JPH06312104A - Initial precipitation sludge extraction control device - Google Patents
Initial precipitation sludge extraction control deviceInfo
- Publication number
- JPH06312104A JPH06312104A JP5102074A JP10207493A JPH06312104A JP H06312104 A JPH06312104 A JP H06312104A JP 5102074 A JP5102074 A JP 5102074A JP 10207493 A JP10207493 A JP 10207493A JP H06312104 A JPH06312104 A JP H06312104A
- Authority
- JP
- Japan
- Prior art keywords
- sludge
- withdrawal
- function
- self
- control device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000010802 sludge Substances 0.000 title claims abstract description 52
- 238000000605 extraction Methods 0.000 title claims description 15
- 238000001556 precipitation Methods 0.000 title 1
- 230000006870 function Effects 0.000 claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000001932 seasonal effect Effects 0.000 claims abstract description 8
- 238000004062 sedimentation Methods 0.000 abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 5
- 230000002542 deteriorative effect Effects 0.000 abstract 1
- 238000000034 method Methods 0.000 description 4
- 230000006866 deterioration Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
Classifications
-
- 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
Landscapes
- Activated Sludge Processes (AREA)
- Treatment Of Sludge (AREA)
Abstract
Description
【０００１】[0001]
【産業上の利用分野】本発明は、プロセスコントローラ
などにより、初沈汚泥引抜制御を行う際に、階層型ニュ
ーラルネットワーク（以下、ＮＮと呼ぶ）を用いて最適
な制御を実現する初沈汚泥引抜制御装置に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to initial sludge extraction using a hierarchical neural network (hereinafter referred to as "NN") for optimum control when performing initial sludge extraction control by a process controller or the like. Regarding the control device.
【０００２】[0002]
【従来の技術】従来より、この種の初沈汚泥引抜制御装
置においては、複数の最初沈殿池に対し、引抜時間を固
定的に決定していると共に、サイクリックに順次引抜き
を行っており、結果的に累積された沈殿汚泥分布のアン
バランスを補正することが困難であった。2. Description of the Related Art Conventionally, in this type of initial settling sludge drawing-out control device, the drawing-out time is fixedly determined for a plurality of first settling basins, and the drawing is performed cyclically in sequence. As a result, it was difficult to correct the accumulated imbalance of sediment sludge distribution.
【０００３】最初沈殿池では、流入下水に含まれるＳＳ
（Ｓｕｓｐｅｎｄｅｄ Ｓｏｌｉｄ：浮遊性固形物）分
が重力作用により、沈殿する。この沈殿汚泥は、ＳＳ分
が濃縮したものであり、粘性の高い泥状有機物を含み、
腐敗しやすいため、短時間で排除する必要がある。初沈
汚泥引抜制御装置は、このための制御装置である。In the first sedimentation tank, SS contained in the inflowing sewage
The (Suspended Solid: floating solid matter) component is precipitated by the action of gravity. This settled sludge is one in which SS content is concentrated, and contains highly viscous mud-like organic matter,
Since it easily decomposes, it must be eliminated in a short time. The initial sludge extraction control device is a control device for this purpose.
【０００４】[0004]
【発明が解決しようとする課題】しかしながら、上述し
た従来の初沈汚泥引抜制御装置では、以下のような問題
があった。However, the above-mentioned conventional first sludge withdrawal control device has the following problems.
【０００５】（１）各最初沈殿池の汚泥分布状態とは無
関係に、固定的に引抜時間を決定しているため、流量分
布の不均等による補正ができず、結果的にそのアンバラ
ンスが累積してしまう。(1) Since the withdrawal time is fixedly determined regardless of the sludge distribution state of each primary sedimentation tank, it is not possible to correct due to the uneven flow distribution, and as a result the imbalance accumulates. Resulting in.
【０００６】（２）汚泥分布のアンバランスにより、Ｓ
Ｓ分の平均濃度に差がでるため、送り先である汚泥処理
プロセスに負荷をかけることになる。また、池内の沈殿
汚泥を適格に排除できない場合には、汚泥の腐敗などに
より、水質の悪化を増長させることになる。(2) Due to the unbalance of sludge distribution, S
Since there is a difference in the average concentration of S, the sludge treatment process, which is the destination, is loaded. In addition, if the settled sludge in the pond cannot be properly removed, the deterioration of water quality will be increased due to the deterioration of sludge.
