WO2020244014A1 - 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法 - Google Patents

一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法 Download PDF

Info

Publication number
WO2020244014A1
WO2020244014A1 PCT/CN2019/094668 CN2019094668W WO2020244014A1 WO 2020244014 A1 WO2020244014 A1 WO 2020244014A1 CN 2019094668 W CN2019094668 W CN 2019094668W WO 2020244014 A1 WO2020244014 A1 WO 2020244014A1
Authority
WO
WIPO (PCT)
Prior art keywords
effluent
conductivity
rural domestic
sewage treatment
domestic sewage
Prior art date
Application number
PCT/CN2019/094668
Other languages
English (en)
French (fr)
Inventor
刘锐
郁强强
陈吕军
Original Assignee
浙江清华长三角研究院
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 浙江清华长三角研究院 filed Critical 浙江清华长三角研究院
Priority to US17/001,668 priority Critical patent/US11370679B2/en
Publication of WO2020244014A1 publication Critical patent/WO2020244014A1/zh

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/02—Aerobic processes
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/02—Aerobic processes
    • C02F3/12—Activated sludge processes
    • C02F3/1236—Particular type of activated sludge installations
    • C02F3/1263—Sequencing batch reactors [SBR]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/30—Aerobic and anaerobic processes
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F3/00—Biological treatment of water, waste water, or sewage
    • C02F3/32—Biological treatment of water, waste water, or sewage characterised by the animals or plants used, e.g. algae
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G01N27/02—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance
    • G01N27/04—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance
    • G01N27/06—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance of a liquid
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/05—Conductivity or salinity
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/06—Controlling or monitoring parameters in water treatment pH
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/08—Chemical Oxygen Demand [COD]; Biological Oxygen Demand [BOD]
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/14—NH3-N
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/16—Total nitrogen (tkN-N)
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2209/00—Controlling or monitoring parameters in water treatment
    • C02F2209/18—PO4-P
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W10/00—Technologies for wastewater treatment
    • Y02W10/10—Biological treatment of water, waste water, or sewage

