CN115204688A - Comprehensive evaluation method for health of drainage system - Google Patents
Comprehensive evaluation method for health of drainage system Download PDFInfo
- Publication number
- CN115204688A CN115204688A CN202210844960.0A CN202210844960A CN115204688A CN 115204688 A CN115204688 A CN 115204688A CN 202210844960 A CN202210844960 A CN 202210844960A CN 115204688 A CN115204688 A CN 115204688A
- Authority
- CN
- China
- Prior art keywords
- rainwater
- dimension
- drainage system
- pollution
- sewage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 93
- 230000036541 health Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000007547 defect Effects 0.000 claims abstract description 39
- 238000011161 development Methods 0.000 claims abstract description 31
- 238000011160 research Methods 0.000 claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims abstract description 18
- 239000010865 sewage Substances 0.000 claims description 93
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 45
- 238000013527 convolutional neural network Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 18
- 230000008595 infiltration Effects 0.000 claims description 16
- 238000001764 infiltration Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000008020 evaporation Effects 0.000 claims description 15
- 238000001704 evaporation Methods 0.000 claims description 15
- 238000004088 simulation Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 239000003344 environmental pollutant Substances 0.000 claims description 5
- 231100000719 pollutant Toxicity 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000005065 mining Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009991 scouring Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Water Supply & Treatment (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Sewage (AREA)
Abstract
A comprehensive evaluation method for the health of a drainage system belongs to the crossing field of municipal engineering, environmental engineering and computer technology. The invention aims to solve the problem that the existing method for evaluating the health of the drainage system is only limited to evaluating the physical damage condition of a drainage pipe network, so that the evaluation accuracy is low. According to the method, the indexes for evaluating the health of the urban drainage system are obtained by deep learning, mining and modeling multi-source data of a research object such as weather, remote sensing, elevation, pipe network and exploration, and the comprehensive weight of each index is calculated, so that the health degree of the drainage system is reflected. The invention has 20 indexes in total from five evaluation dimensions, namely an internal defect dimension, a development scale dimension, a rainwater trend dimension, a facility running state dimension and a pollution discharge dimension. The method is mainly used for comprehensively evaluating the health of the urban drainage system.
Description
Technical Field
The invention belongs to the crossing field of municipal engineering, environmental engineering and computer technology.
Background
The drainage system is an important component of urban infrastructure, carries functions of collecting, conveying, treating and discharging rain sewage and preventing flood and draining waterlogging in cities, is an underground life line of the cities, and is closely related to urban safety and human living environment. Along with the development of the urbanization process, the load of an urban drainage system is gradually increased, for example, the increase of population leads to the rapid increase of domestic sewage discharge, the construction of an urban hardened ground leads to the increase of rainwater runoff rate and the like, and the problems of drainage pipe network loss, pollution discharge increase and the like are caused. In the process, how to measure the health degree of the urban drainage system and put forward reasonable construction opinions becomes an important problem for guiding the development of cities.
The traditional method for evaluating the health degree of the drainage system mainly analyzes the damage degree and the disease degree of a pipe network according to images and detection data obtained by pipe network detection equipment and an underwater detection instrument. The methods can visually reflect the health degree of the pipe network, but due to the applicability problem of the detection instrument, the images of the small-diameter pipe sections are difficult to directly detect, and need to be evaluated from other aspects. In fact, the health problem of the drainage system is not limited to the physical damage condition of the drainage pipe network, and the operation condition, the pollutant discharge and overflow condition, the collection coverage range of the drainage system and the like are all factors influencing the health of the drainage system. Therefore, the damage evaluation of the drainage system in the traditional sense cannot be completely applied to the health analysis of the drainage system, and a comprehensive and comprehensive drainage system health evaluation system and method are urgently needed to guide the development of the urban drainage system.
Disclosure of Invention
The invention aims to solve the problem that the existing method for evaluating the health of a drainage system is only limited to evaluating the physical damage condition of a drainage pipe network, so that the evaluation accuracy is low.
The comprehensive evaluation method for the health of the drainage system evaluates the health of the drainage system through five evaluation dimensions, and comprises the following specific processes:
s1, obtaining five evaluation dimensions which are respectively an internal defect dimension, a development scale dimension, a rainwater converging and diverging dimension, a facility running state dimension and a pollution discharge dimension; the five evaluation dimensions comprise 20 indexes in total;
the internal defect dimensionality comprises 3 indexes which are respectively a pipe section breakage rate, a pipe section siltation rate and a pipe network rain and sewage mixed connection rate;
the development scale dimension comprises 4 indexes which are respectively the density of a drainage pipe network, the processing capacity of a sewage treatment plant, the collection range rate of a rainwater pipe network and the collection range rate of a sewage pipe network;
the rain water convergence dimension comprises 4 indexes which are respectively rain water infiltration rate, rain water runoff rate, rain water storage rate and rain water evaporation rate;
the facility operation state dimension comprises 5 indexes which are respectively the overload operation time of the sewage plant in a unit evaluation period, the total overload time of the pipe sections in the unit evaluation period, the total overload water inflow of the sewage plant in the unit evaluation period, the total overload time of the pipe sections in the unit evaluation period and the total overflow water of the nodes in the unit evaluation period;
the pollution discharge dimension comprises 5 indexes which are the total pollution amount of the rainfall runoff, the total pollution discharge amount of the discharge outlet, the total combined overflow pollution amount and the direct sewage discharge proportion of the unit rainfall;
s2, carrying out subjective weight weighting on each index by utilizing an analytic hierarchy process to obtain a subjective weight A of each index i Meanwhile, the objective weight W of each index is obtained by an entropy method i (ii) a Wherein, A i Is the subjective weight of the ith index, W i Is the objective weight of the ith index, i is an integer;
s3, subjective weight A according to each index i And objective weight W i Obtaining the comprehensive weight psi of each index i (ii) a Then according to the comprehensive weight psi of each index i And the actual value Q of the index i Obtaining a comprehensive evaluation result E of the health of the drainage system;
therein, Ψ i Is the integrated weight of the i-th index, Q i Is the actual value of the ith index.
Preferably, in step S1, the implementation manner of obtaining the internal defect dimension includes:
s11-1, constructing a convolutional neural network model based on an exploration image;
s11-2, analyzing internal defects of the drainage pipe network through the constructed convolutional neural network model based on the exploration image, and thus obtaining the pipe section breakage rate, the pipe section siltation rate and the pipe network rain and sewage mixed connection rate in the internal defect dimensionality.
Preferably, the step S11-1 of constructing the convolutional neural network model based on the exploration image is implemented by:
s11-1-1, acquiring a sample set with autonomous labels according to an actual exploration image of a drainage pipe network, wherein the label types are divided into three types, namely pipeline damage, pipeline silting and pipeline mixed connection;
and S11-1-1, training and verifying the deep learning convolutional neural network by using a sample set to obtain the trained deep learning convolutional neural network, and taking the trained deep learning convolutional neural network as a convolutional neural network model based on the exploration image.
