[go: up one dir, main page]

CN120673562B - Methods and platforms for odor monitoring and early warning in water treatment plants - Google Patents

Methods and platforms for odor monitoring and early warning in water treatment plants

Info

Publication number
CN120673562B
CN120673562B CN202511178956.5A CN202511178956A CN120673562B CN 120673562 B CN120673562 B CN 120673562B CN 202511178956 A CN202511178956 A CN 202511178956A CN 120673562 B CN120673562 B CN 120673562B
Authority
CN
China
Prior art keywords
odor
node
parameters
water plant
nodes
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.)
Active
Application number
CN202511178956.5A
Other languages
Chinese (zh)
Other versions
CN120673562A (en
Inventor
王凤鹭
李婷
王长平
幸敏力
范漳
陈海松
李卓
张智丰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Shenshui Longgang Water Group Co ltd
Original Assignee
Shenzhen Shenshui Longgang Water Group Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Shenshui Longgang Water Group Co ltd filed Critical Shenzhen Shenshui Longgang Water Group Co ltd
Priority to CN202511178956.5A priority Critical patent/CN120673562B/en
Publication of CN120673562A publication Critical patent/CN120673562A/en
Application granted granted Critical
Publication of CN120673562B publication Critical patent/CN120673562B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B29/00Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
    • G08B29/18Prevention or correction of operating errors
    • G08B29/185Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
    • G08B29/188Data fusion; cooperative systems, e.g. voting among different detectors
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18Water
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/23Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/28Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • G08B21/182Level alarms, e.g. alarms responsive to variables exceeding a threshold
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00Predictive alarm systems characterised by extrapolation or other computation using updated historic data
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/12Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00Details relating to the application field
    • G06F2113/08Fluids
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14Force analysis or force optimisation, e.g. static or dynamic forces

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • Emergency Management (AREA)
  • Mathematical Physics (AREA)
  • Pathology (AREA)
  • Mathematical Optimization (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Mathematical Analysis (AREA)
  • Immunology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Fluid Mechanics (AREA)
  • Algebra (AREA)
  • Computer Security & Cryptography (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Investigating Or Analyzing Materials By The Use Of Fluid Adsorption Or Reactions (AREA)

Abstract

The invention discloses a method and a platform for monitoring and early warning of peculiar smell of a water works, and relates to the technical field of monitoring and early warning, wherein the method comprises the steps of carrying out key node identification based on structural design information of a target water works, deploying a sensor network, constructing M water works sensing networks, obtaining water works node sensing data streams, constructing water works peculiar smell identification channels, carrying out peculiar smell identification to obtain M initial node peculiar smell parameters, generating peculiar smell diffusion influence networks according to spatial distribution and process sequences of water works process key nodes, carrying out influence gain analysis, determining M water works node peculiar smell parameters, constructing a grading early warning mechanism, and carrying out early warning grade matching and peculiar smell grading early warning. The technical problems that in the prior art, sensor deployment lacks pertinence, odor identification and diffusion analysis are disjointed, so that the real-time performance and accuracy of odor monitoring and early warning of a water plant are poor are solved, and the technical effects of improving the real-time performance and coverage of odor monitoring and enhancing the accuracy of odor identification are achieved.