【０００７】（３）流入水質の降雨や季節による変動に
対応できる柔軟性ある制御装置ではないために、無駄な
汚泥引抜を行う可能性があり、引抜ポンプの運転時間が
多くなり省エネルギ化が困難となる。また、引抜ポンプ
や引抜弁の動作頻度が多くなり、耐久性を低下させる問
題があった。(3) Since the control device is not a flexible control device that can cope with rainfall of the inflow water quality and fluctuations depending on the season, there is a possibility that wasteful sludge extraction will be performed, and the operation time of the extraction pump will increase, resulting in energy saving. It will be difficult. In addition, the operation frequency of the drawing pump and the drawing valve increases, and there is a problem that durability deteriorates.
【０００８】そこで、本発明の第１の目的は、上記欠点
に鑑み、汚泥流量分布の不均等を補正可能とした初沈汚
泥引抜制御装置を提供することである。In view of the above-mentioned drawbacks, a first object of the present invention is to provide an initial sludge withdrawal control device capable of correcting uneven distribution of sludge flow rate.
【０００９】また、本発明の第２の目的は、汚泥の腐敗
などによる水質の悪化を防止できる初沈汚泥引抜制御装
置を提供することである。A second object of the present invention is to provide an initial sludge withdrawal control device capable of preventing deterioration of water quality due to sludge rotting.
【００１０】さらに、本発明の第３の目的は、引抜ポン
プの運転時間を減少し省エネルギ化の要請に合致し、耐
久性を著しく向上させ得ることができる初沈汚泥引抜制
御装置を提供することである。Further, a third object of the present invention is to provide an initial sludge withdrawal control device which can reduce the operating time of the withdrawal pump and meet the demand for energy saving, and can remarkably improve the durability. That is.
【００１１】[0011]
【課題を解決するための手段】本発明によれば、複数の
最初沈殿池を運用する運用システムに係わる引き抜き時
間と引き抜きサイクル時間を制御する制御部を有する初
沈汚泥引抜制御装置であって、前記制御部は、前記複数
の最初沈殿池に係わる流入流量、汚泥引抜流量を積算
し、かつ引抜汚泥濃度を平均演算し、それぞれを最初沈
殿池の前回値として入力し、予め定められた降雨関数及
び季節関数に基づいて、汚泥分布のアンバランスを修正
するように、前記引き抜き時間及び引き抜きサイクル時
間を制御する階層型ニューラルネットワークを有するこ
とを特徴とするものである。According to the present invention, there is provided an initial sludge withdrawal control device having a control unit for controlling an withdrawal time and an withdrawal cycle time relating to an operation system for operating a plurality of first sedimentation basins, The control unit integrates the inflow flow rate and the sludge withdrawal flow rate associated with the plurality of first settling basins, and averages the drawn out sludge concentration, and inputs each as the previous value of the first settling basin, and a predetermined rainfall function. And a hierarchical neural network for controlling the extraction time and the extraction cycle time so as to correct the imbalance of the sludge distribution based on the seasonal function.
【００１２】また、本発明によれば、前記初沈汚泥引抜
制御装置において、前記階層型ニューラルネットワーク
は、入出力関数としてジグモイド関数を用いることを特
徴とするものである。Further, according to the present invention, in the initial sludge withdrawal control device, the hierarchical neural network uses a zigmoid function as an input / output function.
【００１３】また、本発明によれば、前記初沈汚泥引抜
制御装置において、前記流入流量と前記降雨関数及び前
記季節関数に対する経験則を導入し、その出力と前記各
最初沈殿池の前記引抜流量及び前記引抜汚泥濃度を自己
評価して、学習データを自己作成する自己作成ユニット
を設け、前記階層型ニューラルネットワークは、前記前
回値と前記自己作成された学習データとに基づいて、汚
泥分布のアンバランスを修正するように、前記引抜時間
及び引抜サイクル時間を制御する階層型ニューラルネッ
トワークを有することを特徴とするものである。Further, according to the present invention, in the initial sludge withdrawal control device, an empirical rule for the inflow flow rate, the rainfall function and the seasonal function is introduced, and its output and the withdrawal flow rate of each of the first settling basins are introduced. And self-assessment unit for self-assessment of learning data by self-assessing the drawn sludge concentration, the hierarchical neural network based on the previous value and the self-created learning data It is characterized by having a hierarchical neural network for controlling the withdrawal time and the withdrawal cycle time so as to correct the balance.