Preferably, in the step S11-2, the built convolutional neural network model based on the exploration image is used to analyze the internal defect of the drainage pipe network, so as to obtain the pipe segment breakage rate, the pipe segment siltation rate and the pipe network rain and sewage misconnection rate in the internal defect dimension, in an implementation manner:
preferably, in step S1, the implementation of obtaining the development scale dimension includes:
s12-1, acquiring the density of a drainage pipe network and the treatment capacity of a sewage treatment plant in a development scale dimension by researching regional drainage pipe network data;
s12-2, collecting remote sensing images of the research area, classifying and labeling land use types in partial images of the remote sensing images of the research area, wherein the number of labeled samples of each type of land use type is more than 50, and forming a sample set; wherein the classification result of the land use type includes a high-rise building, a low-rise building, an industrial building, a lake, a river, a forest land, a green land, a bare land and a road; the shape of the sample in the sample set is a polygon;
s12-3, classifying the land utilization type in the remote sensing image of the research area by a supervision classifier in the remote sensing image processing platform ENVI according to the sample set to obtain the classified remote sensing image;
s12-4, correcting the digital elevation of partial land use type DEM in the classified remote sensing images by using a geographic information platform, keeping the digital elevation of the rest land use type DEM unchanged, and obtaining the corrected remote sensing images;
the corrected partial land utilization type DEM digital elevation comprises elevation a of a high-rise building, elevation b of a low-rise building, elevation c of an industrial building and elevation d of a road; and a, b and c are positive values, d is a negative value;
s12-4, based on a D8 flow direction algorithm, carrying out catchment area division on the corrected remote sensing image on a geographic information platform, loading drainage pipe network data, and calculating the rainwater pipe network collection range rate and the sewage pipe network collection range rate in the development scale dimension by taking whether rainwater/sewage pipe sections exist in the catchment area range in the corrected remote sensing image as a standard, so that all indexes in the development scale dimension are obtained.
Preferably, the implementation manner of obtaining the rainwater pipe network collection range rate and the sewage pipe network collection range rate in the step S12-4 is as follows:
preferably, in step S1, the implementation manner of obtaining the rainwater homing dimension, the facility operating state dimension and the pollution discharge dimension includes:
s13-1, constructing a drainage system model based on drainage pipe network data;
s13-2, obtaining a rainwater trend dimension, a facility running state dimension and a pollution discharge dimension according to the constructed drainage system model.
Preferably, the step S13-2 of obtaining the rainwater trend-oriented dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, carrying out hydrological and hydraulic calculation on each catchment area by the drainage system model operating the received rainfall data, obtaining rainwater converging and converging data of each catchment area corresponding to a drainage pipe network of a research area, and carrying out comprehensive statistics according to rainwater converging and converging dimensions of all catchment areas to obtain rainwater converging and converging dimensions of the research area;
the rainwater convergence data of each catchment area comprises rainwater infiltration depth h 1k Rainwater evaporation depth h 2k Rainwater storage depth h 3k Depth of runoff of rainwater h 4k ；
Wherein,
the expression of the rainwater infiltration rate in the dimension of the rainwater convergence is as follows:
and is provided with
H 1 In order to study the rainwater infiltration rate of the area, k is the number of the catchment area, k =1,2,3 \8230, k 8230, q, k and q are integers, and S k Is the area of the kth catchment area, h 1k The rainwater infiltration depth of the kth catchment area, S is the total area of a research area, and Precipitation is the total rainfall;
the expression of the rain evaporation rate in the return dimension of rain is:
and is
H 2 To study the depth of rainwater evaporation in the area, h 2k Is the rainwater evaporation depth of the kth catchment area;
the expression of the rainwater storage rate in the rainwater trend dimension is as follows:
and is
H 3 For investigating the rainwater storage depth of the area, h 3k The rainwater storage depth of the kth catchment area;
the expression for the rain runoff rate in the rain trend dimension is:
and is
H 4 To study the depth of runoff of rainwater in an area, h 4k The runoff depth of the rainwater in the kth catchment area;
in the step S13-2, the implementation manner of obtaining the facility operation state dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, and performing hydraulic calculation on a drainage pipe network by using the rainfall data received by the operation of the drainage system model to obtain the water inlet flow of a sewage plant at each moment, the fullness of each pipe section at each moment and the overflow flow of a connecting node of each pipe section at each moment so as to obtain the facility operation state dimension;
the implementation mode for obtaining the facility running state dimension comprises the following steps:
overload operation time of the sewage plant in a unit evaluation period: comparing the water inlet flow of the sewage plant with the preset water inlet flow of the sewage plant at each moment, counting the total time which is longer than the water inlet flow of the preset sewage plant in a unit evaluation period, and taking the total time as the overload operation time of the sewage plant in the unit evaluation period;
total overload time of pipe sections in unit evaluation period: comparing the fullness of each pipe section at each moment with a preset fullness, counting the total time greater than the preset fullness in a unit evaluation period, and taking the total time as the total overload time of the pipe sections in the unit evaluation period;
the overload total water inflow of the sewage plant in a unit evaluation period is as follows: the sum of the overflow flows of all pipe section connecting nodes at each moment in the unit evaluation period is counted and used as the overload total water inflow of the sewage plant in the unit evaluation period;
in the step S13-2, the implementation mode of obtaining the pollution discharge dimension according to the constructed drainage system model comprises the following steps:
inputting rainfall data in a simulation time period into a drainage system model, operating the drainage system model to receive the rainfall data, taking each catchment area and a drainage pipe network corresponding to the catchment area as a calculation unit, calculating by using a one-dimensional water quality diffusion-plug flow formula, obtaining data of water quality pollution concentration output by the drainage pipe network changing along with time sequence, and obtaining pollution discharge dimensionality according to the data of the water quality pollution concentration output by the drainage pipe network changing along with time sequence;
wherein, the data that the water quality pollution concentration changes along with time series include:
the pollution concentration of the rainwater runoff of each rainwater discharge port at each moment and the runoff flow rate corresponding to the rainwater discharge port;
the pollution concentration of the rainwater discharge port of each rainwater discharge port at each moment and the discharge port flow rate corresponding to the rainwater discharge port;
the combined overflow pollution concentration of each pipe section node at each moment and the node overflow flow rate corresponding to the pipe section node;
the pollution concentration of each sewage discharge port at each moment and the flow of the sewage discharge port;
the pollution concentration of each catchment area at each moment and the pollution discharge flow rate corresponding to the catchment area;
the implementation manner for obtaining the pollutant emission dimension comprises the following steps:
the total rainwater runoff pollution amount is the sum of the rainwater runoff pollution amount of each rainwater discharge port at all times, and the rainwater runoff pollution amount of each rainwater discharge port at each time is the product of the rainwater runoff pollution concentration of each rainwater discharge port at the time and the corresponding runoff flow of the rainwater discharge port;
the total pollution discharge amount of the discharge ports is the sum of the pollution amount of the rainwater discharge ports of all the rainwater discharge ports at all times, and the pollution amount of the rainwater discharge ports of each rainwater discharge port at each time is the product of the pollution concentration of the rainwater discharge ports of each rainwater discharge port at the time and the flow of the discharge ports corresponding to the rainwater discharge ports;
the total amount of combined overflow pollution is the combined overflow pollution amount of each pipe section node at all times, and the combined overflow pollution amount of each pipe section node at each time is the product of the combined overflow pollution concentration of each pipe section node at the time and the node overflow flow corresponding to the pipe section node;
the sewage straight discharge amount is the sum of the pollution amount of each sewage discharge port at all moments, and the pollution amount of each sewage discharge port at each moment is the product of the pollution concentration of each sewage discharge port at the moment and the flow of the sewage discharge port; the total sewage generation amount is the sum of the pollution amount of each catchment area at all times, and the pollution amount of each catchment area at each time is the product of the pollution concentration of each catchment area at the time and the pollution discharge flow corresponding to the catchment area.