Description

Running water plant peculiar smell monitoring and early warning method and platform
Technical Field
The application relates to the technical field of monitoring and early warning, in particular to a method and a platform for monitoring and early warning of peculiar smell of a water works.
Background
How to realize real-time monitoring, accurate discernment and quick early warning to the peculiar smell of water works becomes the key problem that water treatment industry is urgent to be solved, traditional water works water quality monitoring relies on laboratory analysis, detection cycle is long, real-time is poor, coverage is limited, it is difficult to discover the peculiar smell is unusual in time, can realize the continuous monitoring to water works key technology node through deploying multiparameter sensor network, however, peculiar smell material probably is caused by multiple factors such as algae metabolite, industrial pollutant, disinfection accessory substance or pipeline corrosion, single sensor data is difficult to accurately discern peculiar smell type and pollution degree, in addition, the inside rivers dynamic change of water works such as process links such as mixing, precipitation, filtration, disinfection can influence diffusion route and concentration distribution of peculiar smell, influence monitoring early warning accuracy and the real-time of water works quality.
Therefore, in the related technology at the present stage, the technical problems of poor instantaneity and accuracy of monitoring and early warning of the peculiar smell of the water plant caused by lack of pertinence of sensor deployment, peculiar smell identification and diffusion analysis disjoint exist.
Disclosure of Invention
By providing the odor monitoring and early warning method and platform for the water works, the technical problems of poor instantaneity and accuracy of odor monitoring and early warning of the water works caused by lack of pertinence in sensor deployment, odor identification and diffusion analysis disjoint in the prior art are solved, and the technical effects of improving instantaneity and coverage of odor monitoring and enhancing accuracy of odor identification are achieved.
The application provides a waterworks peculiar smell monitoring and early warning method which comprises the steps of carrying out key node identification based on structural design information of a target waterworks to obtain M waterworks process key nodes, deploying sensor networks on the M waterworks process key nodes to construct M waterworks sensing networks, adopting the M waterworks sensing networks to monitor and obtain M waterworks node sensing data streams, constructing a waterworks peculiar smell identification channel, carrying out peculiar smell identification on the M waterworks node sensing data streams based on the waterworks peculiar smell identification channel to obtain M initial node peculiar smell parameters, generating an peculiar smell diffusion influence network according to spatial distribution and process sequences of the M waterworks process key nodes, carrying out influence gain analysis on the M initial node peculiar smell parameters based on the peculiar smell diffusion influence network to determine M waterworks node peculiar smell parameters, constructing a grading early warning mechanism, and carrying out grading matching and grading peculiar smell early warning on the M water works node peculiar smell parameters by adopting the grading early warning mechanism.
In a possible implementation mode, the running water plant peculiar smell monitoring and early warning method further comprises the steps of extracting parameters of structural design information of the target running water plant to obtain a running water plant key parameter set, carrying out three-dimensional modeling on the basis of the space layout parameters and the process equipment parameters to generate a running water plant space model, dividing the running water plant space model into N key processing process sections according to the process flow parameters, and carrying out key point identification on the running water plant space model on the basis of the N key processing process sections to obtain M water plant process key nodes.
In a possible implementation mode, the running water plant peculiar smell monitoring and early warning method further performs the following processing that process node association is carried out on the basis of the N key processing process sections and the running water plant space model respectively to obtain N process section association node sets, water plant processing simulation parameters are determined according to application scenes of the target running water plant, the water plant processing simulation parameters are applied to the running water plant space model to carry out finite element simulation to obtain peculiar smell substance distribution parameters, and key point screening is carried out on the N process section association node sets on the basis of the peculiar smell substance distribution parameters to obtain M process key nodes of the running water plant, wherein M is more than or equal to N.
In a possible implementation mode, the off-flavor monitoring and early warning method for the water works further comprises the steps of respectively carrying out monitoring demand analysis and sensor type selection on the M water works process key nodes to obtain M process node sensor parameters, carrying out deployment position analysis on the M water works process key nodes based on the off-flavor substance distribution parameters to determine M process node deployment position parameters, generating M node sensor deployment schemes according to the M process node sensor parameters and the M process node deployment position parameters, deploying sensor networks on the M water works process key nodes according to the M node sensor deployment schemes, and constructing the M water works sensing networks.
In a possible implementation mode, the running water plant peculiar smell monitoring and early warning method further performs the following processing of mining historical peculiar smell data and generating process node identification based on the target running water plant to obtain a running water plant node peculiar smell monitoring data set, obtaining peculiar smell identification key elements, wherein the peculiar smell identification key elements comprise peculiar smell types, concentration levels and diffusion ranges, classifying and identifying the running water plant node peculiar smell monitoring data set by adopting the peculiar smell identification key elements to obtain a water plant peculiar smell element identification branch channel, and parallelly fusing the water plant peculiar smell element identification branch channel to build the water plant peculiar smell identification channel.
In a possible implementation manner, the running water plant peculiar smell monitoring and early warning method further performs the following processing of performing diffusion path analysis based on spatial distribution of the M water plant process key nodes and node process sequences to generate an peculiar smell diffusion node path network, performing diffusion influence quantification on the peculiar smell diffusion node path network based on the running water plant node peculiar smell monitoring data set, determining a diffusion path influence coefficient set, mapping the diffusion path influence coefficient set to the peculiar smell diffusion node path network for identification, and generating the peculiar smell diffusion influence network.
In a possible implementation mode, the odor monitoring and early warning method for the water works further comprises the steps of extracting node coordinates of spatial distribution of the M water works process key nodes to obtain a process node spatial coordinate database, performing process topology connection on the M water works process key nodes according to the process node spatial coordinate database and the node process sequence to construct a process node topology graph, and performing odor diffusion directed identification on each connection node in the process node topology graph to generate the odor diffusion node path network.
In a possible implementation manner, the running water plant peculiar smell monitoring and early warning method further performs the following processing of carrying out association clustering on the running water plant node peculiar smell monitoring data set and each peculiar smell diffusion path in the peculiar smell diffusion node path network to obtain a plurality of diffusion path associated peculiar smell data sets, carrying out diffusion concentration attenuation fitting quantization on the plurality of diffusion path associated peculiar smell data sets respectively to determine a plurality of path diffusion attenuation coefficients, and determining the diffusion path influence coefficient set according to the plurality of path diffusion attenuation coefficients.
In a possible implementation manner, the odor monitoring and early warning method for the water works further carries out the following processing of sequentially carrying out diffusion influence accumulation on the M initial node odor parameters based on the odor diffusion influence network to obtain M node odor influence accumulation coefficients, and carrying out dynamic gain analysis on the M initial node odor parameters through the M node odor influence accumulation coefficients to determine the M water works node odor parameters.
The application further provides a water works odor monitoring and early warning platform, which comprises a water works sensing network construction module, a water works odor identification module, an odor classification early warning module and an early warning and early warning mechanism, wherein the water works sensing network construction module is used for carrying out key node identification based on structural design information of a target water works to obtain M water works process key nodes, deploying a sensor network on the M water works process key nodes to construct M water works sensing networks, the water works odor identification module is used for monitoring and acquiring M water works node sensing data streams by adopting the M water works sensing networks to construct a water works odor identification channel, carrying out odor identification on the M water works node sensing data streams based on the water works odor identification channel to obtain M initial node odor parameters, the influence gain analysis module is used for generating an odor diffusion influence gain analysis based on the M initial node odor parameters, and determining the M water works node odor parameters, and the classification early warning and early warning mechanism is used for carrying out early warning level matching and classification on the M water works node odor parameters by adopting the classification early warning and early warning mechanism.
