the row array related to the sum in the second array, and calculate the second ratio of the first average value to the average value of all first numbers under the corresponding historical management project involved, as the second average value.

[0160] The first average value of the absolute value of the difference between the adjacent two sums: for example: (0.9-0.8+0.8-0.6) / 2.

[0161] The first average value is the sum of the first number of problem-strategy pairs under each cluster divided by the number of clusters.

[0162] The second average value is the first average value divided by the average value of all first numbers under the corresponding historical project.

[0163] The third average value is the absolute value of the difference between the two largest ratios in the row array associated with the largest ratio in the second array.

[0164] The third average value is the absolute value of the difference between the two largest ratios in the row array associated with the largest ratio in the second array.

[0165] If the second average value is greater than or equal to the third average value, determine the third ratio of the second average value to the third average value, and determine the fourth ratio of the absolute value of the difference between the two sums to the second average value.

[0166] The product of the third ratio and the fourth ratio is rounded down, and a blank is inserted between the corresponding two sums.

[0167] The row array with the inserted blank is updated with the sequence number.

[0168] According to the total number of inserted blanks in the row array after the sequence number update, a blank is inserted in the corresponding row array associated with the largest ratio from the middle of the adjacent largest ratio based on 1 blank, and the process is repeated until the number of inserted blanks matches the total number, and the sequence number is updated.

[0169] Otherwise, the two-dimensional array remains unchanged.

[0170] wherein, is the floor symbol; is the number of inserted blanks.

[0171] For example, there are a1 blanks between and there are a2 blanks between and .

[0172] Assuming the sum of a1 and a2 is 3, the cyclic insertion process is:

[0173]

[0174] The insertion result is: .

[0175] Therefore, by inserting blank spaces between the two adjacent sums in the row array and cyclically updating the row data of the maximum ratio, the corresponding serial number update and insertion operations are performed on the two row arrays, and finally the adjusted two-dimensional array is obtained. Through this way, the data characteristics can be more intuitively displayed, and the distribution of historical pipe laying projects with low similarity in clustering can be helped to analyze.

[0176] The application provides a buried pipeline pipe laying recommendation method based on artificial intelligence, determines the distribution probability of each historical pipe laying project with a similarity less than a preset degree in all clustering analysis results, including:

[0177] Extracting the first serial number based on the first row and the second serial number based on the second row of each historical pipe laying project with a similarity less than a preset degree from the final array;

[0178] Taking the calculation result of 1-(first serial number+second serial number) / (2*total serial number) as the corresponding distribution probability.

[0179] Therefore, by calculating the distribution probability, the similarity of the historical pipe laying project and the current buried pipeline is converted into a specific numerical value, which facilitates quantitative evaluation and comparison of different historical pipe laying projects. For example, the closer the distribution probability is to 1, the greater the difference between the historical pipe laying project and the current buried pipeline; the closer the distribution probability is to 0, the smaller the difference. This helps to quickly identify historical projects that are similar or have large differences with the current buried pipeline, providing a reference for decision-making. The formula comprehensively considers the first serial number based on the first row and the second serial number based on the second row, evaluates the historical pipe laying project from multiple dimensions, avoids the limitations of relying on a single factor for judgment, and makes the evaluation result more comprehensive and accurate. The total serial number as the denominator normalizes the serial number information, so that the distribution probability is within the range of 0 to 1, which is easy to understand and compare. Integrating serial number information of different dimensions into a unified probability value realizes data standardization and normalization. This way, different dimensions and ranges of original data can be converted into comparable probability data, which facilitates further data analysis and mining, such as sorting and classifying historical pipe laying projects according to the distribution probability, providing stronger data support for subsequent decision support.

[0180] The application provides a buried pipeline pipe laying recommendation method based on artificial intelligence, improves the initial recommended arrangement scheme based on the arrangement improvement type of all retained results, including:

[0181] Mapping the solution type of each problem-strategy pair in all retained results to the structure type of each individual pipe in the initial recommended arrangement scheme to obtain a mapping pair for each individual pipe;

[0182] The mapping pairs are fused with the sub-recommendation arrangement schemes of each individual pipeline segment based on a rule fusion algorithm to achieve scheme improvement.

[0183] The problem-strategy pairs in the results are the historical problems and corresponding solutions retained after similarity screening, such as ("railway settlement exceeds the standard", "use micro tunnel boring machine"), for example: in a certain historical project, the problem is "excavation within the foundation protection range of the above-ground pipe gallery causes structural cracks", and the strategy is "non-excavation pipe-jacking construction + foundation settlement monitoring".