Preferably, in S2, the objective weight W of each index is obtained by an entropy method i The implementation mode of the method is as follows:
using entropy values E of individual indicators i Obtaining objective weights W of the corresponding indexes i Wherein, in the process,
m is the total number of indices, P ij Is the value of the j-th repetition of the i-th index, E i Is the entropy value of the ith index, n is the total repeated number, j is an integer, j =1,2,3 \8230, n.
Preferably, in S3,
Ψ i Is the comprehensive weight of the ith index, m is an integer, and i =1,2,3 \8230, m is 8230.
With the proposition and gradual popularization of the concept of smart city, the scale and data volume of big data of a city drainage system, such as city underlying surface remote sensing image data, drainage system exploration image data, drainage system monitoring data, drainage facility structure operation data and the like, gradually meet the requirement of intelligent analysis.
Under the support of big data of a drainage pipe network, the invention provides a comprehensive evaluation method for the health of a drainage system based on the coupling of multi-source data deep learning and a model method, which is mainly used for evaluating the comprehensive index of the urban drainage system, and comprehensively considering the health of the urban drainage system from the single dimension of the traditional internal defect to five dimensions of internal defect, development scale, rainwater tendency, facility operation state and pollution discharge, thereby effectively solving the defects that the traditional drainage system has a single evaluation mode, and a small-pipe-diameter pipe section cannot be brought into an evaluation system, and the like, and further providing a reasonable proposal for the development planning of the drainage system.
The invention has the following beneficial effects:
the invention provides a comprehensive evaluation method for the health of a drainage system based on the coupling of multi-source data deep learning and a model method. The core effects of the invention are mainly embodied in the following three points:
(1) In view of the fact that the traditional evaluation index system is single and does not meet the application of a small-pipe-diameter drainage pipe network, the comprehensive evaluation system for the health of the urban drainage system can comprehensively evaluate five different dimensions of internal defects, development scale, rainwater tendency, facility running state and pollution discharge, and is comprehensive in evaluation range and high in practicability;
(2) The method comprises the steps of image identification based on a convolutional neural network, land utilization type identification based on supervision and classification, a drainage system model constructed based on drainage pipe network data and index weight calculation based on an analytic hierarchy process and an entropy weight method. The method can clearly guide the calculation process of each index in detail and ensure that a correct evaluation result is obtained;
(3) Compared with the traditional manual identification technology, the efficiency of the method is improved by more than 30 times.
Drawings
FIG. 1 is a schematic diagram illustrating the principle of the comprehensive evaluation method for the health of the drainage system according to the present invention;
FIG. 2 is a schematic diagram of a comprehensive health evaluation system of the J county drainage system;
fig. 3 is a remote sensing image supervision classification from 2009 to 2020 by a J-county drainage system;
fig. 4 shows DEM correction and catchment area division in the J county drainage system 2020.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive efforts based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Example 1:
referring to fig. 1, the embodiment of the comprehensive evaluation method for health of a drainage system according to the embodiment of the invention evaluates the health of the drainage system through five evaluation dimensions, and comprises the following specific steps:
s1, obtaining five evaluation dimensions which are respectively an internal defect dimension, a development scale dimension, a rainwater trend dimension, a facility running state dimension and a pollution discharge dimension; the five evaluation dimensions comprise 20 indexes;
the internal defect dimensionality comprises 3 indexes which are respectively a pipe section breakage rate, a pipe section siltation rate and a pipe network rain and sewage mixed connection rate;
the development scale dimension comprises 4 indexes, namely the density of a drainage pipe network, the processing capacity of a sewage treatment plant, the collection range rate of a rainwater pipe network and the collection range rate of a sewage pipe network;
the rainwater converging and diverging dimension comprises 4 indexes which are respectively the rainwater infiltration rate, the rainwater runoff rate, the rainwater storage rate and the rainwater evaporation rate;
the facility operation state dimension comprises 5 indexes which are respectively the overload operation time of the sewage plant in a unit evaluation period, the total overload time of the pipe sections in the unit evaluation period, the total overload water inflow of the sewage plant in the unit evaluation period, the total overload time of the pipe sections in the unit evaluation period and the total overflow water of the nodes in the unit evaluation period;
the pollution discharge dimension comprises 5 indexes which are the total pollution amount of the rainfall runoff, the total pollution discharge amount of the discharge outlet, the total combined overflow pollution amount and the direct sewage discharge proportion of the unit rainfall;
s2, carrying out subjective weight weighting on each index by utilizing an analytic hierarchy process to obtain a subjective weight A of each index i Meanwhile, the objective weight W of each index is obtained by an entropy method i (ii) a Wherein A is i Is the subjective weight of the ith index, W i Objective weight of ith indexHeavy, i is an integer;
s3, subjective weight A according to each index i And objective weight W i Obtaining the comprehensive weight psi of each index i (ii) a Then according to the comprehensive weight psi of each index i And the actual value Q of the index i Obtaining a comprehensive evaluation result E of the health of the drainage system;
therein, Ψ i Is the integrated weight, Q, of the ith index i Is the actual value of the ith index.
The embodiment provides a comprehensive evaluation method for the health of a drainage system based on the coupling of multi-source data deep learning and a model method, which is mainly used for evaluating the comprehensive indexes of the urban drainage system, and comprehensively considering five dimensions of the health of the urban drainage system from the single dimension of the internal defect to the internal defect, the development scale, the return of rainwater, the facility running state and pollution discharge, so that the problem of low evaluation accuracy caused by the fact that the traditional drainage system has a single evaluation mode and a small-diameter pipe section cannot be included in an evaluation system is effectively solved, the health of the urban drainage system is evaluated according to 20 indexes in total in five dimensions during application, and the comprehensive health index is calculated according to the weight, so that the health degree of the drainage system is reflected.