The water works peculiar smell monitoring and early warning method and platform are designed to be used for carrying out key node identification based on structural design information of a target water works, deploying a sensor network, constructing M water works sensing networks, acquiring water works node sensing data streams, constructing water works peculiar smell identification channels, carrying out peculiar smell identification to obtain M initial node peculiar smell parameters, generating peculiar smell diffusion influence networks according to spatial distribution and process sequences of water works process key nodes, carrying out influence gain analysis, determining M water works node peculiar smell parameters, constructing a grading early warning mechanism, and carrying out early warning grade matching and peculiar smell grading early warning. The technical problems that in the prior art, sensor deployment lacks pertinence, odor identification and diffusion analysis are disjointed, so that the real-time performance and accuracy of odor monitoring and early warning of a water plant are poor are solved, and the technical effects of improving the real-time performance and coverage of odor monitoring and enhancing the accuracy of odor identification are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly describe the drawings of the embodiments of the present disclosure, and a flowchart is used in the present disclosure to illustrate operations performed by a platform according to embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic flow chart of a method for monitoring and early warning of the odor of a water works according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a water works odor monitoring and early warning platform according to an embodiment of the present application.
Reference numerals illustrate the water plant perception network construction module 10, the water plant odor identification module 20, the impact gain analysis module 30 and the odor grading early warning module 40.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the technical means thereof may be more clearly understood, and in order that the above-mentioned and other objects, features and advantages of the present application may be more readily understood, the following detailed description of the present application.
The present application will be described in further detail below with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, but all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, platform, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides a method for monitoring and early warning peculiar smell of a water works, which comprises the following steps of:
and step S100, carrying out key node identification based on structural design information of a target water works to obtain M water works process key nodes, deploying sensor networks on the M water works process key nodes, and constructing M water works sensing networks.
The step S100 further comprises a step S110 of extracting parameters of structural design information of the target water works to obtain a water works key parameter set, wherein the water works key parameter set comprises space layout parameters, processing technological process parameters and technological equipment parameters, a step S120 of carrying out three-dimensional modeling based on the space layout parameters and the technological equipment parameters to generate a water works space model, a step S130 of dividing the water works space model into N key processing technological sections according to the processing technological process parameters, and a step S140 of carrying out key point identification on the water works space model based on the N key processing technological sections to obtain M water works technological key nodes.
Preferably, structural design information of a target water works is obtained by analyzing design drawings, process manuals, equipment lists and the like, parameters are extracted, and space layout parameters, treatment process flow parameters and process equipment parameters are obtained, wherein the space layout parameters comprise geometric dimensions, relative positions, elevations and the like of structures such as a factory floor plan, a sedimentation tank, a filter tank and a clean water tank, the treatment process flow parameters refer to the processes of water treatment processes, such as coagulation, sedimentation, filtration, disinfection, water flow directions, residence time, treatment capacity and the like, and the process equipment parameters refer to models, installation positions and operation parameters of equipment such as a water pump, a dosing device, an ozone generator and an active carbon filter tank, so that a structured water works key parameter set is formed.
Preferably, a BIM building information model or a CAD tool is used for modeling according to space layout parameters and process equipment parameters to obtain a visualized running water plant space model, the geometric shapes, pipeline connection modes, equipment positions and the like of a sedimentation tank and a filter tank are accurately marked in the running water plant space model, the whole water treatment process of the running water plant is divided into N key treatment process sections according to process flow parameters and function independence of each section, water quality change characteristics and odor potential sources, wherein N is a positive integer larger than 1, the total number of the water treatment process sections is represented, such as N=6, the running water treatment process sections, the pretreatment process sections, the coagulating sedimentation process sections, the filtration process sections, the disinfection process sections, the delivery water process sections, the delivery pipe network stage, the secondary water supply stage and the like, rust is released by rusting of old metal pipelines, the bad plastic pipelines can release organic compounds, abnormal odors are brought, a community reservoir and a water tank cannot be cleaned timely, and the generated microorganisms or accumulated impurities can cause mildewing odor and the like.
Preferably, the N key treatment process sections identify key points of a space model of a water works, wherein the key nodes are key positions for monitoring peculiar smell, process sensitivity and space representativeness are required to be met, peculiar smell is easy to occur, such as chlorine residues in a disinfection section and algae breeding in a precipitation section, or the overall water quality condition of the process sections, such as a water inlet/water outlet of a filter tank, is reflected, specifically, in each water treatment process section, all possible monitored points, such as the water inlet, the middle part and the water outlet, are marked to form N point sets, then the distribution of peculiar smell substances is analyzed and screened through finite element simulation, including the diffusion path of the peculiar smell substances such as algae toxins, chloroform and the like is simulated through fluid dynamics, the concentration distribution is analyzed, and nodes with obvious concentration gradient change or long-term high risk are selected, such as the water outlet of the precipitation tank is easy to generate soil mildew due to algae aggregation, and finally the M water works process key nodes are determined.
Preferably, according to the risk characteristics of the process key nodes of each water plant, matched sensors are selected and deployed at important positions such as a water inlet of a sedimentation tank, the middle part of a filter tank, an outlet of a disinfection tank and the like to form a sensor network, namely an Internet of things sensing device cluster, which is used for collecting water quality parameters such as chlorophyll, total organic carbon, ammonia nitrogen, pH value, turbidity, residual chlorine, iron, manganese, oxidation-reduction potential and the like in real time, wherein the sensors of the process key nodes of each water plant are connected through wireless or wired communication to generate M water plant sensing networks, so that the dynamic sensing of the peculiar smell of the whole domain of the water plant is realized, and high-reliability data is provided for the identification and grading early warning of the peculiar smell.
Further, the step S140 comprises a step S141 of carrying out process node association on the basis of the N key treatment process sections and the running water plant space model respectively to obtain N process section association node sets, a step S142 of determining water plant treatment simulation parameters according to the application scene of the target running water plant, a step S143 of applying the water plant treatment simulation parameters to the running water plant space model to carry out finite element simulation to obtain peculiar smell substance distribution parameters, and a step S144 of carrying out key point screening on the N process section association node sets on the basis of the peculiar smell substance distribution parameters to obtain M water plant process key nodes, wherein M is more than or equal to N.