[0184] The solution type is a functional classification of the solution strategy, which is used to abstract the core purpose of the strategy, including:

[0185] Spatial optimization: adjust the pipeline arrangement or routing to avoid obstacles (such as "multi-layer pipeline arrangement" and "routing offset");

[0186] Non-excavation construction: avoid excavation crossing methods (such as "pipe-jacking" and "directional drilling");

[0187] Material enhancement: replace the pipeline material or auxiliary material (such as "high-strength steel pipe" and "anticorrosion coating").

[0188] The structure type in the initial scheme is a section type classified according to the laying environment or pipeline characteristics, reflecting the spatial constraints of pipeline laying, including:

[0189] Obstacle-sensitive section: areas close to above-ground pipe gallery foundations and underground cables;

[0190] Complex terrain section: mountainous steep slopes and marshy areas;

[0191] Crossing engineering section: areas that need to cross roads and rivers.

[0192] For example: in a certain initial scheme, the pipeline needs to pass through the 3-meter range outside the above-ground pipe gallery foundation, and the structure type of this section is "pipe gallery foundation sensitive section".

[0193] Type mapping and mapping pairs are (solution type, structure type) binary tuples generated by matching solution types and structure types according to their functions, serving as the basis for scheme improvement. The association is established through manually defined mapping rules or machine learning models (such as decision trees), for example: the solution type "non-excavation construction" is mapped to the structure type "pipe gallery foundation sensitive section", forming the mapping pair ("non-excavation construction", "pipe gallery foundation sensitive section").

[0194] Sub-recommendation arrangement schemes are specific pipe arrangement recommendations for each structure type in the initial scheme, including:

[0195] Pipeline routing coordinates and burial depth;

[0196] Crossing method (large excavation / pipe-jacking).

[0197] Pipe fixing method (support type, spacing).

[0198] For example: the sub-solution of the structure type "sensitive section of pipe gallery foundation" is "route along the outer side of the pipe gallery foundation 5 meters, buried depth 3.5 meters, and large excavation crossing is adopted."

[0199] The rule base is constructed to store the mapping rules of "structure type + solution type → adjustment method", such as: IF structure type = pipe gallery foundation sensitive section AND solution type = non-excavation construction class THEN crossing method = pipe jacking, using forward reasoning (from condition to result) or reverse reasoning (from target to condition) to match rules.

[0200] For example: there is a rule in the rule base: "if the structure type is'sensitive section of pipe gallery foundation' and the solution type is 'non-excavation construction class', then the crossing method is changed from large excavation to pipe jacking, and foundation settlement monitoring points are added."

[0201] The scheme fusion process is as follows: extract the mapping pair ("non-excavation construction class", "sensitive section of pipe gallery foundation"), find the matching rule in the rule base, adjust the original large excavation crossing to pipe jacking construction according to the rule, and add monitoring points, generating the improved sub-solution: "pipe jacking crossing, buried depth 4 meters (avoiding the foundation stress zone), and settlement monitoring points are set every 10 meters."

[0202] For example: the scenario background of sewage pipe laying improvement under urban roads:

[0203] Laying environment: there is a concrete pipe gallery on the ground (foundation buried depth 2 meters, range 10m×5m), and there is a power cable 1.5 meters underground;

[0204] Initial sub-solution: large excavation is adopted for the crossing road section, buried depth 3 meters, and distance from the pipe gallery foundation 2 meters (within the protection range).

[0205] The type mapping is the reserved problem-strategy pair: ("excavation within the protection range of the pipe gallery foundation causes cracks", "non-excavation pipe jacking + foundation reinforcement"), solution type: "non-excavation construction class" "foundation protection class", structure type: "sensitive section of pipe gallery foundation" (within 3 meters from the foundation); mapping pairs: ("non-excavation construction class", "sensitive section of pipe gallery foundation"), ("foundation protection class", "sensitive section of pipe gallery foundation"). At this time, the rule fusion algorithm is applied: rule base matching:

[0206] Rule 1: pipe gallery foundation sensitive section + non-excavation construction class → crossing method = pipe jacking;

[0207] Rule 2: pipe gallery foundation sensitive section + foundation protection class → buried depth ≥ 4 meters (2 meters below the foundation bottom surface);

[0208] Sub-scheme improvement:

[0209] Crossing mode: large excavation → micro tunneling (pipe jacking);

[0210] Buried depth: 3m → 4.2m (2m below the bottom surface of the pipe gallery foundation);

[0211] New measures: simultaneous foundation grouting reinforcement during pipe jacking construction.