Definitions

  • the invention relates to the technical field of wastewater treatment, and in particular to a method for predicting the compliance of the effluent from a rural domestic sewage treatment facility based on a support vector machine.
  • the monitoring of the drainage compliance of these facilities mainly relies on manual sampling and monitoring of the corresponding water quality indicators based on the national standard method.
  • the cost of sampling and water quality testing is high, the cycle is long, the workload is large, and it is difficult to indicate in real time.
  • the water standard of the facility mainly relies on manual sampling and monitoring of the corresponding water quality indicators based on the national standard method.
  • the current discharge standards for rural domestic sewage treatment facilities in the province implement the "Rural Domestic Wastewater Treatment Facilities Water Pollutant Discharge Standards" (DB 33/973-2015).
  • the main water quality indicators include pH and chemical oxygen demand ( COD), ammonia nitrogen (NH 3 -N), total phosphorus (calculated as P), suspended solids (SS), etc.
  • the corresponding primary and secondary emission standards are 6-9, 60mg/L, 15mg/L, 2mg, respectively /L, 20mg/L and 6-9, 100mg/L, 25mg/L, 3mg/L, 30mg/L.
  • the present invention provides a support vector machine-based method for predicting the effluent compliance status of rural domestic sewage treatment facilities.
  • the method combines the detection indicators of influent conductivity, effluent electrical conductivity, and effluent suspended solids concentration with that of rural domestic sewage treatment facilities.
  • the situation is correlated, and the support vector machine model is constructed to obtain the prediction model, which not only has high prediction accuracy, but also is fast and cheap.
  • a support vector machine-based method for predicting the effluent compliance of rural domestic sewage treatment facilities including the following steps:
  • step (3) Collect the influent conductivity, effluent conductivity and effluent suspended solids concentration of the rural domestic sewage treatment facilities to be predicted, and input them into the prediction model obtained in step (2) to obtain the prediction result.
  • the rural domestic sewage refers to the sewage generated by the life of rural residents, specifically including three types of sewage, namely: sewage, kitchen sewage and laundry sewage after treatment in septic tanks.
  • the main pollutants are COD, total nitrogen, ammonia nitrogen, total phosphorus and suspended solids.
  • the rural domestic sewage treatment facility refers to a treatment facility used to treat rural domestic sewage.
  • the number of samples in the training set is at least greater than 120-150.
  • the conductivity value is related to the water temperature
  • the conductivity value at the water temperature of 20°C or 25°C is generally used as a reference for calibration, and conventional conductivity meters generally automatically calibrate. In the present invention, it is only necessary to ensure that the measured conductivity is corrected using the same standard.
  • the rural domestic sewage treatment facility of the present invention is at least one of A 2 O treatment facility, constructed wetland treatment facility, SBR treatment facility and aeration filter treatment facility.
  • the above-mentioned rural domestic sewage treatment facilities are composed of two parts, an inflow regulating tank and a sewage treatment device, and an outlet well is provided at the outlet of the sewage treatment device.
  • step (1)
  • the conductivity of the inlet water is measured in the adjustment tank of the rural domestic sewage treatment facility, and the measurement time is 15 minutes after the lift pump in the adjustment tank is turned on;
  • the electrical conductivity of the effluent and the concentration of suspended solids in the effluent are measured in the effluent well of the rural domestic sewage treatment facility, and measured simultaneously with the electrical conductivity of the influent.
  • Inlet water conductivity, effluent conductivity and effluent suspended solids concentration are determined by collecting water samples in the regulating tank or effluent well to determine the conductivity value and suspended solids concentration, or directly using online monitoring conductivity meter and online suspended solids concentration meter Measure the water in the conditioning tank or outlet well.
  • the lift pump After the lift pump is turned on for 15 minutes, measure the conductivity of the inlet water, the conductivity of the outlet water and the concentration of suspended solids in the outlet water at the same time, and then check the conductivity of the inlet water, the conductivity of the outlet water and the concentration of suspended solids in the outlet water every 15 minutes. A total of 3 to 4 consecutive measurements were taken, and the average values were taken as the inlet water conductivity value, outlet water conductivity value and outlet water suspended solids concentration during the detection phase;
  • the concentration of other pollutants in the outlet wells of the rural domestic sewage treatment facilities is detected, and the average of the concentrations of the pollutants in the inlet and outlet water is calculated as The concentration of other pollutants in the detection stage is compared with the pollutant discharge standard to determine and judge the effluent compliance of rural domestic sewage treatment facilities.
  • the above-mentioned other pollutants refer to other pollutant indicators specified in the "Water Pollutant Discharge Standards for Rural Domestic Sewage Treatment Facilities” other than the concentration of suspended solids, such as pH, chemical oxygen demand (COD), ammonia nitrogen (NH 3 -N ), total phosphorus (calculated as P), suspended solids (SS).
  • COD chemical oxygen demand
  • NH 3 -N ammonia nitrogen
  • P suspended solids
  • the effluent compliance status is that the effluent meets the standard or the effluent exceeds the standard; whether the effluent meets the standard is determined according to the national or local "Rural Domestic Sewage Treatment Facility Water Pollutant Discharge Standard", and all indicators meet the discharge standard It is recorded as the effluent meets the standard, and any indicator does not meet the discharge standard as the effluent exceeds the standard.
  • effluent compliance criteria are selected based on actual conditions, and tests have found that the selection of criteria does not affect the applicability of the method of the present invention.
  • step (2) the influent conductivity, the effluent conductivity, and the effluent suspended solids concentration are respectively substituted into the mapminmax function for normalization, and then input into the support vector machine;
  • mapminmax function (xx min )/(x max -x min ) (1);