【００１４】[0014]
【作用】本発明においては、汚泥分布のアンバランスを
引き抜き時間と引き抜きサイクル時間で修正するための
制御パラメータを、ＮＮの学習機能により獲得して、未
学習データに対する十分な汎化能力を得る。In the present invention, the control function for correcting the unbalance of sludge distribution by the withdrawal time and the withdrawal cycle time is acquired by the learning function of the NN to obtain a sufficient generalization ability for unlearned data.
【００１５】[0015]
【実施例】以下、本発明の実施例を図面を参照して詳細
に説明する。図１は、本発明の１実施例を示すブロック
図である。１は１号，２号…の複数の最初沈殿池１1、
１2を運用する運用システムを示すもので、この運用シ
ステム１は最初沈殿池１1、１2の他に１号、２号引抜弁
１3、１4、汚泥引抜ポンプ１5、流量計１6、濃度計
１7、沈砂池１8から構成される。前記運用システム１は
階層型ニューラルネットワーク２により制御される。Embodiments of the present invention will now be described in detail with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of the present invention. 1 is a plurality of primary sedimentation tanks 1 1 , 2 ...
1 shows the operation system that operates 1 2. This operation system 1 is the first settling tank 1 1 and 1 2 as well as No. 1 and No. 2 extraction valves 1 3 and 1 4 , sludge extraction pump 1 5 and flow meter 1 6 , Consists of densitometer 17 and sand basin 18 The operation system 1 is controlled by a hierarchical neural network 2.
【００１６】まず、階層型ニューラルネットワーク２
は、図示しない入力ユニット、中間ユニット及び出力ユ
ニットの３層構造であり、入力ユニットは８個、出力ユ
ニットは３個から構成される。階層型ニューラルネット
ワーク２には、流量計１6からの出力を第１の積算器４
により積算した引抜流量Ａと、沈砂池１8に流入する流
量を第２の積算器５により積算した流入流量Ｃとを入力
し、さらに、濃度計１7の出力を平均演算器６により平
均化した引抜汚泥濃度Ｂを入力し、各最初沈殿池１1、
１2の前回値としてそれぞれ格納される。また、オペレ
ータにより設定された降雨関数Ｄ及び季節関数Ｅも階層
型ニューラルネットワーク２に入力される。First, the hierarchical neural network 2
Has a three-layer structure of an input unit, an intermediate unit, and an output unit (not shown), which includes eight input units and three output units. The output from the flowmeter 16 is fed to the first integrator 4 in the hierarchical neural network 2.
Input the withdrawal flow rate A accumulated by the above, and the inflow flow rate C obtained by integrating the flow rate flowing into the sand basin 18 by the second integrator 5, and further average the output of the densitometer 17 by the averaging calculator 6. Enter the extracted sludge concentration B and select each primary sedimentation tank 1 1 ,
It is stored as the previous value of 1 2 . Further, the rainfall function D and the seasonal function E set by the operator are also input to the hierarchical neural network 2.
【００１７】一方、流入流量Ｃと降雨関数Ｄ及び季節関
数Ｅを経験則部７に導入し、その出力と各最初沈殿池１
1、１2の引抜流量Ａ及び引抜汚泥濃度Ｂを自己評価して
自己評価部８に導入した後、学習データを自己作成する
自己作成ユニット９に導入し、このユニット９の出力が
階層型ニューラルネットワーク２に導入される。On the other hand, the inflow rate C, the rainfall function D, and the seasonal function E are introduced into the empirical rule section 7, and the output thereof and each first sedimentation tank 1
The self-assessment unit 8 that self-assess the self-assessment unit 8 for self-assessment of the withdrawal flow rate A and withdrawal sludge concentration B of 1 , 1 2 is introduced into the self-creation unit 9 which self-creates learning data, and the output of this unit 9 is a hierarchical neural network. Introduced into network 2.
【００１８】階層型ニューラルネットワーク２は、上述
の入力データと自己作成ユニットにより作成された学習
データとに基づいて、入出力関数としてシグモイド関数
を用いて、汚泥分布のアンバランスを修正するための制
御パラメータを獲得し、各最初沈殿池１1、１2の引き抜
き時間及び引き抜きサイクル時間を出力する。なお、Ｎ
Ｎを構成する各ユニット間の結合強度は、誤差出伝搬学
習法により、調整されている。The hierarchical neural network 2 uses a sigmoid function as an input / output function based on the above-mentioned input data and the learning data created by the self-creating unit to control the unbalance of sludge distribution. Obtain the parameters and output the withdrawal time and withdrawal cycle time of each primary sedimentation tank 1 1 , 1 2 . Note that N
The coupling strength between the units forming N is adjusted by the error out-propagation learning method.