Further, in step S1, an implementation manner of obtaining the dimension of the internal defect includes:
s11-1, constructing a convolutional neural network model based on an exploration image;
s11-2, analyzing internal defects of the drainage pipe network through the constructed convolutional neural network model based on the exploration image, and thus obtaining the pipe section breakage rate, the pipe section siltation rate and the pipe network rain and sewage mixed connection rate in the internal defect dimensionality.
In this preferred embodiment, the process of obtaining the implementation of internal defect dimension compares in traditional manual analysis, and degree of automation promotes, can realize the analysis of pipeline internal defect problem fast high-efficiently.
Furthermore, in the step S11-1, the convolutional neural network model based on the exploration image is constructed in an implementation manner as follows:
s11-1-1, obtaining a sample set with autonomous labels according to an actual exploration image of a drainage pipe network, wherein the label types are divided into three types, namely pipeline damage, pipeline silting and pipeline mixed connection;
s11-1-1, training and verifying the deep learning convolutional neural network by using a sample set to obtain the trained deep learning convolutional neural network, and taking the trained deep learning convolutional neural network as a convolutional neural network model based on an exploration image.
In the preferred embodiment, training and verification of the deep learning convolutional neural network by using the sample set can be realized by the prior art, and the actual picture is identified after the requirements are met by taking the Kappa coefficient and the interaction ratio as the precision judgment standard in the verification process.
Furthermore, in the step S11-2, the built convolutional neural network model based on the exploration image is used to analyze the internal defect of the drainage pipe network, so as to obtain the pipe segment breakage rate, the pipe segment siltation rate and the pipe network rain and sewage mixed joint rate in the internal defect dimension, which are implemented in the following manner:
further, in step S1, an implementation manner of obtaining the development scale dimension includes:
s12-1, acquiring the density of a drainage pipe network and the treatment capacity of a sewage treatment plant in a development scale dimension by researching regional drainage pipe network data;
s12-2, collecting remote sensing images of the research area, classifying and labeling land use types in partial images of the remote sensing images of the research area, wherein the number of labeled samples of each type of land use type is more than 50, and forming a sample set; wherein the classification result of the land use type includes a high-rise building, a low-rise building, an industrial building, a lake, a river, a forest land, a green land, a bare land and a road; the shape of the sample in the sample set is a polygon;
s12-3, classifying the land utilization type in the remote sensing image of the research area by a supervision classifier in the remote sensing image processing platform ENVI according to the sample set to obtain the classified remote sensing image;
s12-4, correcting the digital elevation of partial land use type DEM in the classified remote sensing images by using a geographic information platform, keeping the digital elevation of the rest land use type DEM unchanged, and obtaining the corrected remote sensing images;
the corrected partial land utilization type DEM digital elevation comprises elevation a of a high-rise building, elevation b of a low-rise building, elevation c of an industrial building and elevation d of a road; and a, b and c are positive values, d is a negative value;
s12-4, based on a D8 flow direction algorithm, carrying out catchment area division on the corrected remote sensing image on a geographic information platform, loading drainage pipe network data, and calculating the rainwater pipe network collection range rate and the sewage pipe network collection range rate in the development scale dimension by taking whether rainwater/sewage pipe sections exist in the catchment area range in the corrected remote sensing image as a standard, so that all indexes in the development scale dimension are obtained.
The preferred embodiment can use geographic information data to perform quantitative calculation on the development dimension index in the process of obtaining the implementation of the development scale dimension.
Furthermore, the implementation manner of obtaining the rainwater pipe network collection range rate and the sewage pipe network collection range rate in the step S12-4 is as follows:
furthermore, in step S1, the implementation manner of obtaining the rainwater trend dimension, the facility operation state dimension, and the pollution discharge dimension includes:
s13-1, constructing a drainage system model based on drainage pipe network data;
s13-2, obtaining a rainwater converging and diverging dimension, a facility running state dimension and a pollution discharge dimension according to the constructed drainage system model.
In the preferred embodiment, the indexes of the return and trend of the rainwater, the running state and the pollution concentration are quantitatively calculated in detail through model calculation, so that a sufficient data basis is provided for the health evaluation of the drainage system. Further, in the step S13-2, according to the constructed drainage system model, the implementation manner of obtaining the rainwater trend-oriented dimension includes:
inputting rainfall data in a simulation time period into a drainage system model, carrying out hydrological and hydraulic calculation on each catchment area by the drainage system model operating the received rainfall data, obtaining rainwater converging and converging data of each catchment area corresponding to a drainage pipe network of a research area, and carrying out comprehensive statistics according to rainwater converging and converging dimensions of all catchment areas to obtain rainwater converging and converging dimensions of the research area;
the rainwater trend-return data of each catchment area comprise rainwater infiltration depth h 1k Rainwater evaporation depth h 2k Rainwater storage depth h 3k Rainwater runoff depth h 4k ；
Wherein,
the expression of the rainwater infiltration rate in the rainwater trend dimension is as follows:
and is
H 1 To investigate the rain infiltration rate, H, of the area 1 Has the unit of mm, k is the number of catchment area, k =1,2,3 \8230, q, k and q are integers, S k Is the area of the kth catchment area, h 1k The rainwater infiltration depth of the kth catchment area, S is the total area of a research area, and Precipitation is the total rainfall;
the expression of the rain water evaporation rate in the rain water return-trend dimension is as follows:
and is
H 2 To study the depth of rainwater evaporation in the area, H 2 In units of mm, h 2k Is the rainwater evaporation depth of the kth catchment area;
the expression of the rainwater storage rate in the rainwater converging dimensionality is as follows:
and is provided with
H 3 For investigating the depth of rainwater storage in an area, H 3 In units of mm, h 3k The rainwater storage depth of the kth catchment area;
the expression for the rain runoff rate in the rain trend dimension is:
and is
H 4 To study the depth of runoff of rainwater in an area, H 4 In units of mm, h 4k The rainwater runoff depth of the kth catchment area;
in the step S13-2, the implementation manner of obtaining the facility operation state dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, and performing hydraulic calculation on a drainage pipe network by the aid of the rainfall data received by operation of the drainage system model to obtain inflow of a sewage plant at each moment, fullness of each pipe section at each moment and overflow flow of a connecting node of each pipe section at each moment so as to obtain facility operation state dimensionality;
the implementation mode for obtaining the facility running state dimension comprises the following steps:
overload running time (h) of the sewage plant in a unit evaluation period: comparing the water inlet flow of the sewage plant with the preset water inlet flow of the sewage plant at each moment, counting the total time which is longer than the water inlet flow of the preset sewage plant in a unit evaluation period, and taking the total time as the overload operation time of the sewage plant in the unit evaluation period;