  • y is the measured data of the influent conductivity, effluent conductivity or effluent suspended solids concentration after normalization treatment
  • x is the influent conductivity, effluent conductivity or effluent suspension before normalization treatment Measured data of substance concentration, x min is the minimum value of x, and x max is the maximum value of x;
  • step (2) the Libsvm toolbox is used to train the model, and the training includes optimization of the penalty parameter c and the RBF kernel function parameter g;
  • the optimization is to use the SVMcgForClass function to perform two rounds of optimization on the penalty parameter c and the kernel function parameter g to obtain the optimal solution of the penalty parameter c and the kernel function parameter g.
  • step (3) after collecting the influent conductivity, the effluent conductivity, and the effluent suspended solids concentration of the rural domestic sewage treatment facilities to be predicted, a preliminary judgment is performed;
  • the preliminary judgment method is: directly according to the standard limit of the suspended solids concentration in the water pollutant discharge standard of rural domestic sewage treatment facilities to determine whether the effluent meets the standard or the effluent exceeds the standard;
  • the concentration of suspended solids in the effluent of the rural domestic sewage treatment facility to be predicted exceeds the standard; otherwise, the influent conductivity, the effluent electrical conductivity and the effluent conductivity of the rural domestic sewage treatment facility to be predicted are collected
  • the concentration of suspended matter is input into the prediction model obtained in step (2) to obtain the prediction result.
  • the present invention has the following beneficial effects:
  • the present invention correlates the detection indicators of influent conductivity, effluent conductivity, and effluent suspended solids concentration with the effluent compliance status of rural domestic sewage treatment facilities, and constructs a support vector machine model to obtain a prediction model, which not only has high prediction accuracy, but also And it's fast and cheap.
  • the prediction method of the present invention can realize rapid prediction, which is beneficial to the subsequent facility regulation.
  • Fig. 1 is a flowchart of a method for predicting the compliance of the effluent water from a rural domestic sewage treatment facility based on a support vector machine in Embodiment 1 of the present invention.
  • Example 2 is a diagram of the selection result of the optimal penalty parameter c and the kernel function parameter g in the rough selection process in Example 1.
  • FIG. 3 is a diagram showing the selection result of the optimal penalty parameter c and the kernel function parameter g in the fine selection process in Embodiment 1.
  • Fig. 4 is a comparison diagram between the predicted result and the actual result in Example 1.
  • Fig. 5 is a comparison diagram between the predicted result and the actual result in Example 2.
  • a support vector machine-based method for predicting the effluent compliance status of rural domestic sewage treatment facilities The specific steps are as follows:
  • the rural domestic sewage treatment facilities include mainstream A 2 O treatment facilities, constructed wetland treatment facilities, SBR treatment facilities and aeration filter facilities, with a treatment scale of 5-160t /d varies; all facilities are composed of two parts, the water inlet regulating tank and the sewage treatment device, the water inlet regulating tank is equipped with a lifting pump, and the sewage treatment device has a water outlet at the outlet.
  • the rural domestic sewage treated by the above facilities is composed of fecal sewage, kitchen sewage and laundry sewage treated by septic tanks.
  • the main pollutants are COD, total nitrogen, ammonia nitrogen, total phosphorus and suspended solids SS;
  • the water quality indicators for general monitoring are pH, chemical oxygen demand ( COD), ammonia nitrogen (NH 3 -N), total phosphorus (calculated as P), suspended solids (SS), the corresponding secondary emission standards are 6-9, 100mg/L, 25mg/L, 3mg/L, 30mg/ L.
  • the influent conductivity, the effluent conductivity, and the effluent suspended solids concentration are substituted into the mapminmax function for normalization, and then input into the support vector machine;
  • mapminmax function (xx min )/(x max -x min ) (1);
  • y is the measured data of the influent conductivity, effluent conductivity or effluent suspended solids concentration after normalization treatment
  • x is the influent conductivity, effluent conductivity or effluent suspension before normalization treatment Measured data of substance concentration, x min is the minimum value of x, and x max is the maximum value of x;
  • the first round is rough selection, the variation range of penalty parameter c and kernel function parameter g are [2 -10 ,2 10 ] and [2 -10 ,2 10 ] respectively; the second round is fine selection, penalty parameter c
  • the variation range of g and kernel function parameter g are [2 -5 ,2 5 ] and [2 -5 ,2 5 ] respectively.
  • the preliminary judgment method is to directly determine whether the effluent meets the standard or exceeds the standard limit of the suspended solids concentration in the water pollutant discharge standard of rural domestic sewage treatment facilities;
  • the concentration of suspended solids in the effluent of the rural domestic sewage treatment facility to be predicted exceeds the standard; otherwise, the influent conductivity, the effluent electrical conductivity and the effluent conductivity of the rural domestic sewage treatment facility to be predicted are collected
  • the concentration of suspended matter is input into the prediction model obtained in step (2) to obtain the prediction result.
  • the actual effluent compliance status of the 8 facilities is the same as the predicted effluent compliance status, indicating that the prediction is correct; the actual effluent compliance status of the 2 facilities is different from the predicted effluent compliance status, indicating that the prediction is wrong; therefore, the prediction accuracy rate of the prediction set is 80 %.
  • This embodiment uses the same sample and prediction method as the first embodiment except that the determination standard of the effluent meeting the standard is changed to "according to the national "Urban Wastewater Treatment Plant Pollutant Discharge Standard” Level B Standard”.
  • Prediction results the actual effectiveness of the eight facilities is the same as the predicted effectiveness, indicating that the prediction is correct; the actual effectiveness of the two facilities is different from the predicted effectiveness, indicating that the prediction is wrong; therefore, the prediction accuracy of the prediction set is 80%.