【００１９】さらに、階層型ニューラルネットワーク２
の学習速度を高速に実行させるために、流入流量Ａと降
雨関数Ｄ及び季節関数Ｅを経験則部７に導入し、その出
力と各最初沈殿池１1、１2の引抜流量Ａ及び引抜汚泥濃
度Ｂを自己評価部８で自己評価して、学習データを自己
作成ユニット９で作成する。自己作成ユニット９で作成
されたされた学習データは、階層型ニューラルネットワ
ーク２に入力され、未学習データに対する汎化能力を付
与する。Further, the hierarchical neural network 2
In order to speed up the learning speed of 1., the inflow rate A, the rainfall function D, and the seasonal function E are introduced into the empirical rule section 7, and the output and the extraction flow rate A and the extraction sludge of each of the first settling basins 1 1 , 1 2 are introduced. The concentration B is self-evaluated by the self-evaluation unit 8, and learning data is created by the self-creating unit 9. The learning data created by the self-creating unit 9 is input to the hierarchical neural network 2 to give generalization ability to unlearned data.
【００２０】[0020]
【発明の効果】以上のべたように、本発明によれば、汚
泥分布のアンバランスを補正する最適な制御パラメータ
をＮＮの学習機能により獲得し、引き抜き時間と引き抜
サイクル時間を自動的に修正できるから、以下の効果が
得られる。As described above, according to the present invention, the optimum control parameter for correcting the unbalance of sludge distribution is acquired by the learning function of the NN, and the extraction time and the extraction cycle time are automatically corrected. Therefore, the following effects can be obtained.
【００２１】（１）各最初沈殿池間の汚泥分布を均等化
できる。(1) The sludge distribution among the first settling basins can be equalized.
【００２２】（２）後段における各種プロセスの負荷を
軽減すると共に、処理水質の向上に寄与できる。(2) The load of various processes in the latter stage can be reduced and the quality of treated water can be improved.
【００２３】（３）不要な汚泥引き抜きを排除できるた
め、汚泥ポンプの運転時間の短縮化が図れ、汚泥ポンプ
と引き抜き等の動作回数を低減できるから，長寿命化が
図れる。(3) Since unnecessary sludge withdrawal can be eliminated, the operating time of the sludge pump can be shortened, and the number of operations such as sludge pump and withdrawal can be reduced, so that the service life can be extended.
【図１】本発明の１実施例を示すブロック図である。FIG. 1 is a block diagram showing an embodiment of the present invention.
１…運用システム ２…階層型ニューラルネットワーク ４、５…第２の積算器 ６…平均演算器 ７…経験則部 ８…自己評価部 ９…自己作成ユニット（学習データ） 1 ... Operation system 2 ... Hierarchical neural network 4, 5 ... Second integrator 6 ... Average calculator 7 ... Experience rule part 8 ... Self-evaluation part 9 ... Self-creation unit (learning data)
Claims (3)
ムに係わる引き抜き時間と引き抜きサイクル時間を制御
する制御部を有する初沈汚泥引抜制御装置であって、 前記制御部は、前記複数の最初沈殿池に係わる流入流
量、汚泥引抜流量を積算し、かつ引抜汚泥濃度を平均演
算し、それぞれを各最初沈殿池の前回値として入力する
とともに、予め定められた降雨関数及び季節関数に基づ
いて、汚泥分布のアンバランスを修正するように、前記
引き抜き時間及び引き抜きサイクル時間を制御する階層
型ニューラルネットワークを有することを特徴とする初
沈汚泥引抜制御装置。1. A first settling sludge withdrawal control device having a control unit for controlling a withdrawal time and an withdrawal cycle time relating to an operation system for operating a plurality of first settling basins, wherein the control unit has the plurality of first settling tanks. The inflow flow rate and the sludge extraction flow rate related to the pond are integrated, the extracted sludge concentration is averaged, and each is input as the previous value of each first settling tank, and the sludge is calculated based on the predetermined rainfall function and seasonal function. An initial sludge withdrawal control device having a hierarchical neural network for controlling the withdrawal time and withdrawal cycle time so as to correct the imbalance of distribution.