[0212] Therefore, by type mapping, the solution logic of the historical strategy is applied to the current structure type, the rule fusion algorithm converts the scattered specification clauses into executable scheme adjustment rules, and through the combination of the historical problem-strategy pair and the current structure type, the risk prevention and control measures are injected in advance, compared with manual adjustment of the scheme, the method shortens the single pipe scheme improvement time through automatic mapping and rule fusion.

[0213] The application further provides an electronic device, including a processor, a sending device, an input device, an output device and a memory, the memory is used for storing computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes the method of any one of the above possible implementations.

[0214] The application further provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program includes program instructions, when the program instructions are executed by the processor of the electronic device, the processor executes the method of any one of the above possible implementations.

[0215] Please refer to Figure 2 , Figure 2 A hardware structure schematic diagram of an electronic device provided by the application is provided.

[0216] The electronic device 2 includes a processor 21, a memory 22, an input device 23 and an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are coupled through a connector, and the connector includes various interfaces, transmission lines or buses and the like, and the embodiments of the application are not limited thereto. It should be understood that in various embodiments of the application, coupling means mutual contact in a specific way, including direct connection or indirect connection through other devices, for example, various interfaces, transmission lines, buses and the like can be connected.

[0217] The processor 21 can be one or more graphics processing units (GPUs), which can be single-core GPUs or multi-core GPUs. Alternatively, the processor 21 can be a processor group composed of multiple GPUs, and the multiple processors are coupled with each other through one or more buses. Alternatively, the processor can be other types of processors, and the embodiments of the present application are not limited thereto.

[0218] The memory 22 can be used to store computer program instructions, and various computer program codes for executing the schemes of the present application. Alternatively, the memory includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read only memory (EPROM), or a compact disc read-only memory (CD-ROM), which is used for relevant instructions and data.

[0219] The input device 23 is used to input data and / or signals, and the output device 24 is used to output data and / or signals. The input device 23 and the output device 24 can be independent devices, or can be an integral device.

[0220] It can be understood that, in the embodiments of the present application, the memory 22 can be used to store relevant instructions, and the embodiments of the present application are not limited to the data stored in the memory.

[0221] It can be understood that, Figure 2 Only a simplified design of an electronic device is shown. In actual applications, the electronic device can also include other necessary elements, including but not limited to any number of input / output devices, processors, memories, etc., and all video analysis devices that can implement the embodiments of the present application are within the protection scope of the present application.

[0222] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0223] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. Those skilled in the art can also clearly understand that each embodiment of the present application describes each with emphasis, and for the convenience and brevity of description, the same or similar parts in different embodiments can not be repeated, and therefore, the parts not described or not described in detail in an embodiment can be referred to the description of other embodiments.

[0224] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. For example, the device embodiments described above are only schematic, and for the convenience of description, the division of the units is only a logical function division, and there can be another division way in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0225] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0226] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0227] In the above embodiments, all or part of the methods can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the methods can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (such as a coaxial cable, an optical fiber, a digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0228] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be instructed by a computer program to relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium includes a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A method for recommending buried pipeline layout based on artificial intelligence, characterized in that, The method includes: Collect the current laying environment of the buried pipeline, the purpose of the buried pipeline construction, and obtain the specific parameters of a single type of pipeline applied to the current buried pipeline, and convert them into an input vector; The input vector is fed into a pre-trained buried pipeline layout recommendation model to obtain an initial recommended layout scheme; The project identifies new historical problems and solutions for each historical pipeline project during the pipeline deployment process, forming several problem-strategy pairs. A hierarchical clustering algorithm is then used to perform cluster analysis on the problem-strategy pairs under all historical pipeline projects. The similarity between the current buried pipeline laying environment and the buried pipeline construction purpose and each historical pipeline laying project is calculated based on the autoencoder similarity algorithm. Retain the problem-strategy pairs of historical routing projects with a similarity greater than or equal to the preset level; Each historical deployment project with a similarity less than a preset degree is determined based on the distribution probability in all cluster analysis results, and the central cluster of the cluster analysis result corresponding to the maximum number of problem-strategy pairs involved in each cluster analysis result of the historical deployment project with the highest probability in the distribution probability is retained; Based on all the layout improvement types of the retained results, the initial recommended layout scheme is improved.

2. The method for recommending buried pipeline layout based on artificial intelligence according to claim 1, characterized in that, The laying environment includes the topography, above-ground attachments, and underground obstacles of each individual pipeline section; The specific parameters include: pipe specifications, pipe material, and pipe weight; The improved layout scheme includes: the pipe laying sequence of each individual pipe section, the starting pipe laying position, and the pipe laying auxiliary methods for each pipe section. The pipe laying auxiliary methods include: buried pipe channel transportation method, hoisting equipment auxiliary method, pulley block method, and / or pipe jacking construction method.