Abstract

一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，该方法包括：同时采集训练集中农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，并记录处理设施的出水达标情况；以进水电导率、出水电导率和出水悬浮物浓度作为输入，农村生活污水处理设施出水达标情况作为输出，利用支持向量机对训练集进行训练，构建预测模型；采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，输入至预测模型中，得到预测结果。该方法将检测指标进水电导率、出水电导率和出水悬浮物浓度与农村生活污水处理设施的出水达标情况进行关联，并构建支持向量机模型获得预测模型，不仅预测准确性高，而且快速、廉价。

Description

一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法 技术领域
本发明涉及废水处理技术领域，尤其涉及一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法。
背景技术
随着我国对农村生活污水处理的日益重视，全国各地建设了大量的分散式农村生活污水处理设施，相比于城市污水处理厂，这些设施处理水量较小，每天处理的水量一般为几吨至几百吨，且地理位置高度分散。
目前，这些设施排水达标情况的监测主要依靠人工采样后基于国标法监测相应的水质指标来判断，在监管过程中取样与水质测试的成本较高、周期较长、工作量较大，难以实时指示设施的水达标情况。
以浙江省为例，目前省内的农村生活污水处理设施排放标准执行《农村生活污水处理设施水污染物排放标准》(DB 33/973—2015)，主要水质指标有pH、化学需氧量(COD)、氨氮(NH 3-N)、总磷(以P计)、悬浮物(SS)等，对应的一级和二级排放标准分别为6-9、60mg/L、15mg/L、2mg/L、20mg/L和6-9、100mg/L、25mg/L、3mg/L、30mg/L。
对于数量众多且位置分散的农村生活污水处理设施而言，采样和水质测试的工作量十分巨大。并且，基于国标方法，检测的成本较高，时效性较差，无法通过获得实时出水结果来针对性的调控农村生活污水处理设施。
此外，由于资金上的限制，农村污水处理设施不可能像城市污水厂一样，采用大量的在线监测装置对出水水质进行系统的监测与管理；并且，由于针对COD、氨氮等指标的快速检测方法往往与国标法存在一定误差，当通过这些快速水质检测仪器获得的结果来判断农村生活污水处理设施出水的水质情况时，往往因误差累积而使得判断结果失准。
因此，对农村生活污水处理设施水达标情况的监测是农村污水处理设施运维的难题。
发明内容
本发明提供了一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，该方法将检测指标进水电导率、出水电导率和出水悬浮物浓度与农村生活污水处理设施的出水达标情况进行关联，并构建支持向量机模型获得预测模型，不仅预测准确性高，而且快速、廉价。
具体技术方案如下：
一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，包括以下步骤：
(1)选取若干农村生活污水处理设施作为训练集，同时采集训练集中农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，并记录相对应的农村生活污水处理设施的出水达标情况；
(2)以进水电导率、出水电导率和出水悬浮物浓度作为输入，农村生活污水处理设施出水达标情况作为输出，利用支持向量机对训练集进行训练，构建农村生活污水处理设施运行出水达标情况的预测模型；
(3)采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，输入至步骤(2)所得的预测模型中，得到预测结果。
本发明中，所述的农村生活污水是指农村居民生活所产生的污水，具体包括三类污水，即：经化粪池处理后的粪尿污水、厨房污水和洗衣污水，其主要污染物为COD、总氮、氨氮、总磷以及悬浮物。所述农村生活污水处理设施是指用于处理农村生活污水的处理设置。
经试验发现，对于上述农村生活污水处理设施而言，进水电导率、出水电导率和出水悬浮物浓度与农村生活污水处理设施的出水达标情况之间存在相关性，可以将进水电导率、出水电导率和出水悬浮物浓度作为输入代入支持向量机模型中，并根据农村生活污水处理设施出水达标情况的结果进行训练，构建农村生活污水处理设施出水达标情况的预测模型，进 而实现农村生活污水处理设施水达标情况的预测。
为保证预测模型的预测结果更为准确，步骤(1)中，所述训练集中样本数量至少大于120～150个。
由于电导率值与水温有关，本领域普遍以水温20℃或者25℃时的电导率值作为参比进行校正，且常规电导率仪一般会自动校正。本发明中只需保证测定的电导率采用相同标准进行校正即可。
本发明所述农村生活污水处理设施为A 2O处理设施、人工湿地处理设施、SBR处理设施和曝气滤池处理设施中的至少一种。上述农村生活污水处理设施均由进水调节池和污水处理装置两部分组成，污水处理装置的出水处设有出水井。
进一步地，步骤(1)中，
所述进水电导率在农村生活污水处理设施的调节池内测定，测定时间为调节池内提升泵开启15min后；
所述出水电导率和出水悬浮物浓度在农村生活污水处理设施的出水井内测定，与进水电导率同时测定。
进水电导率、出水电导率和出水悬浮物浓度测定方式为：采集调节池或出水井内的水样测定电导率值和悬浮物浓度，或者，直接采用在线监测电导率仪和在线悬浮物浓度仪测定调节池或出水井内的水。
作为优选，在提升泵开启15min后，同时各测定进水电导率、出水电导率和出水悬浮物浓度一次，此后每隔15分钟各检测进水电导率、出水电导率和出水悬浮物浓度一次，共连续测定3～4次，分别取平均值作为检测阶段的进水电导率值、出水电导率值和出水悬浮物浓度；
在每次检测进水电导率、出水电导率和出水悬浮物浓度的同时，检测农村生活污水处理设施的出水井内其他污染物的浓度，计算各污染物在进水和出水中浓度的平均值作为检测阶段的其他污染物浓度，将其他污染物浓度值与污染物排放标准进行比对，确定判断农村生活污水处理设施的出水达标情况。
上述其他污染物是指除悬浮物浓度以外的《农村生活污水处理设施水污染物排放标准》所规定的其他污染物指标，例如：pH、化学需氧量 (COD)、氨氮(NH 3-N)、总磷(以P计)、悬浮物(SS)。
进一步地，步骤(1)中，所述出水达标情况为出水达标或出水超标；出水是否达标根据国家或当地的《农村生活污水处理设施水污染物排放标准》进行判定，所有指标均符合排放标准记为出水达标，任一指标不符合排放标准记为出水超标。
出水达标判定标准根据实际情况选取，试验发现，判定标准的选取不影响本发明方法的适用性。