total overload time (h) of pipe sections in unit evaluation period: comparing the fullness of each pipe section at each moment with a preset fullness, counting the total time greater than the preset fullness in a unit evaluation period, and taking the total time as the total overload time of the pipe sections in the unit evaluation period;
overload total inflow (m) of sewage plant in unit evaluation period 3 ): the sum of the overflow flows of all pipe section connecting nodes at each moment in the unit evaluation period is counted and used as the overload total water inflow of the sewage plant in the unit evaluation period;
in the step S13-2, the implementation manner of obtaining the pollution discharge dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, operating the drainage system model to receive the rainfall data, taking each catchment area and a drainage pipe network corresponding to the catchment area as a calculation unit, calculating by using a one-dimensional water quality diffusion-plug flow formula, obtaining data of water quality pollution concentration output by the drainage pipe network changing along with time sequence, and obtaining pollution discharge dimensionality according to the data of the water quality pollution concentration output by the drainage pipe network changing along with time sequence;
wherein, the data that the water quality pollution concentration changes along with time series include:
the pollution concentration of the rainwater runoff of each rainwater discharge port at each moment and the runoff flow rate corresponding to the rainwater discharge port;
the pollution concentration of the rainwater discharge port of each rainwater discharge port at each moment and the discharge port flow rate corresponding to the rainwater discharge port;
the combined overflow pollution concentration of each pipe section node at each moment and the node overflow flow rate corresponding to the pipe section node;
the pollution concentration of each sewage discharge port at each moment and the flow of the sewage discharge port;
the pollution concentration of each catchment area at each moment and the pollution discharge flow rate corresponding to the catchment area;
the implementation manner for obtaining the pollutant emission dimension comprises the following steps:
the total rainwater runoff pollution amount is the sum of the rainwater runoff pollution amount of each rainwater discharge port at all times, and the rainwater runoff pollution amount of each rainwater discharge port at each time is the product of the rainwater runoff pollution concentration of each rainwater discharge port at the time and the corresponding runoff flow of the rainwater discharge port;
the total pollution discharge amount of the discharge ports is the sum of the pollution amount of the rainwater discharge ports of all the rainwater discharge ports at all times, and the pollution amount of the rainwater discharge ports of each rainwater discharge port at each time is the product of the pollution concentration of the rainwater discharge port of each rainwater discharge port at the time and the flow of the discharge port corresponding to the rainwater discharge port;
the total amount of combined overflow pollution is the combined overflow pollution amount of each pipe section node at all times, and the combined overflow pollution amount of each pipe section node at each time is the product of the combined overflow pollution concentration of each pipe section node at the time and the node overflow flow corresponding to the pipe section node;
the sewage straight discharge amount is the sum of the pollution amount of each sewage discharge port at all moments, and the pollution amount of each sewage discharge port at each moment is the product of the pollution concentration of each sewage discharge port at the moment and the flow of the sewage discharge port; the total sewage generation amount is the sum of the pollution amount of each catchment area at all times, and the pollution amount of each catchment area at each time is the product of the pollution concentration of each catchment area at the time and the pollution discharge flow corresponding to the catchment area.
When the device is specifically applied, the unit kg/mm of the total pollution amount of the rainfall runoff is unit kg/mm, the unit kg of the total pollution amount of the rainfall runoff is unit mm, the unit kg/mm of the total pollution discharge amount of the discharge outlet of the rainfall is unit kg/mm, the unit kg/mm of the total pollution discharge amount of the discharge outlet is unit kg, the unit kg/mm of the total pollution discharge amount of the combined overflow of the rainfall is unit kg/mm, and the unit kg of the total pollution amount of the combined overflow is unit kg.
Further, in S2, objective weight W of each index is obtained by an entropy method i The implementation mode of the method is as follows:
using entropy values E of individual indices i Obtaining objective weights W of the corresponding indexes i Wherein，
m is the total number of indices, P ij Is the value of the j-th repetition of the i-th index, E i Is the entropy value of the ith index, n is the total repeated number, j is an integer, j =1,2,3 \8230, n.
Further, in S3,
Ψ i Is the comprehensive weight of the ith index, m is an integer, and i =1,2,3 \8230, m is 8230.
The technical effects of the invention are illustrated by verification tests:
the method is successfully applied to comprehensive evaluation of the health of the annual drainage system in J county of a certain province from 2011 to 2010 for ten years, is used for analyzing the change condition of the health of the drainage system in the J county of the last decade and points out a reasonable construction suggestion. The specific process is as follows:
a comprehensive health evaluation system of the urban drainage system is constructed, and according to the invention content, a comprehensive health evaluation system of the J county drainage system is constructed, and as shown in FIG. 2, the comprehensive health evaluation system of the J county drainage system comprises 5 dimensions and 20 subentries in total.
Constructing a convolutional neural network model based on an exploration image to realize the internal defect analysis of the drainage pipe network:
j county carries out pipe network general survey and exploration in 2018, and carries out rain and sewage pipe network basic data detection and video and image acquisition about 130km in urban areas. According to the defect types of the pipe network, 1800 actual samples are prepared, wherein each defect type of the basic sample comprises 200 defect types and 600 defect types, and 1800 defect types are accumulated through two groups of image rotation and mirroring. The convolutional neural network model is built in a PyTorch language environment, pyTorch is used as a framework, a GoogleLeNet deep learning network structure is used as a reference structure, the GoogleLeNet deep learning network structure uses 3-by-3 convolutional kernels, and 39 neural layers are totally arranged and comprise 21 convolutional layers, 4 pooling layers, 1 average pooling layer, 9 DepthCocat layers, 4 LocalRespNorm layers and 1 softmax layer.
The optimization algorithm of the network parameters in the invention specifically comprises the following optimization processes: setting the initial learning rate to be 0.0001, operating 3000 times in each cycle, operating two images every time, changing the learning rate to be 0.985 times of the original learning rate after every four cycles, training the GoogleLeNet deep learning network structure by using the sample images, reducing the learning rate by 10 times to continue training after the loss value is reduced by 10 times, and storing the network parameters at the moment as final network model parameters when the loss value is not reduced any more. The training environment is configured by adopting an Intel (R) Core (TM) i9-9700K processor with a main frequency of 4.0GHz and a memory of 64GB and an England GTX 2080Ti video card with a memory of 11 GB.
And after the GoogLeNet deep learning network structure training is completed, applying the image of the J county drainage network. The results mark a total of 108 mixed nodes, 244 damaged nodes and 89 silted nodes, and the results are converted into mixed joint rate of 6%, damage rate of 9% and silted rate of 14%. Because the internal defects are only detected in 2018 and the damage conditions of the pipe network in other years cannot be known, the method is set to calculate according to the damage rate of 0.5% in years before 2018 and calculate according to the damage rate of 0.2% in newly-built pipe networks after 2018.