3. The method for recommending buried pipeline layout based on artificial intelligence according to claim 2, characterized in that, Convert to an input vector, including: Numerical standardization processing is performed on the numerical data involved in the laying environment, the purpose of buried pipeline construction, and specific parameters. Encode non-numerical data; The transformation results for the laying environment, the purpose of buried pipeline construction, and the specific parameters are extracted from the numerical standardization and coding results, respectively, and then combined and sorted in order to obtain the input vector.

4. The method for recommending buried pipeline layout based on artificial intelligence according to claim 1, characterized in that, The similarity between the current buried pipeline's laying environment and construction purpose and each historical pipeline laying project is calculated based on an autoencoder similarity algorithm, including: The first and second characteristics of the current buried pipeline laying environment and the buried pipeline construction purpose are obtained respectively. At the same time, the standard combination characteristics of the historical pipeline laying projects and the result combination characteristics after project implementation are obtained. Calculate the first Euclidean distance between the first and second representations and the standard combined representation; Calculate the second Euclidean distance between the first representation and the second representation and the combined representation of the result; Simultaneously, the third Euclidean distance between the standard combination representation and the result combination representation is calculated; If the absolute difference between the first Euclidean distance and the second Euclidean distance is less than the third Euclidean distance, determine the average value of the third Euclidean distance and the absolute difference between the two distances, and take the result of the ratio of the average value to the maximum preset distance as the similarity. Otherwise, the similarity is determined by the ratio of the average distance between the first and second Euclidean distances (1 - the first Euclidean distance and the second Euclidean distance) to the maximum preset distance.

5. The method for recommending buried pipeline layout based on artificial intelligence according to claim 1, characterized in that, Before determining the distribution probability of historical pipeline projects with similarity less than a preset value in all cluster analysis results, the following steps are also included: For each historical deployment project with a similarity less than the preset value, the problem-strategy pair is marked with significance in the cluster analysis results, and the first number in each cluster analysis result is counted; Calculate the first ratio between the first quantity and the total number of problem-strategy pairs involved in the corresponding cluster analysis results; Calculate the sum of all first ratios, and extract the largest ratio from all first ratios; Sort the sums and maximum ratios of all historical pipe laying projects with similarity less than the preset value in descending order, and construct a two-dimensional array, where each value occupies one cell; Calculate the first average of the absolute values ​​of the differences between two adjacent sums in the row array related to the sum in the second array, and calculate the second ratio of the first average to the average of all first quantities under the corresponding historical pipeline projects, as the second average. Calculate the third average of the absolute values ​​of the differences between two adjacent maximum ratios in the row array related to the maximum ratio in the second array; If the second average is greater than or equal to the third average, determine the third ratio of the second average to the third average, and at the same time, determine the fourth ratio of the absolute value of the difference between two adjacent sums to the second average. Round down the product of the third and fourth ratios and insert blank cells in the middle of the corresponding two adjacent sums, matching the rounded result. Update the index of the rows in the array where blank cells are inserted; Based on the total number of blank cells inserted into the row array after the sequence number is updated, starting with one blank cell, the row arrays related to the corresponding maximum ratio are cyclically inserted one blank cell from the middle of adjacent maximum ratios until the number of insertions matches the total number. Then, the insertion stops, and the sequence number is updated. Otherwise, leave the two-dimensional array unchanged.

6. The method for recommending buried pipeline layout based on artificial intelligence according to claim 5, characterized in that, Determine the distribution probability of each historical pipe laying project with a similarity less than a preset value in all cluster analysis results, including: Extract each historical pipe laying project with a similarity less than the preset value from the final array, based on the first index of the first row and the second index of the second row; The result of 1 - (first serial number + second serial number) / (2 × total serial number) is taken as the corresponding probability distribution.

7. The method for recommending buried pipeline layout based on artificial intelligence according to claim 1, characterized in that, Based on all retained layout improvement types, the initial recommended layout scheme is improved, including: Map the solution type of each problem-policy pair in all retained results to the structure type of each individual pipeline in the initial recommended layout scheme to obtain the mapping pair for each individual pipeline. The mapping pairs are fused with the sub-recommended layout schemes of each individual pipeline based on the rule fusion algorithm to improve the scheme.

8. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the buried pipeline laying recommendation method based on artificial intelligence as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the artificial intelligence-based buried pipeline layout recommendation method according to any one of claims 1 to 7.

Images