进一步地，步骤(2)中，先分别将进水电导率、出水电导率和出水悬浮物浓度代入mapminmax函数中进行归一化处理，再输入至支持向量机中；
mapminmax函数的公式为：y＝(x-x min)/(x max-x min) (1)；
式(1)中，y为归一化处理后的进水电导率、出水电导率或出水悬浮物浓度的实测数据，x为归一化处理前的进水电导率、出水电导率或出水悬浮物浓度的实测数据，x min为x中的最小值，x max为x中的最大值；
将出水达标的农村生活污水处理设施标记为1，出水超标的农村生活污水处理设施标记为-1。
进一步地，步骤(2)中，利用Libsvm工具箱训练模型，所述训练包括惩罚参数c和RBF核函数参数g的优化；
所述优化为利用SVMcgForClass函数对惩罚参数c和核函数参数g进行两轮优选，得到惩罚参数c和核函数参数g的最优解。
进一步地，步骤(3)中，采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度后，先进行初判；
所述初判的方法为：直接根据农村生活污水处理设施水污染物排放标准中悬浮物浓度的达标限值进行出水达标或出水超标的判定；
若待预测的农村生活污水处理设施的出水悬浮物浓度＞达标限值，判定为出水超标；反之，则再将采集的待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度输入至步骤(2)所得的预测模型中，得到预测结果。
与现有技术相比，本发明具有以下有益效果：
(1)本发明将检测指标进水电导率、出水电导率和出水悬浮物浓度与农村生活污水处理设施的出水达标情况进行关联，并构建支持向量机模型获得预测模型，不仅预测准确性高，而且快速、廉价。
(2)相对于常规的标准检测方法(最快需要30min左右的时间)，本发明预测方法可以实现快速预测，有利于后续设施调控的进行。
附图说明
图1为本发明实施例1中基于支持向量机的农村生活污水处理设施出水达标情况的预测方法的流程图。
图2为实施例1中粗选过程最佳惩罚参数c和核函数参数g的选择结果图。
图3为实施例1中细选过程最佳惩罚参数c和核函数参数g选择结果图。
图4为实施例1中预测结果与实际结果对比图。
图5为实施例2中预测结果与实际结果对比图。
具体实施方式
下面结合具体实施例对本发明作进一步描述，以下列举的仅是本发明的具体实施例，但本发明的保护范围不仅限于此。
实施例1
一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，具体步骤如下：
(1)选取长三角地区164个农村生活污水处理设施，该农村生活污水处理设施包含主流的A 2O处理设施、人工湿地处理设施、SBR处理设施和曝气滤池设施，处理规模5-160t/d不等；所有设施均由进水调节池和污水处理装置两部分组成，进水调节池内装有提升泵，污水处理装置的出水处设有出水井。上述设施处理的农村生活污水由经化粪池处理后的粪尿污水、厨房污水和洗衣污水组成，其主要污染物为COD、总氮、氨氮、总磷以及悬浮物SS；
测定农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，具体测定方法为：
在提升泵开启15min后，同时采集调节池和出水井内的水样，测定得到第一次进水电导率值、第一次出水电导率值和第一次出水悬浮物浓度；15分钟后，测定得到第二次进水电导率值、第二次出水电导率值和第二次出水悬浮物浓度；30分钟后，测定得到第三次进水电导率值、第三次出水电导率值和第三次出水悬浮物浓度；分别将三次进水电导率的值、进水电导率值和出水悬浮物浓度进行平均，得到平均进水电导率值、平均出水电导率值和出水悬浮物浓度；
与此同时，参照目前浙江省内执行的《农村生活污水处理设施水污染物排放标准》(DB 33/973—2015)中的二级标准，一般监测的水质指标为pH、化学需氧量(COD)、氨氮(NH 3-N)、总磷(以P计)、悬浮物(SS)，对应的二级排放标准为6-9、100mg/L、25mg/L、3mg/L、30mg/L。记录测定电导率和悬浮物浓度所对应的农村生活污水处理设施的出水各污染物的浓度，分别计算各污染物浓度的三次平均值，将各出水污染物浓度平均值与污染物排放标准限值进行比对，确定判断农村生活污水处理设施的出水达标情况。即：当设施出水达标时记为1，设施出水超标时记为-1。
(2)以进水电导率、出水电导率和出水悬浮物浓度作为输入，农村生活污水处理设施的出水达标情况作为输出，在164组数据中随机选取154组作为训练集，利用支持向量机对训练集进行训练，构建农村生活污水处理设施出水达标情况的预测模型；
具体步骤为：
先分别将进水电导率、出水电导率和出水悬浮物浓度代入mapminmax函数中进行归一化处理，再输入至支持向量机中；
mapminmax函数的公式为：y＝(x-x min)/(x max-x min) (1)；
式(1)中，y为归一化处理后的进水电导率、出水电导率或出水悬浮物浓度的实测数据，x为归一化处理前的进水电导率、出水电导率或出水悬浮物浓度的实测数据，x min为x中的最小值，x max为x中的最大值；
训练过程中，利用Libsvm工具箱，实现支持向量机对训练集进行训 练，构建农村生活污水处理设施运行出水达标情况的预测模型，进行惩罚参数c和RBF核函数参数g的优化；
利用SVMcgForClass函数对惩罚参数c和核函数参数g进行两轮优选，得到惩罚参数c和核函数参数g的最优解；
其中，第一轮为粗选，惩罚参数c和核函数参数g的变化范围分别为[2 -10,2 10]和[2 -10,2 10]；第二轮为细选，惩罚参数c和核函数参数g的变化范围分别为[2 -5,2 5]和[2 -5,2 5]。
(3)剩余的10组数据作为预测集，采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，进行初判；
初判的方法为：直接根据农村生活污水处理设施水污染物排放标准中悬浮物浓度的达标限值进行出水达标或出水超标的判定；
若待预测的农村生活污水处理设施的出水悬浮物浓度＞达标限值，判定为出水超标；反之，则再将采集的待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度输入至步骤(2)所得的预测模型中，得到预测结果。
预测结果：8个设施的实际出水达标情况与预测出水达标情况相同，表明预测正确；2个设施的实际出水达标情况与预测出水达标情况不同，表明预测错误；故预测集的预测正确率为80％。
实施例2
本实施例除将出水达标的判定标准改为“根据国家《城镇污水处理厂污染物排放标准》一级B标准”外，其余采用与实施例1完全相同的样本和预测方法。
预测结果：8个设施的实际有效性与预测有效性相同，表明预测正确；2个设施的实际有效性与预测有效性不同，表明预测错误；故预测集的预测正确率为80％。