おいて、 前記階層型ニューラルネットワークは、入出力関数とし
てジグモイド関数を用いることを特徴とする初沈汚泥引
抜制御装置。2. The initial sludge withdrawal control device according to claim 1, wherein the hierarchical neural network uses a sigmoid function as an input / output function.
おいて、 前記流入流量と前記降雨関数及び前記季節関数に対する
経験則を導入し、その出力と前記各最初沈殿池の前記引
抜流量及び前記引抜汚泥濃度を自己評価して、学習デー
タを自己作成する自己作成ユニットを設け、 前記階層型ニューラルネットワークは、前記前回値と前
記自己作成された学習データとに基づいて、汚泥分布の
アンバランスを修正するように、前記引抜時間及び引抜
サイクル時間を制御する階層型ニューラルネットワーク
を有することを特徴とする初沈汚泥引抜制御装置。3. The initial sludge withdrawal control device according to claim 2, wherein an empirical rule for the inflow rate, the rainfall function and the seasonal function is introduced, and its output and the withdrawal rate and the withdrawal flow rate of each of the first settling basins. The self-assessment unit for self-assessing the drawn sludge concentration and self-creating the learning data is provided, and the hierarchical neural network, based on the previous value and the self-created learning data, unbalances the sludge distribution. An initial sludge withdrawal control device comprising a hierarchical neural network for controlling the withdrawal time and the withdrawal cycle time so as to be modified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP5102074A JPH06312104A (en) | 1993-04-28 | 1993-04-28 | Initial precipitation sludge extraction control device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP5102074A JPH06312104A (en) | 1993-04-28 | 1993-04-28 | Initial precipitation sludge extraction control device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH06312104A true JPH06312104A (en) | 1994-11-08 |
Family
ID=14317628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP5102074A Pending JPH06312104A (en) | 1993-04-28 | 1993-04-28 | Initial precipitation sludge extraction control device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH06312104A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908111A (en) * | 2017-11-27 | 2018-04-13 | 北华大学 | A kind of computer control method of the sludge dewatering system based on BP neural network |
| CN109111030A (en) * | 2018-08-27 | 2019-01-01 | 重庆固润科技发展有限公司 | Integrated sewage disposal intelligence control system and control method |
-
1993
- 1993-04-28 JP JP5102074A patent/JPH06312104A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908111A (en) * | 2017-11-27 | 2018-04-13 | 北华大学 | A kind of computer control method of the sludge dewatering system based on BP neural network |
| CN109111030A (en) * | 2018-08-27 | 2019-01-01 | 重庆固润科技发展有限公司 | Integrated sewage disposal intelligence control system and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4334317B2 (en) | Sewage treatment system | |
| CZ282411B6 (en) | Waste or sewage water treatment and apparatus for making the same | |
| JP6621866B2 (en) | Operation support device and operation support method for sewage treatment plant using activated sludge method | |
| JP4649175B2 (en) | Sewage treatment plant control equipment | |
| JP2001353497A (en) | Mobile membrane separation unit | |
| KR100978706B1 (en) | Wastewater treatment unit | |
| JPH07115025B2 (en) | Bulking control method using SVI | |
| JPH06335694A (en) | Controller of device for biologically treating waste water | |
| JPH10286585A (en) | Aeration air volume control device | |
| JPH0147238B2 (en) | ||
| JP2017121595A (en) | Monitor and control system using activated-sludge process | |
| SU861343A1 (en) | Device for automatic control of loading of wastewater biological purification units | |
| HUP0300628A2 (en) | Improvements to waste water treatment using activated sludge process | |
| JPS625036B2 (en) | ||
| US5308490A (en) | Sewage delivery for an activated sludge process | |
| JPS61227894A (en) | Batch device for treating filthy water | |
| JP2921159B2 (en) | Filtration Pond Control Method by Fuzzy Inference | |
| JPH06312105A (en) | Filter control device | |
| Deena et al. | Artificial intelligence based control approach for membrane bioreactor in sewage water treatment | |
| JP2003126881A (en) | Sludge concentration controller and wastewater treatment system provided with the same | |
| JPS61263688A (en) | Device for controlling use of water in water purification plant | |
| JP6805024B2 (en) | Water treatment equipment and treatment methods for water treatment processes | |
| JPH03258312A (en) | Automatic washing device for rapid filtration pool | |
| JPH01310184A (en) | Pump controller | |
| CN108217947A (en) | A kind of batch-type control method of sewage disposal AO and AAO techniques |