The catchment area based on remote sensing image supervision and classification realizes the determination of catchment range:
(1) Carrying out object-oriented supervision and classification based on remote sensing images by using a remote sensing image processing platform ENVI, dividing the land utilization of a research area into nine types of high-rise buildings, low-rise buildings, industrial buildings, lakes, rivers, forest lands, green lands, bare lands and roads, and displaying the supervision and classification result of the remote sensing images in J county in a graph in FIG. 3; in the two horizontal rows of images in fig. 3, the first horizontal row is a remote sensing image which is not classified, and the second horizontal row is a remote sensing image which is classified;
(2) Based on the land classification result, the digital elevation data is corrected in a geographic information platform (namely GIS software), the correction elevation quantities are respectively +10m for an elevation building, +3.5m for a low-rise building, +5m for an industrial building, 0.5m for a road and the like, and a DEM correction result and a catchment area division result are shown in FIG. 4;
(3) Performing hydrological model catchment area division on the corrected DEM digital elevation data in a geographic information platform (namely, GIS software) based on a D8 flow direction algorithm, and performing experience setting on hydrological parameters according to a land utilization result;
(4) And calculating the collection range rate of the rainwater pipe network and the sewage pipe network according to whether the rainwater pipeline or the sewage pipeline is connected in the catchment area. The rainwater collection coverage rate of J county is increased from 41% in 2009 to 66% in 2020, and the sewage collection coverage rate is increased from 48% in 2009 to 79% in 2020.
The invention constructs 12 hydrodynamic water quality models in total from 2009 to 2020, and the difference between the models is related to the actual data collection situation of the current year, as shown in table 1. And inputting rainfall monitoring data of different years into the drainage system model to obtain the simulation result of the J county drainage system every year.
TABLE 1 Difference parameters for drainage System models
Calculating the comprehensive weight of the evaluation index system by using an analytic hierarchy process and an entropy method:
index weight calculation is performed by using an analytic hierarchy process and an entropy weight method, and the calculation result is shown in table 2.
TABLE 2 index weights
Calculating a comprehensive health score of the drainage system and analyzing the change trend:
scores of the indices of health of the drainage system between 2009 and 2020 in J prefecture are shown in table 3.
TABLE 3J county drainage System health assessment Table
From the calculation results in table 3, the health of the urban drainage system in J prefecture in 2009-2020 is generally in a state of descending first and then ascending. Health is in a fluctuating state in 2009-2016, which means that the health of the drainage system is gradually reduced due to the influence of urban development, the increase of pollutants and the continuous increase of the operation load of the drainage system. And the health of the drainage system is gradually improved between 2017 and 2020, which shows that the health of the drainage system is improved due to the implementation of upgrading and reconstruction projects in the period of time.
The score for the internal defect dimension is reduced year by year, which means that the internal defect gradually generates with the increase of time, and the pipeline maintenance is required to be carried out regularly. The score of the development scale dimension is firstly reduced and then improved, and the process is related to the upgrading and reconstruction construction of the drainage pipe network. The score of the rainwater trend dimension gradually shows the descending trend, which shows that the proportion of rainwater power in J county is lower and lower since the last decade, the infiltration rainwater is changed into runoff discharge to enter the river channel, the risk of urban waterlogging is increased, and the rainwater scouring pollution is increased, so that the J county is recommended to control the rainwater runoff so as to improve the overall health degree of the drainage system. The score of the operation state dimension shows a trend of descending year by year, which shows that the operation state of the drainage system has abnormal states along with the development of cities, such as the situations that the inflow water of a sewage plant exceeds the design scale, the water level of a pipe network is too high, and the like, so J county is recommended to carry out the operation state investigation of the drainage system, and a reasonable drainage pipe network modification scheme is provided according to the actual abnormal state. The score of the pollution discharge dimension shows a state of descending first and then ascending, which indicates that the river pollution amount entering J county is increased first and then reduced, and the reason for the reduction is that the treatment load of old sewage plants can be greatly reduced by putting a new sewage treatment plant into use in 2019, and the intercepted domestic sewage directly enters the river channel, which is beneficial to the health of a drainage system.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that various dependent claims and the features described herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (10)
1. The comprehensive evaluation method for the health of the drainage system is characterized by evaluating the health of the drainage system through five evaluation dimensions, and comprises the following specific processes:
s1, obtaining five evaluation dimensions which are respectively an internal defect dimension, a development scale dimension, a rainwater trend dimension, a facility running state dimension and a pollution discharge dimension; the five evaluation dimensions comprise 20 indexes;
the internal defect dimensionality comprises 3 indexes which are respectively a pipe section breakage rate, a pipe section siltation rate and a pipe network rain and sewage mixed connection rate;
the development scale dimension comprises 4 indexes which are respectively the density of a drainage pipe network, the processing capacity of a sewage treatment plant, the collection range rate of a rainwater pipe network and the collection range rate of a sewage pipe network;
the rainwater converging and diverging dimension comprises 4 indexes which are respectively the rainwater infiltration rate, the rainwater runoff rate, the rainwater storage rate and the rainwater evaporation rate;
the facility operation state dimension comprises 5 indexes which are respectively the overload operation time of the sewage plant in a unit evaluation period, the total overload time of the pipe sections in the unit evaluation period, the total overload water inflow of the sewage plant in the unit evaluation period, the total overload time of the pipe sections in the unit evaluation period and the total overflow water of the nodes in the unit evaluation period;
the pollution discharge dimension comprises 5 indexes which are the total pollution amount of the rainfall runoff, the total pollution discharge amount of the discharge outlet, the total combined overflow pollution amount and the direct sewage discharge proportion of the unit rainfall;
s2, carrying out subjective weight weighting on each index by utilizing an analytic hierarchy process to obtain a subjective weight A of each index i Meanwhile, the objective weight W of each index is obtained by an entropy method i (ii) a Wherein, A i Is the subjective weight of the ith index, W i Is the objective weight of the ith index, i is an integer;
s3, subjective weight A according to each index i And objective weight W i Obtaining the comprehensive weight psi of each index i (ii) a Then according to the comprehensive weight psi of each index i And actual value Q of the index i Obtaining a comprehensive evaluation result E of the health of the drainage system;
therein, Ψ i Is the integrated weight of the i-th index, Q i Is the actual value of the ith index.
2. The comprehensive evaluation method for the health of the drainage system according to claim 1, wherein the step S1 of obtaining the dimension of the internal defect comprises the following steps:
s11-1, constructing a convolutional neural network model based on an exploration image;
s11-2, analyzing internal defects of the drainage pipe network through the constructed convolutional neural network model based on the exploration image, and accordingly obtaining the pipe section breakage rate, the pipe section siltation rate and the pipe network rain and sewage mixed connection rate in the internal defect dimensionality.