Claims (6)

  1. 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，包括以下步骤：
    (1)选取若干农村生活污水处理设施作为训练集，同时采集训练集中农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，并记录相对应的农村生活污水处理设施的出水达标情况；
    (2)以进水电导率、出水电导率和出水悬浮物浓度作为输入，农村生活污水处理设施出水达标情况作为输出，利用支持向量机对训练集进行训练，构建农村生活污水处理设施运行出水达标情况的预测模型；
    (3)采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度，输入至步骤(2)所得的预测模型中，得到预测结果。
  2. 如权利要求1所述的基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，步骤(1)中，所述农村生活污水处理设施为A 2O处理设施、人工湿地处理设施、SBR处理设施和曝气滤池处理设施中的至少一种。
  3. 如权利要求1所述的基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，步骤(1)中，
    所述进水电导率在农村生活污水处理设施的调节池内测定，测定时间为调节池内提升泵开启15min后；
    所述出水电导率和出水悬浮物浓度在农村生活污水处理设施的出水井内测定，与进水电导率同时测定。
  4. 如权利要求1所述的基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，步骤(2)中，先分别将进水电导率、出水电导率和出水悬浮物浓度代入mapminmax函数中进行归一化处理，再输入至支持向量机中；
    mapminmax函数的公式为：y＝(x-x min)/(x max-x min)      (1)；
    式(1)中，y为归一化处理后的进水电导率、出水电导率或出水悬浮 物浓度的实测数据，x为归一化处理前的进水电导率、出水电导率或出水悬浮物浓度的实测数据，x min为x中的最小值，x max为x中的最大值。
    将出水达标的农村生活污水处理设施标记为1，出水超标的农村生活污水处理设施标记为-1。
  5. 如权利要求1所述的基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，步骤(2)中，利用Libsvm工具箱训练模型，所述训练包括惩罚参数c和RBF核函数参数g的优化；
    所述优化为采用SVMcgForClass函数对惩罚参数c和核函数参数g进行两轮优选，得到惩罚参数c和核函数参数g的最优解。
  6. 如权利要求1所述的基于支持向量机的农村生活污水处理设施出水达标情况的预测方法，其特征在于，步骤(3)中，采集待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度后，先进行初判；
    所述初判的方法为：直接根据农村生活污水处理设施水污染物排放标准中悬浮物浓度的达标限值进行出水达标或出水超标的判定；
    若待预测的农村生活污水处理设施的出水悬浮物浓度＞达标限值，判定为出水超标；反之，则再将采集的待预测的农村生活污水处理设施的进水电导率、出水电导率和出水悬浮物浓度输入至步骤(2)所得的预测模型中，得到预测结果。
PCT/CN2019/094668 2019-06-06 2019-07-04 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法 WO2020244014A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/001,668 US11370679B2 (en) 2019-06-06 2020-08-24 Method for predicting discharge level of effluent from decentralized sewage treatment facilities