Preferably, the process node association is carried out on the basis of N key treatment process sections and a running water plant space model respectively, namely, all potential monitoring points contained in the running water plant space model are marked on each key treatment process section, N process section association node sets are determined, for example, a sedimentation section association node set comprises a water inlet, a middle baffle, a water outlet and a sludge discharge port, a disinfection section association node set comprises a chlorine contact tank inlet, a middle part, an outlet and a residual chlorine monitor mounting point, historical water quality data, a process design manual and real-time monitoring data are acquired according to the application scene of a target running water plant, and the water plant treatment simulation parameters comprising hydraulic parameters, pollution source parameters and environmental parameters are determined by analysis, wherein the hydraulic parameters comprise flow, flow rate and water flow direction, the pollution source parameters comprise peculiar smell substance types, initial concentration and release positions, and the environmental parameters comprise temperature, pH value and the like. According to a running water plant space model, a fluid dynamic model of the water plant is built by using CFD software, water plant treatment simulation parameters are injected into the model, finite element simulation calculation is carried out, peculiar smell substance distribution parameters are obtained, the peculiar smell substance distribution parameters comprise a peculiar smell substance concentration field, namely, the concentration distribution of each point in a three-dimensional space, such as the higher concentration of chloroform at an outlet of a disinfection tank and a diffusion path, peculiar smell substances diffuse along with migration tracks of water flow, such as algae toxins, from a sedimentation tank to a filter tank, finally, key point screening is carried out on N process section association node sets based on the peculiar smell substance distribution parameters, namely, M process key nodes of the water plant are identified and determined by combining water quality change characteristics, potential pollution risks and necessary nodes for peculiar smell substance migration in each key process section, wherein M is more than or equal to N, and each key process section possibly comprises a plurality of key nodes, such as water inlet, filter layer, backwash drainage and the like, which need to be monitored in the filter section.
Further, the step S100 further comprises a step S150 of carrying out monitoring demand analysis and sensor model selection on the M water plant process key nodes to obtain M process node sensor parameters, a step S160 of carrying out deployment position analysis on the M water plant process key nodes based on the peculiar smell substance distribution parameters to determine M process node deployment position parameters, a step S170 of generating M node sensor deployment schemes according to the M process node sensor parameters and the M process node deployment position parameters, and a step S180 of deploying sensor networks on the M water plant process key nodes according to the M node sensor deployment schemes to construct the M water plant sensing networks.
Preferably, for the process characteristics and the peculiar smell risk characteristics of the process key nodes of each water plant, such as algae metabolism of a sedimentation tank and chloroform generation of a disinfection tank, monitoring requirement analysis is performed, namely parameters to be monitored, such as 2-methyl isoborneol, residual chlorine, THM S and the like, are analyzed, and then the adaptive sensor types, which may include an electronic nose, a gas chromatograph, a fluorescence algae sensor and the like, are selected according to the parameters, such as measuring range, precision, sampling frequency and the like, of each sensor are defined, so that M process node sensor parameters are finally formed. Based on the peculiar smell substance distribution parameters obtained by the early finite element simulation, the optimal installation position of each sensor is determined by combining physical conditions such as water flow state, equipment layout and the like on site, for example, an algae sensor is deployed at the position (algae enrichment layer) with the water depth of 1.2-1.5M in a sedimentation tank, an eddy region is avoided in a pipeline, the middle part of a straight pipe section is selected to ensure data representativeness, and then M technological node deployment position parameters are generated. And then fusing the parameters of the M process node sensors and the parameters of the M process node deployment positions to formulate an M-set node sensor deployment scheme comprising an equipment list, an installation drawing and a communication configuration. And finally, deploying sensor networks on M water plant process key nodes according to an M node sensor deployment scheme, respectively integrating each node sensor through the Internet of things, and finally constructing M water plant sensing networks to support real-time data acquisition, edge calculation and cloud collaborative analysis so as to ensure the accurate matching of high space-time resolution and risk early warning of peculiar smell early warning.
And step 200, monitoring and acquiring M water plant node perception data streams by adopting the M water plant perception networks, building a water plant odor identification channel, and carrying out odor identification on the M water plant node perception data streams based on the water plant odor identification channel to obtain M initial node odor parameters.
Preferably, a water plant sensing network deployed through M key nodes, such as an electronic nose, a GC-MS (gas chromatography-mass spectrometer), an optical sensor and the like, monitors and acquires multidimensional water quality parameters at a set sampling frequency to form M water plant node sensing data streams, acquires historical process node odor monitoring data of a target water plant, performs data preprocessing including standardization, missing value filling and feature extraction, determines training data, builds an identification model based on machine learning, such as SVM (support vector machine), trains by using the training data, acquires parallel identification branches, can perform identification detection on different odor types, and then integrates all the identification branches through an attention mechanism in a weighting manner to determine a water plant odor identification channel, performs odor identification on the M water plant node sensing data streams by using the water plant odor identification channel, and outputs structured M initial node odor parameters which possibly contain odor types, intensity, time attenuation and the like, thereby ensuring odor identification speed and accuracy.
Further, the step S200 also comprises a step S210 of mining historical odor data and generating process node identifiers based on the target running water plant to obtain a running water plant node odor monitoring data set, a step S220 of obtaining odor identification key elements, wherein the odor identification key elements comprise odor types, concentration levels and diffusion ranges, a step S230 of classifying, identifying and training the running water plant node odor monitoring data set by adopting the odor identification key elements to obtain a running water plant odor element identification branch channel, and a step S240 of parallelly fusing the running water plant odor element identification branch channel to build the running water plant odor identification channel.
Preferably, the historical odor data mining is performed based on the target waterworks, namely odor event records, water quality detection reports and sensor logs accumulated by the waterworks for many years are collected, and then process node identifiers are generated, namely unique identifiers are added to each process node such as a sedimentation tank outlet, a filter tank water inlet and the like and associated process attributes, so that the odor monitoring data sets of the waterworks nodes are obtained in an aligned manner, wherein the odor monitoring historical data sets comprise the odor monitoring historical data of each process node such as time stamps, node positions, meteorological data, water quality parameters, odor event records and the like. The method comprises the steps of determining the type of the peculiar smell, the concentration grade and the diffusion range as key elements for identifying the peculiar smell, wherein the type of the peculiar smell is used as an output label of a classification model, such as 'earthy smell/mildewing smell', 'fishy smell', 'chlorine smell/disinfection by-product smell', and the like, the concentration grade is that the intensity of the peculiar smell or the concentration of the odor-causing substance is mapped to a grade 0-5 to be used as the output label of a regression model, and the diffusion range is that the number of affected downstream nodes is used as the output label of the regression model.
The method comprises the steps of carrying out classification recognition training on a water works node peculiar smell monitoring data set according to peculiar smell recognition key elements, namely training an independent water works peculiar smell element recognition branch channel for each peculiar smell recognition key element, specifically, constructing a training peculiar smell type recognition channel by using a support vector machine or a random forest, constructing a training concentration grade recognition channel by using support vector regression, using water quality, operation parameters and meteorological data corresponding to each key node as input characteristics, outputting peculiar smell concentration grade, constructing a training diffusion range recognition channel by using support vector regression, using water quality, operation parameters and meteorological data corresponding to each key node as input characteristics, and outputting peculiar smell diffusion range. And finally, carrying out parallel fusion on the water plant peculiar smell element identification branch channels, namely adopting an attention network to automatically calculate the weight of each branch and self-adaptively adjusting according to real-time working conditions, further carrying out weighted integration to obtain the water plant peculiar smell identification channels, carrying out peculiar smell identification according to the type of the generating process node and the sensing data corresponding to the node, and determining the peculiar smell type, concentration level and diffusion range.
And step S300, generating an odor diffusion influence network according to the spatial distribution and the process sequence of the M water plant process key nodes, and carrying out influence gain analysis on the M initial node odor parameters based on the odor diffusion influence network to determine M water plant node odor parameters.
The step S300 further comprises a step S310 of carrying out diffusion path analysis based on the spatial distribution of the M water plant process key nodes and the node process sequences to generate an odor diffusion node path network, a step S320 of carrying out diffusion influence quantification on the odor diffusion node path network based on the water plant node odor monitoring data set to determine a diffusion path influence coefficient set, and a step S330 of mapping the diffusion path influence coefficient set to the odor diffusion node path network for identification to generate the odor diffusion influence network.
Preferably, spatial distribution and a process sequence of M water plant process key nodes are obtained, wherein the spatial distribution refers to three-dimensional coordinates of the M key nodes, such as a sedimentation tank water inlet coordinate X=102.3, Y=45.6 and Z=0, the process sequence refers to an ordered process segment number in the water flow direction, such as 1 sedimentation, 2 filtration and 3 disinfection, diffusion path analysis is carried out according to the spatial distribution of the M water plant process key nodes and the node process sequence, specifically, directional edges, such as a sedimentation tank water outlet and a filter tank water inlet, are established according to the process sequence, topological connection of each node is generated, wherein vertexes represent key nodes, edges represent water flow paths, diffusion attributes are added to each edge, namely diffusion paths are marked, and an odor diffusion node path network is generated, wherein the odor diffusion node path network comprises a directional weighting network of all possible diffusion paths.
Preferably, the odor diffusion node path network is subjected to diffusion influence quantification based on the odor monitoring data set of the nodes of the water works, namely, for each diffusion path, concentration time sequences of upstream nodes and downstream nodes of the diffusion path network are extracted, softmax standardized values are calculated for all the odor diffusion paths through a least square fitting transfer function, influence coefficients of each diffusion path are determined, and then a diffusion path influence coefficient set is formed, the diffusion path influence coefficient set is mapped to the odor diffusion node path network for identification, namely, the corresponding diffusion path influence coefficients are marked on the corresponding diffusion path edges, so that a key diffusion path is obtained, and finally, the odor diffusion influence network is formed, so that the odor diffusion node path network has real-time risk visualization capability, such as a red path prompt priority control area, is provided.
Further, the step S310 further comprises a step S311 of extracting node coordinates of the spatial distribution of the M water plant process key nodes to obtain a process node spatial coordinate database, a step S312 of performing process topology connection on the M water plant process key nodes according to the process node spatial coordinate database and the node process sequence to construct a process node topology graph, and a step S313 of performing peculiar smell diffusion directed identification on each connection node in the process node topology graph to generate the peculiar smell diffusion node path network.
Preferably, based on the spatial distribution of M water plant process key nodes, extracting three-dimensional coordinates of each water plant process key node from a water plant spatial model to form a process node spatial coordinate database, then performing process topology connection on the M water plant process key nodes according to the process node spatial coordinate database and a node process sequence, specifically, connecting the water plant process key nodes according to the node process sequence to form directed edges, such as water inlet, grid flocculation, inclined tube precipitation, V-shaped filtration, disinfection and water outlet, so as to construct a process node topological graph, verifying connection rationality, and finally performing directed identification of the odor diffusion on each connection node in the process node topological graph, namely adding diffusion direction arrows on all edges of the process node topological graph, and simultaneously adding diffusion attribute parameters, possibly including diffusion time, diffusion attenuation coefficient, risk weight and the like, for each edge so as to identify an odor diffusion path, and generating an odor diffusion node path network, namely a directed weighting graph with multidimensional attribute so as to ensure enhanced odor identification accuracy.
Further, the step S300 further comprises a step S340 of carrying out association clustering on the odor monitoring data set of the water works node and each odor diffusion path in the odor diffusion node path network to obtain a plurality of diffusion path association odor data sets, a step S350 of respectively carrying out diffusion concentration attenuation fitting quantization on the plurality of diffusion path association odor data sets to determine a plurality of path diffusion attenuation coefficients, and a step S360 of determining the diffusion path influence coefficient set according to the plurality of path diffusion attenuation coefficients.
Preferably, the odor monitoring data set of the nodes of the water works is clustered in association with each odor diffusion path in the odor diffusion node path network, namely, the odor monitoring data of the nodes of the water works are associated with the odor diffusion paths, and then the odor diffusion paths are clustered and grouped according to the types of odor substances such as algae metabolites and disinfection byproducts, for example, a first type of algae odor diffusion path, a sedimentation tank, a filter tank, water outlet, a second type of chemical odor diffusion path, a disinfection tank and a clean water tank, and finally a plurality of diffusion path associated odor data sets are output, wherein each odor diffusion path corresponds to a group of concentration sequences matched in time and space. And then carrying out diffusion concentration attenuation fitting quantification based on a plurality of diffusion path associated peculiar smell data sets, specifically, fitting a concentration attenuation rule on each group of diffusion path data by adopting a physical-statistical mixed model, calculating a diffusion attenuation coefficient of each path through a least square method, characterizing the attenuation rate of peculiar smell substances on the path, further determining a plurality of path diffusion attenuation coefficients, and comprehensively reflecting the common influence of water flow power, pipeline characteristics and substance chemical properties. Finally, the attenuation coefficients of all the peculiar smell diffusion paths are normalized and converted into relative influence weights, the weights are adjusted according to real-time monitoring data, if a certain path frequently generates high-concentration peculiar smell recently, the weights are increased, and finally, a diffusion path influence coefficient set is generated, wherein the diffusion path influence coefficient set comprises the attenuation coefficient and the influence weight of each path.
Further, the step S300 further comprises a step S370 of sequentially carrying out diffusion influence accumulation on the M initial node odor parameters based on the odor diffusion influence network to obtain M node odor influence accumulation coefficients, and a step S380 of carrying out dynamic gain analysis on the M initial node odor parameters through the M node odor influence accumulation coefficients to determine the M water plant node odor parameters.
Preferably, the impact gain analysis is performed on the M initial node odor parameters based on the odor diffusion impact network, specifically, the diffusion impact accumulation is performed on the M initial node odor parameters sequentially according to the odor diffusion impact network, that is, each target node is searched for all upstream nodes pointing to the target node, the accumulated impact of the upstream nodes on the current node is calculated according to the diffusion path impact coefficient accumulation in the odor diffusion impact network, and M node odor impact accumulation coefficients are output, that is, the comprehensive value of each node affected by peripheral diffusion is quantized. And then carrying out dynamic gain analysis on M initial node odor parameters through M node odor influence accumulation coefficients, namely calculating a dynamic gain factor through (1+node odor influence accumulation coefficient/threshold value) based on the node odor influence accumulation coefficients, and correcting the initial node odor parameters by utilizing the dynamic gain factor to acquire M water plant node odor parameters so as to further improve the dynamic adaptability, early warning sensitivity and accuracy of monitoring early warning.
And step 400, constructing a grading early warning mechanism, and carrying out early warning grade matching and peculiar smell grading early warning on the peculiar smell parameters of the M water plant nodes by adopting the grading early warning mechanism.
Preferably, a grading early warning mechanism is constructed for dividing the odor risk into different early warning grades and triggering differentiated response measures, specifically, when the odor parameters of a single node exceed a base line value but are lower than 120% of a threshold value, a slight early warning such as slight algae breeding in a local process section is triggered, when multi-node linkage exceeds a standard, namely more than 3 nodes exceed the threshold value by 150% or key nodes continuously exceed the standard for 30 minutes, a moderate early warning such as incomplete filter backwashing causes accumulation of organic matters is triggered, when the core process node exceeds the standard by 200% or extremely toxic substances such as microcystin are detected, serious early warning such as sudden water source pollution or disinfection system faults are triggered, the grading early warning mechanism is adopted for carrying out early warning grade matching on the odor parameters of M water plants, including automatic labeling of abnormal parameters and matching the early warning grades through a decision tree model, the odor grading early warning is output, the early warning information comprises the extremely standard substances, the concentration and the influence range, and the auxiliary treatment measures are carried out, for example, the moderate early warning starts a standby filter, the serious early warning switching of the disinfectant is carried out, the serious early warning supervision and supervision department is carried out, thereby the identification of the water plant is remarkably improved, and the risk control capability is improved.
In the above, the method for monitoring and early warning the odor of the water works according to the embodiment of the invention is described in detail with reference to fig. 1. Next, a water works odor monitoring and early warning platform according to an embodiment of the present invention will be described with reference to fig. 2.
According to the odor monitoring and early warning platform for the water works, which is disclosed by the embodiment of the invention, the technical problems of poor instantaneity and accuracy of odor monitoring and early warning of the water works caused by lack of pertinence in sensor deployment, odor identification and diffusion analysis uncoupling in the prior art are solved, and the technical effects of improving instantaneity and coverage of odor monitoring and enhancing accuracy of odor identification are achieved. As shown in fig. 2, the water works peculiar smell monitoring and early warning platform comprises a water works perception network construction module 10, a water works peculiar smell identification module 20, an influence gain analysis module 30 and an peculiar smell grading early warning module 40.
The system comprises a water plant perception network construction module 10, a water plant odor identification module 20, an odor classification early warning module 40 and an odor classification early warning module, wherein the water plant perception network construction module 10 is used for carrying out key node identification based on structural design information of a target water plant to obtain M water plant process key nodes, deploying a sensor network on the M water plant process key nodes to construct M water plant perception networks, the water plant odor identification module 20 is used for monitoring and acquiring M water plant node perception data streams by adopting the M water plant perception networks to construct a water plant odor identification channel, carrying out odor identification on the M water plant node perception data streams based on the water plant odor identification channel to obtain M initial node odor parameters, the impact gain analysis module 30 is used for generating an odor diffusion impact network according to the spatial distribution and the process sequence of the M water plant process key nodes, carrying out impact gain analysis on the M initial node odor parameters based on the odor diffusion impact network to determine M water plant node odor parameters, and the odor classification early warning module 40 is used for constructing a classification early warning mechanism to carry out early warning level matching and classification early warning on the M water plant node parameters by adopting the classification early warning mechanism.
Next, the specific configuration of the water plant aware network construction module 10 will be described in detail. The water plant perception network construction module 10 further comprises the steps of extracting parameters of structural design information of the target water plant to obtain a water plant key parameter set, wherein the water plant key parameter set comprises space layout parameters, processing technological process parameters and technological equipment parameters, performing three-dimensional modeling based on the space layout parameters and the technological equipment parameters to generate a water plant space model, dividing the water plant space model into N key processing technological sections according to the processing technological process parameters, and performing key point identification on the water plant space model based on the N key processing technological sections to obtain M water plant technological key nodes.
The specific configuration of the water plant aware network construction module 10 will be described in further detail below. The water plant perception network construction module 10 further comprises the steps of carrying out process node association on the basis of the N key treatment process segments and the water plant space model respectively to obtain N process segment association node sets, determining water plant treatment simulation parameters according to the application scene of the target water plant, applying the water plant treatment simulation parameters to the water plant space model to carry out finite element simulation to obtain peculiar smell substance distribution parameters, and carrying out key point screening on the N process segment association node sets based on the peculiar smell substance distribution parameters to obtain the M water plant process key nodes, wherein M is larger than or equal to N.
The specific configuration of the water plant aware network construction module 10 will be described in further detail below. The water plant perception network construction module 10 further comprises the steps of respectively carrying out monitoring demand analysis and sensor model selection on the M water plant process key nodes to obtain M process node sensor parameters, carrying out deployment position analysis on the M water plant process key nodes based on the peculiar smell substance distribution parameters to determine M process node deployment position parameters, generating M node sensor deployment schemes according to the M process node sensor parameters and the M process node deployment position parameters, and deploying a sensor network on the M water plant process key nodes according to the M node sensor deployment schemes to construct the M water plant perception network.
Next, the specific configuration of the water plant odor identification module 20 will be described in detail. The water plant odor identification module 20 further comprises the steps of mining historical odor data of the water plant based on the target water plant and generating process node identification to obtain a water plant node odor monitoring data set, acquiring odor identification key elements, wherein the odor identification key elements comprise odor types, concentration levels and diffusion ranges, classifying, identifying and training the water plant node odor monitoring data set by adopting the odor identification key elements to obtain a water plant odor element identification branch channel, and parallelly fusing the water plant odor element identification branch channel to construct the water plant odor identification channel.
Next, a specific configuration of the influence gain analysis module 30 will be described in detail. The impact gain analysis module 30 still further includes performing a diffusion path analysis based on the spatial distribution of the M water plant process key nodes and the node process sequence to generate an odor diffusion node path network, quantifying a diffusion impact on the odor diffusion node path network based on the water plant node odor monitoring dataset, determining a diffusion path impact coefficient set, mapping the diffusion path impact coefficient set to the odor diffusion node path network for identification, and generating the odor diffusion impact network.
Next, the specific configuration of the influence gain analysis module 30 will be described in further detail. The influence gain analysis module 30 further comprises node coordinate extraction on the spatial distribution of the M water plant process key nodes to obtain a process node spatial coordinate database, process topology connection on the M water plant process key nodes according to the process node spatial coordinate database and the node process sequence to construct a process node topology graph, and peculiar smell diffusion directed identification on each connection node in the process node topology graph to generate the peculiar smell diffusion node path network.
Next, the specific configuration of the influence gain analysis module 30 will be described in further detail. The influence gain analysis module 30 still further includes performing association clustering on the water works node odor monitoring data set and each odor diffusion path in the odor diffusion node path network to obtain a plurality of diffusion path associated odor data sets, performing diffusion concentration attenuation fitting quantization on the plurality of diffusion path associated odor data sets respectively to determine a plurality of path diffusion attenuation coefficients, and determining the diffusion path influence coefficient set according to the plurality of path diffusion attenuation coefficients.
Next, the specific configuration of the influence gain analysis module 30 will be described in further detail. The influence gain analysis module 30 further includes performing diffusion influence accumulation on the M initial node odor parameters in sequence based on the odor diffusion influence network to obtain M node odor influence accumulation coefficients, and performing dynamic gain analysis on the M initial node odor parameters through the M node odor influence accumulation coefficients to determine the M water plant node odor parameters.
The running water plant peculiar smell monitoring and early warning platform provided by the embodiment of the invention can execute the running water plant peculiar smell monitoring and early warning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Although the present application makes various references to certain modules in the platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and/or the server, and the included units and modules are merely divided according to functional logic, but are not limited to the above-described division, so long as the corresponding functions can be implemented, and in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not intended to limit the scope of protection of the present application.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.

Claims (6)

1.自来水厂异味监测预警方法,其特征在于,所述方法包括:1. A method for monitoring and early warning of odors in a waterworks, characterized in that the method includes: 基于目标自来水厂的结构设计信息进行关键节点识别,得到M个水厂工艺关键节点,并在所述M个水厂工艺关键节点上部署传感器网络,构建M个水厂感知网络;Based on the structural design information of the target waterworks, key nodes are identified to obtain M key process nodes of the waterworks. Sensor networks are then deployed on the M key process nodes of the waterworks to construct M waterworks sensing networks. 采用所述M个水厂感知网络监测获取M个水厂节点感知数据流,搭建水厂异味识别通道,基于所述水厂异味识别通道对所述M个水厂节点感知数据流进行异味识别,得到M个初始节点异味参数;The M water plant sensing networks are used to monitor and acquire the sensing data streams of the M water plant nodes. An odor identification channel for the water plants is built. Based on the odor identification channel, the M water plant node sensing data streams are used to identify odors, and M initial node odor parameters are obtained. 根据所述M个水厂工艺关键节点的空间分布和工艺序列,生成异味扩散影响网络,基于所述异味扩散影响网络对所述M个初始节点异味参数进行影响增益分析,确定M个水厂节点异味参数;Based on the spatial distribution and process sequence of the M key nodes of the water plant process, an odor diffusion influence network is generated. Based on the odor diffusion influence network, an influence gain analysis is performed on the odor parameters of the M initial nodes to determine the odor parameters of the M water plant nodes. 构建分级预警机制,采用所述分级预警机制对所述M个水厂节点异味参数进行预警等级匹配和异味分级预警;A hierarchical early warning mechanism is constructed, and the mechanism is used to match the early warning level and classify the odor parameters of the M water plant nodes for early warning. 所述生成异味扩散影响网络,包括:The generated odor diffusion influence network includes: 基于所述M个水厂工艺关键节点的空间分布和节点工艺序列进行扩散路径分析,生成异味扩散节点路径网络;Based on the spatial distribution and process sequence of the M key nodes of the water plant process, diffusion path analysis is performed to generate an odor diffusion node path network. 基于自来水厂节点异味监测数据集对所述异味扩散节点路径网络进行扩散影响量化,确定扩散路径影响系数集;Based on the odor monitoring dataset of waterworks nodes, the diffusion impact of the odor diffusion node path network is quantified to determine the diffusion path impact coefficient set. 将所述扩散路径影响系数集映射至所述异味扩散节点路径网络进行标识,生成所述异味扩散影响网络;The set of diffusion path influence coefficients is mapped to the odor diffusion node path network for identification, thereby generating the odor diffusion influence network. 所述生成异味扩散节点路径网络,包括:The generated odor diffusion node path network includes: 对所述M个水厂工艺关键节点的空间分布进行节点坐标提取,获得工艺节点空间坐标数据库;The spatial distribution of the M key process nodes of the water plant is analyzed by extracting node coordinates to obtain a process node spatial coordinate database. 按照所述工艺节点空间坐标数据库和所述节点工艺序列对所述M个水厂工艺关键节点进行工艺拓扑连接,构建工艺节点拓扑图;Based on the process node spatial coordinate database and the node process sequence, process topology connections are made to the M key process nodes of the water plant to construct a process node topology diagram. 对所述工艺节点拓扑图中的各连接节点进行异味扩散有向标识,生成所述异味扩散节点路径网络;Odor diffusion is directionally identified for each connecting node in the process node topology diagram, and the odor diffusion node path network is generated. 所述确定扩散路径影响系数集,包括:The set of diffusion path influence coefficients includes: 将所述自来水厂节点异味监测数据集与所述异味扩散节点路径网络中的每条异味扩散路径进行关联聚类,获得多条扩散路径关联异味数据集;The odor monitoring dataset of the waterworks node is associated and clustered with each odor diffusion path in the odor diffusion node path network to obtain multiple diffusion path associated odor datasets; 基于所述多条扩散路径关联异味数据集分别进行扩散浓度衰减拟合量化,确定多条路径扩散衰减系数;Based on the odor dataset associated with the multiple diffusion paths, diffusion concentration attenuation fitting and quantification are performed to determine the diffusion attenuation coefficients for each path. 根据所述多条路径扩散衰减系数,确定所述扩散路径影响系数集;Based on the diffusion attenuation coefficients of the multiple paths, determine the set of diffusion path influence coefficients; 所述确定M个水厂节点异味参数,包括:The determination of odor parameters at M water plant nodes includes: 基于所述异味扩散影响网络依次对所述M个初始节点异味参数进行扩散影响累加,获得M个节点异味影响累积系数;Based on the odor diffusion influence network, the diffusion influence of the odor parameters of the M initial nodes is accumulated sequentially to obtain the cumulative coefficient of odor influence of the M nodes; 通过所述M个节点异味影响累积系数对所述M个初始节点异味参数进行动态增益分析,确定所述M个水厂节点异味参数,其中,所述M个水厂节点异味参数通过1+节点异味影响累积系数/阈值计算动态增益因子,再利用动态增益因子对初始节点异味参数进行修正获取。Dynamic gain analysis is performed on the M initial node odor parameters using the cumulative odor influence coefficients of the M nodes to determine the M water plant node odor parameters. The M water plant node odor parameters are obtained by calculating the dynamic gain factor using 1 + cumulative odor influence coefficient of the node / threshold, and then using the dynamic gain factor to correct the initial node odor parameters. 2.如权利要求1所述的自来水厂异味监测预警方法,其特征在于,所述得到M个水厂工艺关键节点,包括:2. The method for monitoring and early warning of odor in a waterworks as described in claim 1, characterized in that obtaining M key process nodes in the waterworks includes: 对所述目标自来水厂的结构设计信息进行参数提取,得到自来水厂关键参数集,所述自来水厂关键参数集包括空间布局参数、处理工艺流程参数以及工艺设备参数;The structural design information of the target waterworks is extracted to obtain a set of key parameters for the waterworks, which includes spatial layout parameters, treatment process parameters, and process equipment parameters. 基于所述空间布局参数和所述工艺设备参数进行三维建模,生成自来水厂空间模型;Based on the spatial layout parameters and the process equipment parameters, a three-dimensional model is created to generate a waterworks spatial model. 根据所述处理工艺流程参数,划分得到N个关键处理工艺段;Based on the processing flow parameters, N key processing segments are obtained; 基于所述N个关键处理工艺段对所述自来水厂空间模型进行关键点识别,得到M个水厂工艺关键节点。Based on the N key processing stages, key points are identified in the spatial model of the waterworks to obtain M key process nodes of the waterworks. 3.如权利要求2所述的自来水厂异味监测预警方法,其特征在于,所述基于所述N个关键处理工艺段对所述自来水厂空间模型进行关键点识别,得到M个水厂工艺关键节点,包括:3. The method for monitoring and early warning of odor in a waterworks as described in claim 2, characterized in that, the step of identifying key points in the spatial model of the waterworks based on the N key treatment process segments to obtain M key process nodes of the waterworks includes: 基于所述N个关键处理工艺段分别与所述自来水厂空间模型进行工艺节点关联,获取N个工艺段关联节点集;Based on the N key processing segments, process nodes are associated with the spatial model of the waterworks to obtain N process segment association node sets. 根据所述目标自来水厂的应用场景,确定水厂处理模拟参数;Based on the application scenario of the target waterworks, determine the simulation parameters for waterworks treatment; 将所述水厂处理模拟参数施加至所述自来水厂空间模型进行有限元模拟,获得异味物质分布参数;The water treatment simulation parameters of the water plant are applied to the spatial model of the water plant for finite element simulation to obtain the distribution parameters of odor substances. 基于所述异味物质分布参数对所述N个工艺段关联节点集进行关键点筛选,得到所述M个水厂工艺关键节点,其中,M≥N。Based on the odor substance distribution parameters, key points are screened for the N process segment associated node sets to obtain the M key process nodes of the water plant, where M≥N. 4.如权利要求3所述的自来水厂异味监测预警方法,其特征在于,所述构建M个水厂感知网络,包括:4. The method for monitoring and early warning of odor in water treatment plants as described in claim 3, characterized in that the construction of M water treatment plant sensing networks includes: 分别对所述M个水厂工艺关键节点进行监测需求分析和传感器选型,得到M个工艺节点传感器参数;Monitoring requirements analysis and sensor selection were performed for the M key process nodes of the water plant, and sensor parameters for the M process nodes were obtained. 基于所述异味物质分布参数对所述M个水厂工艺关键节点进行部署位置解析,确定M个工艺节点部署位置参数;Based on the odor substance distribution parameters, the deployment locations of the M key process nodes in the water plant are analyzed to determine the deployment location parameters of the M process nodes; 根据所述M个工艺节点传感器参数和所述M个工艺节点部署位置参数,生成M个节点传感器部署方案;Based on the sensor parameters of the M process nodes and the deployment location parameters of the M process nodes, generate a sensor deployment scheme for the M nodes; 按照所述M个节点传感器部署方案在所述M个水厂工艺关键节点上部署传感器网络,构建所述M个水厂感知网络。According to the M-node sensor deployment scheme, a sensor network is deployed on the M key process nodes of the water plant to construct the M water plant sensing network. 5.如权利要求1所述的自来水厂异味监测预警方法,其特征在于,所述搭建水厂异味识别通道,包括:5. The method for monitoring and early warning of odors in a water treatment plant as described in claim 1, characterized in that the step of establishing an odor identification channel in the water treatment plant includes: 基于所述目标自来水厂进行历史异味数据挖掘和生成工艺节点标识,得到自来水厂节点异味监测数据集;Based on the target waterworks, historical odor data is mined and process node identifiers are generated to obtain a waterworks node odor monitoring dataset. 获取异味识别关键要素,所述异味识别关键要素包括异味类型、浓度等级以及扩散范围;Key elements for odor identification are obtained, including odor type, concentration level, and diffusion range. 采用所述异味识别关键要素对所述自来水厂节点异味监测数据集进行分类识别训练,得到水厂异味要素识别分支通道;The odor identification key elements are used to classify and train the odor monitoring dataset of the waterworks node to obtain the waterworks odor element identification branch channel. 将所述水厂异味要素识别分支通道进行并行融合,搭建所述水厂异味识别通道。The odor identification branches of the water plant are fused in parallel to build the odor identification channel of the water plant. 6.自来水厂异味监测预警平台,其特征在于,所述平台用于实施权利要求1至5任意一项所述的自来水厂异味监测预警方法,所述平台包括:6. A water treatment plant odor monitoring and early warning platform, characterized in that the platform is used to implement the water treatment plant odor monitoring and early warning method according to any one of claims 1 to 5, the platform comprising: 水厂感知网络构建模块,用于基于目标自来水厂的结构设计信息进行关键节点识别,得到M个水厂工艺关键节点,并在所述M个水厂工艺关键节点上部署传感器网络,构建M个水厂感知网络;The water plant sensing network construction module is used to identify key nodes based on the structural design information of the target water plant, obtain M key nodes of the water plant process, and deploy sensor networks on the M key nodes of the water plant process to construct the M water plant sensing network. 水厂异味识别模块,用于采用所述M个水厂感知网络监测获取M个水厂节点感知数据流,搭建水厂异味识别通道,基于所述水厂异味识别通道对所述M个水厂节点感知数据流进行异味识别,得到M个初始节点异味参数;The water plant odor identification module is used to monitor and acquire the sensing data streams of M water plant nodes using the M water plant sensing networks, build a water plant odor identification channel, and perform odor identification on the sensing data streams of the M water plant nodes based on the water plant odor identification channel to obtain M initial node odor parameters. 影响增益分析模块,用于根据所述M个水厂工艺关键节点的空间分布和工艺序列,生成异味扩散影响网络,基于所述异味扩散影响网络对所述M个初始节点异味参数进行影响增益分析,确定M个水厂节点异味参数;The influence-gain analysis module is used to generate an odor diffusion influence network based on the spatial distribution and process sequence of the M key nodes of the water plant process, and to perform influence-gain analysis on the odor parameters of the M initial nodes based on the odor diffusion influence network to determine the odor parameters of the M water plant nodes. 异味分级预警模块,用于构建分级预警机制,采用所述分级预警机制对所述M个水厂节点异味参数进行预警等级匹配和异味分级预警。The odor classification and early warning module is used to construct a classification and early warning mechanism, and to perform early warning level matching and odor classification and early warning for the odor parameters of the M water plant nodes using the classification and early warning mechanism.
CN202511178956.5A 2025-08-22 2025-08-22 Methods and platforms for odor monitoring and early warning in water treatment plants Active CN120673562B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202511178956.5A CN120673562B (en) 2025-08-22 2025-08-22 Methods and platforms for odor monitoring and early warning in water treatment plants

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202511178956.5A CN120673562B (en) 2025-08-22 2025-08-22 Methods and platforms for odor monitoring and early warning in water treatment plants

Publications (2)

Publication Number Publication Date
CN120673562A CN120673562A (en) 2025-09-19
CN120673562B true CN120673562B (en) 2025-12-12

Family

ID=97054469

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202511178956.5A Active CN120673562B (en) 2025-08-22 2025-08-22 Methods and platforms for odor monitoring and early warning in water treatment plants

Country Status (1)

Country Link
CN (1) CN120673562B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105424840A (en) * 2015-12-28 2016-03-23 周俊杰 On-line continuous environmental air quality automatic monitoring system and peculiar smell source tracing method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9452234B2 (en) * 2014-04-18 2016-09-27 Thomas A. Conroy Method and system for switching between packages in a diffusion device based on a liquid level sensor
KR102600109B1 (en) * 2022-10-31 2023-11-08 주식회사 데카엔지니어링 Method and apparatus of predicting and reacting sewage odor based on ai

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105424840A (en) * 2015-12-28 2016-03-23 周俊杰 On-line continuous environmental air quality automatic monitoring system and peculiar smell source tracing method

Also Published As

Publication number Publication date
CN120673562A (en) 2025-09-19

Similar Documents

Publication Publication Date Title
CN114444259B (en) Rain and sewage pipe network tracing and tracking system and method
CN117116382B (en) Method and system for spatial and temporal prediction of water quality of lakes affected by water diversion projects
CN103473463B (en) A kind of method quantitatively determining background concentration of nitrogen and phosphorus of water body of lake basins
CN119322770B (en) Intelligent Internet of things-based method for tracing pollution abnormality of surface water river-entering drain outlet
CN116205592A (en) Pollution anomaly tracing method for drainage pipe network of intelligent Internet of things
CN117113038B (en) Method and system for tracing the source of urban water and soil erosion yellow mud water events
CN119648472B (en) Sewage treatment plant abnormal water inflow tracing method and system based on Frecher distance
CN114022008A (en) Estuary suitable ecological flow assessment method based on water ecological zoning theory
CN119005757B (en) Environment variable driven perchlorate point source pollution treatment method and system
CN114814135A (en) A method and system for traceability of river water pollution based on multivariate monitoring
CN119207627B (en) A dynamic monitoring method and system for river micropollutants based on artificial intelligence
CN116384268A (en) Pollution source traceability method, device and equipment based on water pollution
CN117521917A (en) Urban non-point source pollution load prediction method and system based on real-time monitoring
CN116483807A (en) Construction method of soil pollutant environment and toxicity database
CN120296329A (en) A method for tracing the source of ecological environmental pollution based on data analysis
CN118864203A (en) A pollution source tracing method based on the spatial topological relationship between air and space big data and rivers
CN118396230A (en) Marine environment data asset value analysis system and assessment method
CN120673562B (en) Methods and platforms for odor monitoring and early warning in water treatment plants
CN118883880B (en) Water pollution traceability analysis method and system based on multidimensional data fusion analysis
CN116913047B (en) A method and early warning system for tracing agricultural non-point source pollutants in a watershed
CN119476643A (en) Basin water quality prediction method and system based on spatial river network topology structure
CN116842851B (en) Model system for water service data perception and mechanism analysis based on drainage basin subsystem
CN118886923A (en) A digital precise traceability method and system
CN114238530B (en) Method and device for selecting water environment pollution source investigation points
CN117852859A (en) A method for groundwater health risk assessment based on heavy metal forms

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
GR01 Patent grant
GR01 Patent grant