3. The comprehensive evaluation method for the health of the drainage system according to claim 2, wherein the step S11-1 of constructing the convolutional neural network model based on the exploration image is implemented by:
s11-1-1, obtaining a sample set with autonomous labels according to an actual exploration image of a drainage pipe network, wherein the label types are divided into three types, namely pipeline damage, pipeline silting and pipeline mixed connection;
and S11-1-1, training and verifying the deep learning convolutional neural network by using a sample set to obtain the trained deep learning convolutional neural network, and taking the trained deep learning convolutional neural network as a convolutional neural network model based on the exploration image.
4. The comprehensive evaluation method for the health of the drainage system according to claim 2, wherein the step S11-2 of analyzing the internal defects of the drainage pipe network through the constructed convolutional neural network model based on the exploration image so as to obtain the pipe segment breakage rate, the pipe segment siltation rate and the pipe network rain and sewage misconnection rate in the internal defect dimension is implemented by:
5. the comprehensive evaluation method for the health of the drainage system according to claim 1, wherein the step S1 of obtaining the dimension of development scale comprises:
s12-1, acquiring the density of a drainage pipe network and the treatment capacity of a sewage treatment plant in a development scale dimension by researching regional drainage pipe network data;
s12-2, collecting remote sensing images of the research area, classifying and labeling land use types in partial images of the remote sensing images of the research area, wherein more than 50 labeled samples of each land use type form a sample set; wherein the classification result of the land use type includes a high-rise building, a low-rise building, an industrial building, a lake, a river, a forest land, a green land, a bare land and a road; the shape of the sample in the sample set is a polygon;
s12-3, classifying the land utilization type in the remote sensing image of the research area by a supervision classifier in the remote sensing image processing platform ENVI according to the sample set to obtain a classified remote sensing image;
s12-4, correcting the digital elevation of part of the land use type DEM in the classified remote sensing images by using a geographic information platform, keeping the digital elevation of the rest part of the land use type DEM unchanged, and obtaining the corrected remote sensing images;
the corrected partial land use type DEM digital elevation comprises elevation a of a high-rise building, elevation b of a low-rise building, elevation c of an industrial building and elevation d of a road; and a, b and c are positive values, d is a negative value;
s12-4, based on a D8 flow direction algorithm, carrying out catchment area division on the corrected remote sensing image on a geographic information platform, loading drainage pipe network data, and calculating the rainwater pipe network collection range rate and the sewage pipe network collection range rate in the development scale dimension by taking whether rainwater/sewage pipe sections exist in the catchment area range in the corrected remote sensing image as a standard, so that all indexes in the development scale dimension are obtained.
6. The comprehensive evaluation method for the health of the drainage system according to claim 5, wherein the step S12-4 of obtaining the rainwater pipe network collection range rate and the sewer pipe network collection range rate is implemented by:
7. the comprehensive evaluation method for the health of the drainage system according to claim 1, wherein the step S1 of obtaining the rainwater trend dimension, the facility operation state dimension and the pollution discharge dimension comprises:
s13-1, constructing a drainage system model based on drainage pipe network data;
s13-2, obtaining a rainwater trend dimension, a facility running state dimension and a pollution discharge dimension according to the constructed drainage system model.
8. The comprehensive evaluation method for the health of the drainage system according to claim 7, wherein the step S13-2 of obtaining the rainwater trend dimension according to the constructed drainage system model comprises the following implementation modes:
inputting rainfall data in a simulation time period into a drainage system model, performing hydrological and hydraulic calculation on each catchment area by the drainage system model according to the received rainfall data to obtain rainwater converging and diverging data of each catchment area corresponding to a drainage pipe network of a research area, and performing comprehensive statistics according to the rainwater converging and diverging dimensions of all catchment areas to obtain the rainwater converging and diverging dimensions of the research area;
the rainwater trend-return data of each catchment area comprise rainwater infiltration depth h 1k Rainwater evaporation depth h 2k Rainwater storage depth h 3k Depth of runoff of rainwater h 4k ；
Wherein,
the expression of the rainwater infiltration rate in the rainwater trend dimension is as follows:
and is
H 1 Is a research areaThe rainwater infiltration rate of the area, k is the number of the catchment area, k =1,2,3 \8230, q, k and q are integers, S k Is the area of the kth catchment area, h 1k The rainwater infiltration depth of the kth catchment area, S is the total area of a research area, and Precipitation is the total rainfall;
the expression of the rain water evaporation rate in the rain water return-trend dimension is as follows:
and is
H 2 To study the depth of rainwater evaporation in the area, h 2k Is the rainwater evaporation depth of the kth catchment area;
the expression of the rainwater storage rate in the rainwater trend dimension is as follows:
and is
H 3 For investigating the rainwater storage depth of the area, h 3k The rainwater storage depth of the kth catchment area;
the expression for the rain runoff rate in the rain trend dimension is:
and is
H 4 To study the depth of runoff of rainwater in an area, h 4k The rainwater runoff depth of the kth catchment area;
in the step S13-2, the implementation manner of obtaining the facility operation state dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, and performing hydraulic calculation on a drainage pipe network by the aid of the rainfall data received by operation of the drainage system model to obtain inflow of a sewage plant at each moment, fullness of each pipe section at each moment and overflow flow of a connecting node of each pipe section at each moment so as to obtain facility operation state dimensionality;
the implementation mode for obtaining the facility running state dimension comprises the following steps:
overload operation time of the sewage plant in a unit evaluation period: comparing the water inlet flow of the sewage plant with the preset water inlet flow of the sewage plant at each moment, counting the total time which is longer than the water inlet flow of the preset sewage plant in a unit evaluation period, and taking the total time as the overload operation time of the sewage plant in the unit evaluation period;
total overload time of pipe sections in unit evaluation period: comparing the fullness of each pipe section at each moment with a preset fullness, counting the total time greater than the preset fullness in a unit evaluation period, and taking the total time as the total overload time of the pipe sections in the unit evaluation period;
the total overload water inflow of the sewage plant in a unit evaluation period is as follows: the sum of the overflow flows of all pipe section connecting nodes at each moment in the unit evaluation period is counted and used as the overload total water inflow of the sewage plant in the unit evaluation period;
in the step S13-2, the implementation manner of obtaining the pollution discharge dimension according to the constructed drainage system model includes:
inputting rainfall data in a simulation time period into a drainage system model, operating the drainage system model to receive the rainfall data, taking each catchment area and a drainage pipe network corresponding to the catchment area as a calculation unit, calculating by using a one-dimensional water quality diffusion-plug flow formula, obtaining data of water quality pollution concentration output by the drainage pipe network changing along with time sequence, and obtaining pollution discharge dimensionality according to the data of the water quality pollution concentration output by the drainage pipe network changing along with time sequence;