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910492731.5 2019-06-06
CN201910492731.5A CN110186505B (zh) 2019-06-06 2019-06-06 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/001,668 Continuation-In-Part US11370679B2 (en) 2019-06-06 2020-08-24 Method for predicting discharge level of effluent from decentralized sewage treatment facilities

Publications (1)

Publication Number Publication Date
WO2020244014A1 true WO2020244014A1 (zh) 2020-12-10

Family

ID=67720801

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/094668 WO2020244014A1 (zh) 2019-06-06 2019-07-04 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法

Country Status (2)

Country Link
CN (1) CN110186505B (zh)
WO (1) WO2020244014A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114047719A (zh) * 2021-11-02 2022-02-15 江西零真生态环境集团有限公司 一种农村生活污水处理设施远程监测评估系统与运行方法
CN114240127A (zh) * 2021-12-14 2022-03-25 云南省设计院集团有限公司 基于水质水量诊断分析的城镇污水提质增效评估方法
CN115684529A (zh) * 2022-11-04 2023-02-03 湖北碧尔维环境科技有限公司 基于反馈调节的污水去污优化方法及装置
CN116029589A (zh) * 2022-12-14 2023-04-28 浙江问源环保科技股份有限公司 基于两段式rbf的农村生活污水动植物油在线监测方法
CN117035230A (zh) * 2023-08-08 2023-11-10 上海东振环保工程技术有限公司 一种基于大数据分析的污水处理设备运行状态评估方法
CN117035230B (zh) * 2023-08-08 2024-04-30 上海东振环保工程技术有限公司 一种基于大数据分析的污水处理设备运行状态评估方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112964843A (zh) * 2021-01-26 2021-06-15 清华大学 污水处理设施水质监测的物联网传感器系统及监测方法

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266254A (zh) * 2008-05-09 2008-09-17 邯郸市隆达利科技发展有限公司 水质自动在线监测系统
CN101944275A (zh) * 2010-08-26 2011-01-12 天津市环境保护科学研究院 中空纤维设备的膜污染诊断与预警决策系统
CN102249411A (zh) * 2011-05-17 2011-11-23 中国科学技术大学 一种污水处理工艺的优化方法
CN104787875A (zh) * 2015-04-14 2015-07-22 北京金控自动化技术有限公司 一种序批式活性污泥法的曝气控制方法及系统
CN204666616U (zh) * 2015-05-07 2015-09-23 广西壮族自治区环境保护科学研究院 一种农村污水监测系统
KR20160019681A (ko) * 2014-08-12 2016-02-22 두산중공업 주식회사 감지 조류 제거 시스템 및 방법
CN107531528A (zh) * 2015-04-03 2018-01-02 住友化学株式会社 预测规则生成系统、预测系统、预测规则生成方法和预测方法
CN108027137A (zh) * 2015-09-18 2018-05-11 三菱日立电力系统株式会社 水质管理装置、水处理系统、水质管理方法及水处理系统的最佳化程序
CN108425405A (zh) * 2018-04-02 2018-08-21 淮阴工学院 一种网络化水源监测及分级供水装置及其监测系统
CN109542150A (zh) * 2018-12-03 2019-03-29 浙江清华长三角研究院 一种农村生活污水处理设施进水负荷的调节方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8198075B2 (en) * 2005-08-31 2012-06-12 Ut-Battelle, Llc Method and apparatus for enhanced detection of toxic agents
CN202075272U (zh) * 2011-03-30 2011-12-14 北京中拓百川投资有限公司 一种应用于污水处理的软测量系统
US20150323514A1 (en) * 2014-04-28 2015-11-12 University Of Massachusetts Systems and methods for forecasting bacterial water quality
CN109534501B (zh) * 2018-12-03 2019-11-05 浙江清华长三角研究院 一种农村生活污水处理设施的监管方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101266254A (zh) * 2008-05-09 2008-09-17 邯郸市隆达利科技发展有限公司 水质自动在线监测系统
CN101944275A (zh) * 2010-08-26 2011-01-12 天津市环境保护科学研究院 中空纤维设备的膜污染诊断与预警决策系统
CN102249411A (zh) * 2011-05-17 2011-11-23 中国科学技术大学 一种污水处理工艺的优化方法
KR20160019681A (ko) * 2014-08-12 2016-02-22 두산중공업 주식회사 감지 조류 제거 시스템 및 방법
CN107531528A (zh) * 2015-04-03 2018-01-02 住友化学株式会社 预测规则生成系统、预测系统、预测规则生成方法和预测方法
CN104787875A (zh) * 2015-04-14 2015-07-22 北京金控自动化技术有限公司 一种序批式活性污泥法的曝气控制方法及系统
CN204666616U (zh) * 2015-05-07 2015-09-23 广西壮族自治区环境保护科学研究院 一种农村污水监测系统
CN108027137A (zh) * 2015-09-18 2018-05-11 三菱日立电力系统株式会社 水质管理装置、水处理系统、水质管理方法及水处理系统的最佳化程序
CN108425405A (zh) * 2018-04-02 2018-08-21 淮阴工学院 一种网络化水源监测及分级供水装置及其监测系统
CN109542150A (zh) * 2018-12-03 2019-03-29 浙江清华长三角研究院 一种农村生活污水处理设施进水负荷的调节方法

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114047719A (zh) * 2021-11-02 2022-02-15 江西零真生态环境集团有限公司 一种农村生活污水处理设施远程监测评估系统与运行方法
CN114240127A (zh) * 2021-12-14 2022-03-25 云南省设计院集团有限公司 基于水质水量诊断分析的城镇污水提质增效评估方法
CN115684529A (zh) * 2022-11-04 2023-02-03 湖北碧尔维环境科技有限公司 基于反馈调节的污水去污优化方法及装置
CN115684529B (zh) * 2022-11-04 2023-05-16 湖北碧尔维环境科技有限公司 基于反馈调节的污水去污优化方法及装置
CN116029589A (zh) * 2022-12-14 2023-04-28 浙江问源环保科技股份有限公司 基于两段式rbf的农村生活污水动植物油在线监测方法
CN116029589B (zh) * 2022-12-14 2023-08-22 浙江问源环保科技股份有限公司 基于两段式rbf的农村生活污水动植物油在线监测方法
CN117035230A (zh) * 2023-08-08 2023-11-10 上海东振环保工程技术有限公司 一种基于大数据分析的污水处理设备运行状态评估方法
CN117035230B (zh) * 2023-08-08 2024-04-30 上海东振环保工程技术有限公司 一种基于大数据分析的污水处理设备运行状态评估方法

Also Published As

Publication number Publication date
CN110186505B (zh) 2020-02-14
CN110186505A (zh) 2019-08-30

Similar Documents

Publication Publication Date Title
WO2020244014A1 (zh) 一种基于支持向量机的农村生活污水处理设施出水达标情况的预测方法
WO2020244265A1 (zh) 一种利用支持向量机预测农村生活污水处理设施运行有效性的方法
CN110146122B (zh) 一种农村生活污水处理设施运行有效性的预测方法
Spinelli et al. Critical analyses of nitrous oxide emissions in a full scale activated sludge system treating low carbon-to-nitrogen ratio wastewater
KR101244445B1 (ko) 데이터마이닝 기법에 의한 응집제 자동제어 장치 및 이를 이용한 응집제 자동제어 방법
CN108002532A (zh) 基于物联网和大数据技术的污水处理模型动态核验方法
US11370679B2 (en) Method for predicting discharge level of effluent from decentralized sewage treatment facilities
CN108982790B (zh) 污水毒性的检测方法及污水毒性检测装置
CN110642393A (zh) 一种基于神经网络模型的曝气控制系统
CN110632267A (zh) 一种对超出在线仪表适用量程的高浓度污水的连续测定系统及方法
CN116199351A (zh) 曝气池溶解氧仪表故障容错控制方法、装置、系统及介质
CN112573641B (zh) 一种污水处理量确定方法及装置
JP2003290789A (ja) 嫌気処理設備及びその監視方法
CN113551708B (zh) 一种火电厂湿法烟气脱硫系统水平衡评价及控制方法
CN115220408A (zh) A2/o工艺系统的故障诊断方法、系统、设备及存储介质
US20210155510A1 (en) Method for determining a dose of coagulant for treating raw water
CN108090706B (zh) 中点概化河道纳污能力风险估计及促进规划合理化方法
JP4248043B2 (ja) 生物学的りん除去装置
CN101418333A (zh) 一种用于诊断污水除磷系统中聚磷菌构成的检测方法
JP3381749B2 (ja) 計測器の異常検出方法とその装置
CN108675439A (zh) 一种选择污水处理过程调控措施的方法
CN108491995A (zh) 一种用于饮用水风险因子识别的关键控制因素筛选方法
Rahbari et al. Evaluating the process efficiency of industrial wastewater treatment plants using data envelopment analysis approach case study: Khuzestan steel company treatment plant
CN109300513A (zh) 一种磷酸盐缓蚀剂抑制供水管网铁释放效果的检测方法
CN114195205B (zh) 一种污水厂尾水安全排放预警系统及其运行工艺

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19932168

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19932168

Country of ref document: EP

Kind code of ref document: A1