wherein, the data that the water quality pollution concentration changes along with time series include:
the pollution concentration of the rainwater runoff of each rainwater discharge port at each moment and the runoff flow rate corresponding to the rainwater discharge port;
the pollution concentration of the rainwater discharge port of each rainwater discharge port at each moment and the discharge port flow rate corresponding to the rainwater discharge port;
the combined overflow pollution concentration of each pipe section node at each moment and the node overflow flow rate corresponding to the pipe section node;
the pollution concentration of each sewage discharge port at each moment and the flow of the sewage discharge port;
the pollution concentration of each catchment area at each moment and the pollution discharge flow rate corresponding to the catchment area;
the implementation manner for obtaining the pollutant discharge dimension comprises the following steps:
the total rainwater runoff pollution amount is the sum of the rainwater runoff pollution amount of each rainwater discharge port at all times, and the rainwater runoff pollution amount of each rainwater discharge port at each time is the product of the rainwater runoff pollution concentration of each rainwater discharge port at the time and the corresponding runoff flow of the rainwater discharge port;
the total pollution discharge amount of the discharge ports is the sum of the pollution amount of the rainwater discharge ports of all the rainwater discharge ports at all times, and the pollution amount of the rainwater discharge ports of each rainwater discharge port at each time is the product of the pollution concentration of the rainwater discharge ports of each rainwater discharge port at the time and the flow of the discharge ports corresponding to the rainwater discharge ports;
the total combined overflow pollution amount is the combined overflow pollution amount of each pipe section node at all times, and the combined overflow pollution amount of each pipe section node at each time is the product of the combined overflow pollution concentration of each pipe section node at the time and the node overflow flow corresponding to the pipe section node;
the sewage straight discharge amount is the sum of the pollution amount of each sewage discharge port at all moments, and the pollution amount of each sewage discharge port at each moment is the product of the pollution concentration of each sewage discharge port at the moment and the flow of the sewage discharge port; the total sewage generation amount is the sum of the pollution amount of each catchment area at all times, and the pollution amount of each catchment area at each time is the product of the pollution concentration of each catchment area at the time and the pollution discharge flow corresponding to the catchment area.
9. The comprehensive evaluation method for health of a drainage system according to claim 1, wherein in S2, the objective weight W of each index is obtained by an entropy method i The implementation mode of the method is as follows:
using entropy values E of individual indices i Obtaining objective weights W of the corresponding indexes i Wherein
m is the total number of indices, P ij Is the value of the j-th repetition of the i-th index, E i Is the entropy value of the ith index, n is the total repeated number, j is an integer, j =1,2,3 \8230, n.
10. The method for comprehensively evaluating the health of a drainage system according to claim 1, wherein in S3,
Ψ i Is the comprehensive weight of the ith index, m is an integer, and i =1,2,3 \8230, 8230m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844960.0A CN115204688A (en) | 2022-07-18 | 2022-07-18 | Comprehensive evaluation method for health of drainage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844960.0A CN115204688A (en) | 2022-07-18 | 2022-07-18 | Comprehensive evaluation method for health of drainage system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115204688A true CN115204688A (en) | 2022-10-18 |
Family
ID=83581708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210844960.0A Pending CN115204688A (en) | 2022-07-18 | 2022-07-18 | Comprehensive evaluation method for health of drainage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115204688A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829614A (en) * | 2024-03-06 | 2024-04-05 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN117934450A (en) * | 2024-03-13 | 2024-04-26 | 中国人民解放军国防科技大学 | Interpretive method and system for multi-source image data deep learning model |
| CN118657295A (en) * | 2024-08-16 | 2024-09-17 | 长江三峡集团实业发展(北京)有限公司 | Evaluation system construction method and equipment for water system |
-
2022
- 2022-07-18 CN CN202210844960.0A patent/CN115204688A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829614A (en) * | 2024-03-06 | 2024-04-05 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN117829614B (en) * | 2024-03-06 | 2024-05-07 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN117934450A (en) * | 2024-03-13 | 2024-04-26 | 中国人民解放军国防科技大学 | Interpretive method and system for multi-source image data deep learning model |
| CN118657295A (en) * | 2024-08-16 | 2024-09-17 | 长江三峡集团实业发展(北京)有限公司 | Evaluation system construction method and equipment for water system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115204688A (en) | Comprehensive evaluation method for health of drainage system | |
| CN110929359B (en) | Pipe network siltation risk prediction modeling method based on PNN neural network and SWMM technology | |
| CN106022518B (en) | A kind of piping failure probability forecasting method based on BP neural network | |
| CN112001610B (en) | Agricultural non-point source pollution treatment method and device | |
| CN110646867A (en) | Urban drainage monitoring and early warning method and system | |
| CN112528563B (en) | Urban waterlogging early warning method based on SVM algorithm | |
| CN112348290B (en) | River water quality prediction method, river water quality prediction device, storage medium and storage device | |
| CN113095694B (en) | Rainfall sand transportation model construction method suitable for multiple landform type areas | |
| CN117540329B (en) | Online early warning method and system for defects of drainage pipe network based on machine learning | |
| CN114942948A (en) | Drainage pipe network diagnosis and management method | |
| CN113191582B (en) | Road torrential flood vulnerability evaluation method based on GIS and machine learning | |
| CN116205136A (en) | Large-scale river basin deep learning flood forecasting method based on runoff lag information | |
| CN110232334A (en) | A kind of steel construction corrosion recognition methods based on convolutional neural networks | |
| CN114936505B (en) | Method for rapidly forecasting multi-point water depth of urban rainwater well | |
| CN117491585A (en) | Water ecological pollution monitoring method, device and system based on time sequence network | |
| CN114565603A (en) | Integrated flood disaster accurate monitoring and early warning method | |
| CN111199298A (en) | Flood forecasting method and system based on neural network | |
| CN114858207A (en) | Soft measurement-based gridding source tracing investigation method for drain outlet of river channel | |
| CN117520796B (en) | Highway subgrade water damage assessment method and system based on knowledge graph | |
| CN118070957A (en) | Semi-moist urban LSTM-BERT waterlogging prediction method integrating rainfall waterlogging runoff characteristic factors | |
| CN112780953B (en) | Independent metering area pipe network leakage detection method based on mode detection | |
| CN104569340B (en) | Underground environment quality determination method and device | |
| CN109101734A (en) | A kind of prediction technique of Continuous Rigid-Frame Bridge downwarp risk | |
| CN116164241A (en) | Intelligent detection method for leakage faults of gas extraction pipe network | |
| CN107977727B (en) | Method for predicting blocking probability of optical cable network based on social development and climate factors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |