JP2002126721A - Method and apparatus for controlling injection ratio of chemicals - Google Patents
Method and apparatus for controlling injection ratio of chemicalsInfo
- Publication number
- JP2002126721A JP2002126721A JP2000320743A JP2000320743A JP2002126721A JP 2002126721 A JP2002126721 A JP 2002126721A JP 2000320743 A JP2000320743 A JP 2000320743A JP 2000320743 A JP2000320743 A JP 2000320743A JP 2002126721 A JP2002126721 A JP 2002126721A
- Authority
- JP
- Japan
- Prior art keywords
- injection rate
- chemical injection
- water
- value
- quality
- 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.)
- Granted
Links
Landscapes
- Feeding, Discharge, Calcimining, Fusing, And Gas-Generation Devices (AREA)
Abstract
Description
【０００１】[0001]
【発明の属する技術分野】本発明は、薬品注入制御方法
及びその装置に関するものである。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for controlling chemical injection.
【０００２】[0002]
【従来の技術】我が国における一般的な浄水設備として
は、凝集沈殿＋砂ろ過＋塩素消毒を主要なプロセスとし
て用いているところが多い。2. Description of the Related Art Many common water purification facilities in Japan use coagulation sedimentation + sand filtration + chlorination as main processes.
【０００３】原水水質によっては河川からの導水管内に
粉末活性炭処理を設置したり、異臭味物質や有機物処理
を目的としてさらにオゾン＋活性炭処理を付帯している
所もある。また、これらの設備に合せて、主に凝集剤、
塩素、アルカリ剤等を薬品として注入している。[0003] Depending on the quality of raw water, there is a place where a powdered activated carbon treatment is installed in a water pipe from a river, and an ozone + activated carbon treatment is additionally provided for the treatment of off-flavor substances and organic substances. In addition, according to these facilities, mainly coagulant,
Chlorine and alkaline agents are injected as chemicals.
【０００４】図６に基づいて浄水設備の問題とその対策
について述べる。図６は、急速ろ過器の浄水場にオゾン
・活性炭による高度浄水処理設備を付加した事例の一例
である。[0004] The problem of the water purification equipment and its countermeasures will be described with reference to FIG. FIG. 6 is an example of a case where an advanced water purification treatment facility using ozone and activated carbon is added to a water purification plant of a rapid filter.
【０００５】浄水設備に流入する原水は、湖沼３１、河
川３３及び原水調整池３５から供給される。着水井３７
に導入された原水は、急速混和池３９において添加され
た凝集剤と均一に混ざり合い、フロック形成池４１にお
いては沈降性のフロックを得るために緩やかに攪拌され
る。フロック形成池４１において原水中の汚濁物質が凝
集し形成したフロックは、沈殿池143において固液分離
される。固液分離処理水は、急速ろ過池５１に供給され
るが、さらに異臭味物質や溶存性有機物の処理を施す場
合は、高度浄水処理設備４５に移送される。高度浄水処
理設備４５に導入された固液分離処理水中の異臭成分や
溶存性有機物成分は、オゾン接触池４７において、オゾ
ン発生装置４４から供給されたオゾンによって酸化処理
される。オゾン処理された固液分離処理水は、活性炭吸
着池４９において処理された後、急速ろ過池５１に供給
される。ろ過処理水は、浄水池５３、配水池５５を介し
て上水として利用されて一部は放流される。[0005] Raw water flowing into the water purification facility is supplied from a lake 31, a river 33, and a raw water regulating pond 35. Irrigation well 37
Is uniformly mixed with the coagulant added in the rapid mixing pond 39, and is gently stirred in the floc forming pond 41 in order to obtain a settling floc. The flocs formed by flocculation of the pollutants in the raw water in the floc forming pond 41 are separated into solid and liquid in the settling pond 143. The solid-liquid separation treatment water is supplied to the rapid filtration pond 51, and is further transferred to the advanced water purification treatment facility 45 when the treatment of the off-flavor substance or the dissolved organic substance is further performed. Offensive odor components and dissolved organic components in the solid-liquid separation treatment water introduced into the advanced water purification treatment equipment 45 are oxidized by the ozone supplied from the ozone generator 44 in the ozone contact pond 47. The ozone-treated solid-liquid separation treatment water is treated in the activated carbon adsorption pond 49 and then supplied to the rapid filtration pond 51. The filtered water is used as clean water through the water purification reservoir 53 and the distribution reservoir 55, and a part of the water is discharged.
【０００６】近年の原水水質の悪化、除去対象物質の多
様化に伴い、先に挙げた薬品注入プロセスも複雑化して
いる。原水水質悪化の具体例の一つとして、湖沼131に
おける富栄養化現象であり、これは湖沼３１周辺の住宅
地や耕地等から流入した生活排水や肥料由来の窒素、リ
ン等を含んだ地下水等から起因している。そして、この
湖沼131の水が河川３３に流れ込んだ場合、河川汚濁の
原因となっている。[0006] With the recent deterioration of raw water quality and the diversification of substances to be removed, the above-described chemical injection process has become complicated. One specific example of the deterioration of the raw water quality is the eutrophication phenomenon in the lake 131, which includes domestic wastewater flowing from residential and arable land around the lake 31 and groundwater containing nitrogen, phosphorus, etc. derived from fertilizers. Is caused by When the water of the lake 131 flows into the river 33, it causes river pollution.
【０００７】これにより、上水設備内においてはアンモ
ニア性窒素、鉄、マンガン等、塩素要求量物質の存在、
フロック形成池や沈殿池においては、前塩素処理による
トリハロメタンなどの消毒副生成物質の増加、凝集・沈
殿障害等によって固液分離処理水の濁度が悪化する結果
となる。また、高度浄水処理設備においてはオゾン接触
池におけるオゾン副生成物質の残留や活性炭吸着池にお
ける生物漏洩、急速ろ過池においてはろ過機能低下によ
るクリプトスポリジウムの漏洩等の二次的障害を引き起
こす結果となっている。さらに、設備の老朽化、例えば
埋設配管の老朽等が、処理水質の悪化の原因となる場合
もある。As a result, the presence of chlorine demand substances such as ammoniacal nitrogen, iron, manganese, etc.
In a floc forming pond or a sedimentation pond, the turbidity of the solid-liquid separation treatment water is deteriorated due to an increase in disinfecting by-products such as trihalomethane due to the pre-chlorination treatment, coagulation and sedimentation obstacles. In addition, in advanced water treatment facilities, secondary obstacles such as residual ozone by-products in the ozone contact pond and biological leakage in the activated carbon adsorption pond, and leakage of cryptosporidium due to reduced filtration function in the rapid filtration pond may result. ing. Further, aging of facilities, for example, aging of buried pipes, and the like, may cause deterioration of treated water quality.
【０００８】これらの問題に対して、浄水設備の原水供
給源となる河川３３においては、上流側と下流側の浄水
設備付近に、水質監視装置３２，３４を設置して、常
時、流入原水の水質監視を行なっている。[0008] In order to solve these problems, in the river 33 serving as a raw water supply source of the water purification equipment, water quality monitoring devices 32 and 34 are installed near the upstream and downstream water purification equipment so that the inflowing raw water is constantly provided. Monitors water quality.
【０００９】そして、浄水設備においては、従来の凝集
沈殿＋砂ろ過＋塩素処理による汚濁物質除去・殺菌のみ
ならず、アンモニア対策として急速混和池３９の手前に
低濃度ＵＶ計３６と三態窒素計３８を設置して、常時水
質を監視しながら水質の変動に併せて、塩素処理等が施
されている。また、トリハロメタン生成を低減化するた
めの中間塩素処理、さらに後処理として水道管保護のた
めのアルカリ処理等などが実施されている。高度浄水処
理設備においては、流入側と排出側に低濃度ＵＶ計４
２，４８を配置し、またオゾン接触池４７には溶存オゾ
ン計を設置して、設備の機能評価を行い、オゾン接触量
や活性炭の洗浄や交換についての検討を行なっている。
急速ろ過池５１においては、近年になって問題になって
いるクリプトスポリジウム対策として砂ろ過プロセス流
出水の濁度監視が重要となり、凝集剤注入の調整も再び
脚光を浴びている。そこで、濁色度計４０や高感度濁度
計５０，５２を設置して、ろ過池の性能判断やろ材交
換、さらには着水井３７や急速混和池３９における凝集
剤注入の調整の検討などを行なっている。In the water purification equipment, not only the conventional method of removing and sterilizing pollutants by coagulation sedimentation + sand filtration + chlorination, but also a low-concentration UV meter 36 and a three-phase nitrogen meter before the rapid mixing pond 39 as a measure against ammonia. 38 is installed, and chlorination and the like are performed according to fluctuations in water quality while constantly monitoring the water quality. Further, an intermediate chlorination treatment for reducing trihalomethane production and an alkali treatment for protecting a water pipe as a post-treatment are performed. In advanced water treatment facilities, low concentration UV meters 4
2 and 48 are installed, and a dissolved ozone meter is installed in the ozone contact pond 47 to evaluate the function of the equipment and to examine the ozone contact amount and the cleaning and replacement of activated carbon.
In the rapid filtration pond 51, turbidity monitoring of the sand filtration process effluent has become important as a measure against Cryptosporidium, which has recently become a problem, and adjustment of coagulant injection has been spotlighted again. Therefore, the turbidity meter 40 and the high-sensitivity turbidity meters 50 and 52 are installed to evaluate the performance of the filtration basin, replace the filter medium, and examine the adjustment of coagulant injection in the landing well 37 and the rapid mixing basin 39. I do.
【００１０】埋設管老朽問題については、設備内の配水
管網５７の適所に配水水質モニタ５４を配置して、配水
の水質を監視しながら設備内の汚染源や老朽手段分の探
索を行なって、必要とあらば修繕を施している。Regarding the problem of aging of buried pipes, a distribution water quality monitor 54 is arranged at an appropriate place of a distribution pipe network 57 in the facility, and while monitoring the water quality of the distribution water, a search is made for a pollution source and aging means in the facility. Repairs are applied if necessary.
【００１１】以上述べたように、良好な水質が得られて
いる浄水設備においては、熟練した操作員の豊富な経験
を頼りに薬品注入による水質制御などの運転管理が実施
されているのが現状である。また、各地で水質が違うの
で、各々の浄水場で水質制御方法が構築されているのが
現状である。[0011] As described above, in the water purification equipment where good water quality is obtained, operation management such as water quality control by chemical injection is performed based on the abundant experience of skilled operators. It is. In addition, since the water quality is different in each place, it is the present condition that each water treatment plant has a water quality control method.
【００１２】[0012]
【発明が解決しようとする課題】今日の浄水設備におけ
る運転調整、例えば薬品注入率の調整は、手動操作で行
なわれているのがほとんどである。薬品注入率の調整
は、設計計算から算出された基本注入率に基づいて、操
作員が現場においてジャーテストによる凝集剤やアルカ
リ剤等の薬品注入率の決定を行うのが一般的な手段であ
る。In most cases, the operation adjustment in today's water purification equipment, for example, the adjustment of the chemical injection rate, is performed manually. In general, the adjustment of the chemical injection rate is based on the basic injection rate calculated from the design calculation, in which the operator determines the injection rate of the coagulant, alkali agent, or the like by a jar test at the site. .
【００１３】しかし、ジャーテストによる薬品注入率の
最終的な判断基準は、操作員の豊富な実務経験とそれに
培われた勘によるものがほとんどである。このように薬
品注入率の決定判断は主観的な傾向があるので、判断ミ
スも少なくはなく、被処理水の特性に対する最適な薬品
注入率は決定するのが難しいのが現状である。However, the final criterion for judging the chemical injection rate by the jar test is mostly based on the abundant practical experience of the operator and the intuition cultivated therefrom. As described above, the determination of the chemical injection rate has a subjective tendency, so that there are not few errors in determination, and it is presently difficult to determine the optimum chemical injection rate for the characteristics of the water to be treated.
【００１４】また、被処理水質の変動、季節の変化に伴
い、同じ水質でも薬品注入率が異なる状況が多々ある。
そのため、状況分析能力と適確な対応能力を備えた熟練
操作員なしには薬品注入率の決定や設備の性能維持を図
ることは困難となり、常に操作員を常駐させておく状況
となっている。そして、改造などで設備の動特性が変化
した場合には、前記と同様に、薬品注入率が変化してし
まうことがある。[0014] In addition, there are many situations in which the chemical injection rate is different even with the same water quality due to fluctuations in the quality of the water to be treated and changes in seasons.
For this reason, it is difficult to determine the chemical injection rate and maintain the performance of the equipment without a skilled operator with the ability to analyze the situation and the appropriate response capability, and the operator is always stationed. . If the dynamic characteristics of the equipment change due to modification or the like, the chemical injection rate may change in the same manner as described above.
【００１５】さらに、近年、水質に対する要求が多くな
っており、濁度除去だけでなく発ガン性物質の生成量低
減も求められている。しかしながら、これらの項目を同
時に安定化させることは非常に難しい。また、薬品を多
量に使用してしまうことも懸念される。Furthermore, in recent years, there has been an increasing demand for water quality, and not only removal of turbidity but also reduction of the amount of carcinogenic substances generated has been demanded. However, it is very difficult to stabilize these items at the same time. In addition, there is a concern that a large amount of chemicals will be used.
【００１６】本発明は、上記の事情に鑑み創作されたも
ので、変動しやすい原水の特性に対して優れた学習能力
と自己性能診断能力とを備えた水質制御方法を新たに提
供することを目的とする。The present invention has been made in view of the above-mentioned circumstances, and provides a new water quality control method having excellent learning ability and self-performance diagnosis ability with respect to the characteristics of raw water that is easily changed. Aim.
【００１７】[0017]
【課題を解決するための手段】前記課題を解決するため
の、請求項１記載の本発明に係る薬品注入制御方法は、
原水の水質と薬品の注入率とをニューラルネットワーク
に供給して、処理水の水質を予測した後、この予測値を
目標値と比較し、この比較結果に基づき、該薬品注入率
を調整する薬品注入率制御方法であって、該予測値が目
標値以下である場合、該薬品注入率を、該原水に対し適
正な薬品注入率として採用し、該予測値が目標値以上で
ある場合、該薬品注入率を、演算によって補正した後
に、再度、前記ニューラルネットワークに供給するこ
と、を特徴としている。According to a first aspect of the present invention, there is provided a method for controlling chemical injection according to the present invention.
The water quality of the raw water and the injection rate of the chemical are supplied to the neural network to predict the water quality of the treated water. Then, the predicted value is compared with a target value, and a chemical for adjusting the chemical injection rate based on the comparison result. In the injection rate control method, when the predicted value is equal to or less than the target value, the chemical injection rate is adopted as an appropriate chemical injection rate for the raw water, and when the predicted value is equal to or more than the target value, The method is characterized in that the chemical injection rate is corrected by calculation and then supplied to the neural network again.
【００１８】また、請求項２記載の本発明に係る薬品注
入制御方法は、原水の水質と薬品の注入率とをニューラ
ルネットワークに供給して、処理水の水質を予測した
後、この予測値を目標値と比較し、この比較結果に基づ
き、該薬品注入率を調整する薬品注入率制御方法であっ
て、薬品が凝集剤とアルカリ剤である場合、予測値が目
標値以下となる凝集剤とアルカリ剤の注入率が最小とな
るように、該薬品の注入率を調整すること、を特徴とし
ている。According to a second aspect of the present invention, there is provided a chemical injection control method according to the present invention, wherein the quality of raw water and the injection rate of chemicals are supplied to a neural network to predict the quality of treated water. A method for controlling a chemical injection rate, which adjusts the chemical injection rate based on a result of comparison with a target value, wherein when the chemicals are a coagulant and an alkaline agent, a predicted value is equal to or less than the target value. The injection rate of the chemical is adjusted so that the injection rate of the alkali agent is minimized.
【００１９】さらに、請求項３記載の本発明に係る薬品
注入率制御方法は、原水の水質と薬品の注入率とをニュ
ーラルネットワークに供給して、処理水の水質を予測し
た後、この予測値を目標値と比較し、この比較結果に基
づき、該薬品注入率を調整する薬品注入率制御方法であ
って、薬品が凝集剤と塩素剤である場合、予測値が目標
値以下となる凝集剤とアルカリ剤の注入率が最小となる
ように、該薬品の注入率を調整すること、を特徴として
いる。Furthermore, in the chemical injection rate control method according to the present invention, the quality of the raw water and the injection rate of the chemical are supplied to the neural network to predict the quality of the treated water. Is compared with a target value, and based on the result of the comparison, a chemical injection rate control method for adjusting the chemical injection rate, wherein when the chemicals are a coagulant and a chlorine agent, the predicted value is less than or equal to the target value. And the injection rate of the chemical is adjusted so that the injection rate of the alkaline agent is minimized.
【００２０】また、請求項４に記載されたように、前記
処理水の水質指標が、濁度であって、この予測値と実績
値との偏差が、一定時間、一定値範囲以外である場合、
前記ニューラルネットワークに再学習させるとよい。According to a fourth aspect of the present invention, when the water quality index of the treated water is turbidity, and the deviation between the predicted value and the actual value is out of a certain value range for a certain time. ,
The neural network may be re-learned.
【００２１】さらに、請求項５に記載されたように、前
記処理水の水質指標が、濁度及びUV-VISであって、これ
らの予測値と実績値との偏差が一定値範囲以外である場
合、前記ニューラルネットワークに再学習させてもよ
い。Further, as described in claim 5, the water quality index of the treated water is turbidity and UV-VIS, and the deviation between the predicted value and the actual value is out of a certain value range. In this case, the neural network may be re-learned.
【００２２】以上の解決手段において、原水の水質指標
としては、水温、pH、濁度、アルカリ度、導電率、導電
率偏差（現在値−６時間前）、凝集剤（例えば、ポリ塩
化アルミニウム（ＰＡＣ））注入率、前アルカリ注入
率、前塩素注入率及びUV-VISの１０項目が、また処理水
の水質指標としては、濁度及びUV-VISの２項目が採用さ
れている。In the above solution, the water quality index of raw water includes water temperature, pH, turbidity, alkalinity, conductivity, conductivity deviation (current value minus 6 hours before), coagulant (for example, polyaluminum chloride ( PAC)) Injection rate, pre-alkali injection rate, pre-chlorine injection rate and 10 items of UV-VIS, and two items of turbidity and UV-VIS are adopted as water quality indicators of treated water.
【００２３】ここで、前アルカリとは、凝集沈殿処理工
程の前工程において、原水のアルカリ度及びpHを調整す
るために添加されるアルカリ剤のことをいい、例えば苛
性ソーダがある。また、前塩素とは、原水に藻類が混入
している時に、凝集沈殿処理工程の前工程において、凝
集性改善の目的で添加される塩素剤のことをいう。さら
に、処理水は凝集沈殿処理工程で固液分離された上澄水
のことをいう。Here, the pre-alkali refers to an alkali agent added for adjusting the alkalinity and pH of raw water in the pre-step of the coagulation-sedimentation treatment step, such as caustic soda. In addition, pre-chlorine refers to a chlorine agent added for the purpose of improving cohesiveness in a process preceding the coagulation-sedimentation treatment process when algae are mixed in raw water. Further, the treated water refers to supernatant water that has been subjected to solid-liquid separation in the coagulation-sedimentation treatment step.
【００２４】ニューラルネットワークの構成は、例え
ば、入力層と、中間層と、出力層とから成り、各層のニ
ューロン数としては、入力層においては１０、中間層に
おいては１０または１５、出力層においては２とし、各
ニューロンの伝達関数にシグモイド関数を採用してい
る。また、学習手段としては、バックプロパゲーション
法またはこの変法が用いられる。The configuration of the neural network includes, for example, an input layer, an intermediate layer, and an output layer. The number of neurons in each layer is 10 in the input layer, 10 or 15 in the intermediate layer, and 10 or 15 in the output layer. 2, and the sigmoid function is adopted as the transfer function of each neuron. As a learning means, a back propagation method or a modification thereof is used.
【００２５】尚、薬品注入率の補正は、加算法を用いて
いる。The correction of the chemical injection rate uses an addition method.
【００２６】薬品注入率の調整は、薬品注入率の初期値
を過去のデータに基づき、低めに設定し、この設定値に
一定値づつ加算していき、加算毎に予測した処理水質を
目標水質と比較することで、最小の薬品注入率を決定す
る。ここで、複数種類の薬品が注入される場合、総薬品
注入率も考慮される。尚、加算される値は、任意に設定
できる。To adjust the chemical injection rate, the initial value of the chemical injection rate is set lower based on past data, and the set value is added by a constant value, and the treated water quality predicted for each addition is set to the target water quality. By comparing with, the minimum chemical injection rate is determined. Here, when a plurality of types of drugs are injected, the total drug injection rate is also considered. The value to be added can be set arbitrarily.
【００２７】そして、前述の解決手段を実施するため
の、請求項６記載の本発明に係る薬品注入率制御装置
は、原水の水質と薬品注入率をニューラルネットワーク
に供給して処理水の水質を予測する水質予測手段と、前
記水質の予測値と目標値とを比較する比較手段と、前記
比較手段における比較結果に基づき、演算によって該薬
品注入率を補正する薬品注入率補正手段とを備えたこと
を特徴としている。A chemical injection rate control apparatus according to a sixth aspect of the present invention for implementing the above-mentioned solution means supplies the quality of raw water and the chemical injection rate to a neural network to adjust the quality of treated water. Water quality prediction means for predicting, comparison means for comparing the predicted value of water quality with a target value, and chemical injection rate correction means for correcting the chemical injection rate by calculation based on the comparison result in the comparison means. It is characterized by:
【００２８】ここで、前記比較手段は、該予測値が目標
値以上である場合、該薬品注入率を、該原水に対し適正
な薬品注入率として判断し、予測値が目標値以上である
場合、該薬品注入率を適正でないと判断する。そして、
前記薬品注入率補正手段は、前記比較手段において該予
測値が目標値以上であると判断された場合、該薬品注入
率の補正を実行する。尚、補正された薬品注入率は、再
度、前記水質予測手段のニューラルネットワークによる
演算に供される。Here, when the predicted value is equal to or more than the target value, the comparing means judges the chemical injection rate as an appropriate chemical injection rate for the raw water, and when the predicted value is equal to or more than the target value. It is determined that the chemical injection rate is not appropriate. And
The chemical injection rate correction means executes correction of the chemical injection rate when the comparing means determines that the predicted value is equal to or more than the target value. It should be noted that the corrected chemical injection rate is again used for the calculation by the neural network of the water quality prediction means.
【００２９】また、請求項７記載の本発明に係る薬品注
入率制御装置は、請求項６記載の薬品注入率制御装置に
おいて、薬品注入率補正手段は、処理水の水質の予測値
が目標値以下となる薬品注入率が最小となるように、該
薬品注入率を演算によって補正すること、を特徴とす
る。According to a seventh aspect of the present invention, in the chemical injection rate control device according to the sixth aspect of the present invention, the chemical injection rate correction means may be configured so that the predicted value of the quality of the treated water is a target value. The chemical injection rate is corrected by calculation so that the following chemical injection rate is minimized.
【００３０】さらに、請求項８記載の本発明に係る薬品
注入制御装置は、請求項６記載の薬品注入率制御装置に
おいて、水質予測手段は、前記比較手段が、前記処理水
の水質指標が濁度であって、この予測値と実績値との偏
差が、一定時間、一定値範囲以外である、と判断した場
合、ニューラルネットワークの再学習を実行すること、
を特徴としている。Further, in the chemical injection control device according to the present invention according to claim 8, in the chemical injection rate control device according to claim 6, the water quality estimating means includes: the comparing means; Degree, and the deviation between the predicted value and the actual value is determined to be out of the fixed value range for a certain period of time.
It is characterized by.
【００３１】また、請求項９記載の本発明に係る薬品注
入率制御装置は、請求項６または７記載の薬品注入率制
御装置において、水質予測手段は、前記比較手段が、前
記処理水の水質指標が濁度及びUV-VISであって、これら
の予測値と実績値との偏差が一定値範囲以外である、と
判断した場合、ニューラルネットワークの再学習を実行
すること、を特徴としている。According to a ninth aspect of the present invention, in the chemical injection rate control apparatus according to the sixth or seventh aspect, the water quality predicting means is such that: When the indices are turbidity and UV-VIS, and it is determined that the deviation between the predicted value and the actual value is out of a certain value range, the neural network is re-learned.
【００３２】[0032]
【発明の実施の形態】以下、本発明の実施形態を図面に
基づいて説明する。Embodiments of the present invention will be described below with reference to the drawings.
【００３３】発明者らは、凝集剤等の薬品を用いた水質
制御システムにおいて、ニューラルネットによる水質予
測を利用した新たな薬品注入制御システムを創出した。 （第１実施形態）図１は、本発明に係る薬品注入制御シ
ステムの構成図である。The present inventors have created a new chemical injection control system utilizing a water quality prediction by a neural network in a water quality control system using a chemical such as a flocculant. (First Embodiment) FIG. 1 is a configuration diagram of a chemical injection control system according to the present invention.
【００３４】当該制御システムは、水質予測手段１１
と、比較手段１２と、薬品注入率算出手段１３と、ベー
タベース１４とから構成され、これらは図示省略された
制御手段によって実行制御される。The control system includes a water quality prediction means 11
, A comparison means 12, a chemical injection rate calculation means 13, and a beta base 14, which are controlled by a control means (not shown).
【００３５】水質予測手段１１は、供給されたデータか
らニューラルネットワークによって一定時間後の処理水
の水質を予測する機能を有している。ニューラルネット
ワークは、脳の情報処理方式を工学的に模擬しようとす
るものであり、これまでの信号処理方式とは原理的に異
なり、一般的に入出力関係が非線形性であっても表現が
可能であり、さらに学習による適応性を備えた特徴を持
っている。したがって、ニューラルネットワークを、浄
水プラントの運転制御に対し、優れた学習性と自己性能
診断能力を備えた熟練操作員に模して、適応させること
ができる。ここでは、水質データと、薬品注入率が、当
該ネットワークの入力因子として供給される。水質予測
手段１１については、後に詳細に説明する。The water quality predicting means 11 has a function of predicting the quality of treated water after a certain period of time from the supplied data by a neural network. Neural networks attempt to simulate the information processing system of the brain in terms of engineering, and are fundamentally different from conventional signal processing systems. In general, they can be expressed even if the input / output relationship is nonlinear. , And has a feature of adaptability by learning. Therefore, the neural network can be adapted to the operation control of the water purification plant by imitating a skilled operator having excellent learning ability and self-performance diagnosis ability. Here, the water quality data and the chemical injection rate are supplied as input factors of the network. The water quality prediction means 11 will be described later in detail.
【００３６】比較手段１２は、図示省略された入力手段
あるいはデータベース１４から供給された目標値（目標
水質）と、水質予測手段１１から供給された予測値（予
測水質）との、比較を行う。そして、予測値が目標値以
下である場合、前記の水質予測手段１１に供給された薬
品注入率は適性であると判断する。一方、目標値と予測
値との比較により、予測値が目標値以上である場合、該
薬品注入率は適正でないと判断する。The comparing means 12 compares the target value (target water quality) supplied from the input means or the database 14 (not shown) with the predicted value (predicted water quality) supplied from the water quality predicting means 11. When the predicted value is equal to or smaller than the target value, the chemical injection rate supplied to the water quality predicting unit 11 is determined to be appropriate. On the other hand, by comparing the target value with the predicted value, if the predicted value is equal to or larger than the target value, it is determined that the chemical injection rate is not appropriate.
【００３７】薬品注入率補正手段１３は、比較手段１２
において現行の薬品注入率（例えば薬品注入率の初期
値）が適性でないと判断されると、該薬品注入率を演算
によって補正する。具体的には、加算法によって薬品注
入率初期値を補正する。補正された薬品注入率は、再
度、水質予測手段１１における水質予測に供される。The chemical injection rate correcting means 13 comprises a comparing means 12
If it is determined that the current drug injection rate (for example, the initial value of the drug injection rate) is not appropriate, the drug injection rate is corrected by calculation. Specifically, the initial value of the chemical injection rate is corrected by the addition method. The corrected chemical injection rate is used again for water quality prediction by the water quality prediction means 11.
【００３８】データベース１４は、外手段から供給され
た水質データや薬品注入率、また比較手段１２から供給
された薬品注入率を、引き出し可能に保存し、メモリ等
の記憶手段に格納されている。The database 14 stores the water quality data and the chemical injection rate supplied from the external means and the chemical injection rate supplied from the comparison means 12 in a retrievable manner and is stored in a storage means such as a memory.
【００３９】次に、水質予測手段１１について説明す
る。Next, the water quality prediction means 11 will be described.
【００４０】水質予測手段１１は、本実施形態におい
て、ニューラルネットワークへの入出力因子の一例とし
て、入力因子に原水の水質と薬品注入率を、出力因子に
処理水の濁度とUV-VISを選択している。ネットワークの
学習アルゴリズムとしては、バックプロパゲーション法
を採用している。尚、バックプロパゲーション法は演算
時間を多く必要とするので、当該学習手段にモーメンタ
ム法若しくはLevenberg-Marquardt最適化手法を備える
ことにより、学習の高速化を図っている。In the present embodiment, the water quality predicting means 11 includes, as an example of input / output factors to / from the neural network, input factors such as raw water quality and chemical injection rate, and output factors such as turbidity of treatment water and UV-VIS. You have selected. As a network learning algorithm, a back propagation method is employed. Since the back propagation method requires a long calculation time, the learning means is provided with a momentum method or a Levenberg-Marquardt optimization method to speed up the learning.
【００４１】当該ネットワークの主な学習条件を以下に
示す。 １）入力データ、教師データ（出力） 入力：原水水温、原水pH、原水濁度、原水アルカリ度、
原水導電率、原水導電率偏差（現在値−６時間前）、Ｐ
ＡＣ注入率、前苛性注入率、前塩素注入率及び原水UV-V
IS（合計１０項目） 出力：２時間後の処理水濁度、２時間後の処理水UV-VIS
（合計２項目） ここで、UV-VIS値はE254（波長254nmでの吸光度、以下U
Vと記す）からE546（波長546nmでの吸光度、以下VISと
記す）を差し引いたものであり、トリハロメタン生成能
と相関がある。また、処理水は、浄水プラントの凝集沈
澱池で固液分離された上澄水を意味する。さらに、前苛
性は、前述のように、アルカリ度不足やpHが低い水源に
対し使用する薬品で、苛性ソーダのことをいう。尚、ネ
ットワークのニューロンの出力は０〜１の範囲であるの
で、出力データをこの範囲で規格化した。 ２）ネットワークアーキテクチャー 階層：入力層（１０）、中間層（１０）、出力層（２） ここで、カッコ内の数字はニューロン数を示す。ニュー
ロンの伝達関数としては、全て下記のシグモイド関数lo
gsigを採用した。logsigの特性を図２に示す。The main learning conditions of the network are shown below. 1) Input data, teacher data (output) Input: Raw water temperature, raw water pH, raw water turbidity, raw water alkalinity,
Raw water conductivity, raw water conductivity deviation (current value-6 hours ago), P
AC injection rate, pre-caustic injection rate, pre-chlorine injection rate and raw water UV-V
IS (10 items in total) Output: treated water turbidity after 2 hours, treated water UV-VIS after 2 hours
Here, the UV-VIS value is E254 (absorbance at a wavelength of 254 nm, hereinafter U
V), minus E546 (absorbance at a wavelength of 546 nm, hereinafter referred to as VIS), which is correlated with trihalomethane-forming ability. Further, the treated water refers to supernatant water that has been solid-liquid separated in a coagulation settling pond of a water purification plant. Further, as described above, pre-caustic is a chemical used for a water source with insufficient alkalinity or low pH, and refers to caustic soda. Since the output of the neuron of the network is in the range of 0 to 1, the output data is normalized in this range. 2) Network architecture Hierarchy: input layer (10), hidden layer (10), output layer (2) Here, the numbers in parentheses indicate the number of neurons. The transfer functions of the neurons are all sigmoid functions lo
gsig was adopted. Fig. 2 shows the characteristics of logsig.
【００４２】logsig（Ｘ）＝１／（１＋exp（−Ｘ）） 図３は、６日間（1998年10月18から同年10月24日）に渡
る処理水の水質予測結果を示したもので、（ａ）は処理
水濁度の実測値と予測値の経時的変化を、（ｂ）は処理
水UV-VISの実績値と予測値の経時的変化を示している。Logsig (X) = 1 / (1 + exp (−X)) FIG. 3 shows the results of the prediction of the quality of the treated water over six days (October 18, 1998 to October 24, 1998). (A) shows the temporal change of the measured value and the predicted value of the treated water turbidity, and (b) shows the temporal change of the actual value and the predicted value of the treated water UV-VIS.
【００４３】結果のごとく、処理水の濁度及びUV-VISの
予測値は、実績値とほぼ一致した経時的変化を辿ってい
る。また、当該ニューラルネットワークの中間層におけ
るニューロン数を１５としても、図３とほぼ同様な結果
が得られた。As can be seen from the results, the predicted values of the turbidity of the treated water and the UV-VIS follow a change with time that almost coincides with the actual value. Also, when the number of neurons in the hidden layer of the neural network was set to 15, almost the same results as those in FIG. 3 were obtained.
【００４４】このように、現在値の水質データや薬品注
入率の値を水質予測手段１１のニューラルネットワーク
に供給することで、ほぼ正確に２時間後の処理水濁度を
予測することができる。As described above, by supplying the current value of the water quality data and the value of the chemical injection rate to the neural network of the water quality prediction means 11, it is possible to predict the treated water turbidity two hours later almost exactly.
【００４５】従来の浄水プラントの維持管理において
は、凝集剤注入率を手動により設定を変えた後に、濁度
観察などよりその除去特性判断を行なって設定の検討を
行なっている。そのため、設定を誤ると良好な水質を得
るのに、多くの時間が費やされる。In the maintenance of a conventional water purification plant, after the setting of the coagulant injection rate is manually changed, the setting of the coagulant is examined by judging its removal characteristics by turbidity observation or the like. Therefore, if the setting is wrong, much time is spent for obtaining good water quality.
【００４６】そこで、本実施形態に係るニューラルネッ
トワークの導入によって、過去及び現在のデータから迅
速かつ正確に一定時間後の処理水濁度を予測することが
可能となり、過誤の運転管理による水質悪化を事前に回
避させることができる。Therefore, the introduction of the neural network according to the present embodiment makes it possible to quickly and accurately predict the turbidity of the treated water after a certain period of time from the past and present data. It can be avoided in advance.
【００４７】特に、ニューラルネットワークを用いて処
理水の濁度及びUV-VISを同時に正確予測することがで
き、これを浄水場水質制御システムに組み込むことで最
適な薬品注入率の決定に役立つ。また、ニューラルネッ
トワークは自己学習可能であるので、これを自動運転制
御システム内に導入することが可能となる。 （第２実施形態）薬品注入率の変更方法（その１） さらに、薬品注入率補正手段１３は、処理水の水質の予
測値が目標値以下となる薬品注入率が最小となるよう
に、該薬品注入率を演算によって補正することも可能で
ある。In particular, the turbidity of the treated water and the UV-VIS can be simultaneously and accurately predicted using a neural network, and incorporating this into a water purification system for a water treatment plant helps to determine the optimum chemical injection rate. Further, since the neural network is capable of self-learning, it can be introduced into the automatic driving control system. (Second Embodiment) Method for Changing Chemical Injection Rate (No. 1) Further, the chemical injection rate correcting means 13 adjusts the chemical injection rate so that the predicted value of the quality of the treated water becomes equal to or less than the target value, so that the chemical injection rate is minimized. It is also possible to correct the chemical injection rate by calculation.
【００４８】ここでの薬品注入率の調整は、薬品注入率
の初期値を過去のデータに基づき、低めに設定し、この
設定値に一定値づつ加算していき、加算毎に水質予測手
段１１で予測した処理水質を目標水質と比較すること
で、最小の薬品注入率を決定する。加算される値は、任
意に設定できる。尚、複数種類の薬品が注入される場
合、総薬品注入率も考慮される。本実施形態において
は、凝集剤としてＰＡＣが、前アルカリ剤としては苛性
ソーダ（以下、前苛性）が採用され、メインとなる薬品
を凝集剤としている。Here, the adjustment of the chemical injection rate is performed by setting the initial value of the chemical injection rate to a lower value based on past data and adding the set value by a constant value. The minimum chemical injection rate is determined by comparing the treated water quality predicted in the above with the target water quality. The value to be added can be set arbitrarily. When a plurality of types of chemicals are injected, the total chemical injection rate is also considered. In the present embodiment, PAC is used as the coagulant and caustic soda (hereinafter, pre-caustic) is used as the pre-alkali agent, and the main chemical is the coagulant.
【００４９】図４に、本発明による凝集剤と前苛性の注
入率の同時決定方法を示す。FIG. 4 shows a method for simultaneously determining the coagulant and pre-caustic injection rates according to the present invention.
【００５０】薬品注入率の初期値は、過去のデータに基
づき設定され、例えば、凝集剤注入率は１０mg/l程度
と、前苛性注入率は０mg/lなどと設定される。先ず、こ
れら薬品注入率の初期値に対し凝集剤注入率が例えば１
mg/lづつ加算され、加算毎に水質予測手段１１で処理水
の水質が予測される。このとき、処理水の濁度とUV-VIS
の予測値が目標値以下になった場合の凝集剤注入率と前
苛性注入率が、暫定的な、凝集剤注入率PAC-SV0と、前
苛性注入率OH-SV0が定められる。The initial value of the chemical injection rate is set based on past data. For example, the coagulant injection rate is set to about 10 mg / l, and the pre-caustic injection rate is set to 0 mg / l. First, the coagulant injection rate is, for example, 1 to the initial value of the chemical injection rate.
The water quality is predicted by the water quality prediction means 11 for each addition. At this time, the turbidity of the treated water and UV-VIS
The coagulant injection rate before and caustic injection rate when the predicted value is equal to or less than the target value, tentative, and coagulant injection rate PAC-SV 0, before caustic injection rate OH-SV 0 is determined.
【００５１】次に、前苛性注入率の初期値に例えば１mg
/lが加算された後、先の要領で凝集剤注入率を得て、こ
のときの凝集剤注入率と前苛性注入率である、PAC-SV1
とOH-SV1が定められる。以下、同様の演算を実行し、PA
C-SVnとPAC-SVn+1が同じ値になれば、PAC-SVnとOH-SVn
を最終的な薬品注入率として採用する。Next, the initial value of the pre-caustic injection rate is, for example, 1 mg.
After adding / l, the coagulant injection rate is obtained as described above, and the PAC-SV 1
And OH-SV 1 are defined. Hereinafter, the same operation is performed, and PA
If C-SV n and PAC-SV n + 1 have the same value, PAC-SV n and OH-SV n
Is adopted as the final chemical injection rate.
【００５２】このように、本実施形態においては、処理
水の水質予測に基づいた、最適な、凝集剤と前苛性の注
入率の決定が可能となる。これにより、当該薬品の過剰
注入が回避される。 （第３実施形態）薬品注入率の変更方法（その２） また、図５は、本発明による凝集剤と前塩素の注入率の
同時決定方法を説明している。ここでは、メインとなる
薬品を凝集剤（ここでは、ＰＡＣ）としている。尚、前
塩素とは、原水に藻類が混入している時に、凝集沈殿処
理工程の前工程において、凝集性改善の目的で添加され
る塩素剤のことをいう。As described above, in this embodiment, it is possible to determine the optimum coagulant and pre-caustic injection rate based on the prediction of the quality of the treated water. This avoids excessive injection of the drug. (Third Embodiment) Method of Changing Chemical Injection Rate (Part 2) FIG. 5 illustrates a method of simultaneously determining an injection rate of a flocculant and pre-chlorine according to the present invention. Here, the main chemical is a flocculant (here, PAC). In addition, pre-chlorine refers to a chlorine agent added for the purpose of improving cohesion in a process preceding the coagulation-sedimentation treatment process when algae are mixed in raw water.
【００５３】薬品注入率の初期値は、第２実施形態と同
様に、過去のデータに基づき設定され、例えば、凝集剤
注入率は１０mg/l程度と、前塩素注入率は０mg/lなどと
設定される。先ず、これら薬品注入率の初期値に対し凝
集剤注入率が例えば１mg/lづつ加算され、加算毎に水質
予測手段１１で処理水の水質が予測される。このとき、
処理水の濁度とUV-VISの予測値が目標値以下になった場
合の凝集剤注入率と前塩素注入率が、暫定的な、凝集剤
注入率PAC-SV0と、前塩素注入率Cl-SV0が定められる。The initial value of the chemical injection rate is set based on the past data as in the second embodiment. For example, the coagulant injection rate is about 10 mg / l, and the pre-chlorine injection rate is 0 mg / l. Is set. First, the coagulant injection rate is added to the initial value of the chemical injection rate, for example, by 1 mg / l, and the water quality predicting means 11 predicts the quality of the treated water for each addition. At this time,
When the turbidity of the treated water and the predicted value of UV-VIS are below the target values, the coagulant injection rate and the pre-chlorine injection rate are provisional, and the coagulant injection rate PAC-SV 0 and the pre-chlorine injection rate Cl-SV 0 is determined.
【００５４】次に、前塩素注入率の初期値に例えば１mg
/lが加算された後、先の要領で凝集剤注入率を得て、こ
のときの凝集剤注入率と前塩素注入率である、PAC-SV1
とCl-SV1が定められる。以下、同様の演算を実行し、PA
C-SVnとPAC-SVn+1が同じ値になれば、PAC-SVnとCl-SVn
を最終的な薬品注入率として採用する。Next, the initial value of the pre-chlorine injection rate is set to, for example, 1 mg.
After adding / l, the coagulant injection rate was obtained as described above, and the coagulant injection rate and the pre-chlorine injection rate at this time, PAC-SV 1
And Cl-SV 1 are defined. Hereinafter, the same operation is performed, and PA
If C-SV n and PAC-SV n + 1 have the same value, PAC-SV n and Cl-SV n
Is adopted as the final chemical injection rate.
【００５５】このように、本実施形態においても、処理
水の水質予測に基づいた、最適な凝集剤と前塩素の注入
率の決定が可能となる。これにより、当該薬品の過剰注
入が回避される。 （第４実施形態）凝集剤注入率が大きすぎるときの対応 第２、３実施形態においては、処理水の濁度とUV-VISと
が共に目標値に達するように薬品注入率が決定される。
濁度は必ず安定した除去が求められるが、UV-VISは必ず
しも除去する必要がない場合がある。このような場合、
薬品注入率のうち、特に凝集剤注入率が大きくなりすぎ
ることが懸念される。As described above, also in the present embodiment, it is possible to determine the optimum coagulant and pre-chlorine injection rate based on the prediction of the quality of the treated water. This avoids excessive injection of the drug. (Fourth Embodiment) Response When Coagulant Injection Rate Is Too Large In the second and third embodiments, the chemical injection rate is determined so that both the turbidity of the treated water and the UV-VIS reach the target values. .
Turbidity is always required for stable removal, but UV-VIS may not always need to be removed. In such a case,
Among the chemical injection rates, there is a concern that the coagulant injection rate becomes excessively large.
【００５６】そこで、凝集剤注入率が大きすぎると判断
された場合、目標値を処理水濁度のみとし、第２，３実
施形態と同様の演算を行う。このようにして、過剰な凝
集剤の注入が回避される。 （第５実施形態）予測値と実績値が合わないときの対応
（その１） また、第１実施形態に係るシステムで予測した処理水の
濁度やUV-VISが実運転時の値とずれることが予想され
る。そこで、本発明に係る薬注制御システムは、予測と
実績が合わないときの対処機能をも備えている。Therefore, if it is determined that the coagulant injection rate is too large, the same calculation as in the second and third embodiments is performed with the target value being only the treated water turbidity. In this way, excessive coagulant injection is avoided. (Fifth embodiment) Correspondence when predicted value and actual value do not match (part 1) In addition, the turbidity of treated water and UV-VIS predicted by the system according to the first embodiment deviate from the values during actual operation. It is expected that. Therefore, the medicine injection control system according to the present invention also has a function to cope with a case where the prediction and the result do not match.
【００５７】実負荷運転では、濁度除去が優先されるこ
とから、当該制御システムは、濁度が正確に予測されて
いるか否かを優先的に判断する。具体的には、図１にお
いて、比較手段１２は、データベース１４に蓄えられた
沈殿水濁度の実績値と予測値とを比較する。そして、一
定期間、この両者の偏差が一定値以内、例えば0.2度以
内、であれば、現行のニューラルネットワークは適正と
判断され、水質予測手段１１において、このネットワー
クモデルが継続して使用される。逆に、一定期間、前記
偏差が0.2度以上であれば、現行のニューラルネットワ
ークは適正でないと判断する。このとき、水質予測手段
１１は、データベース１４内の水質や薬品注入率データ
に基づき、現行のネットワークに再学習を実行させて、
該ネットワークを更新する。In actual load operation, turbidity removal is prioritized, so the control system preferentially determines whether turbidity is accurately predicted. Specifically, in FIG. 1, the comparison unit 12 compares the actual value and the predicted value of the sedimentation water turbidity stored in the database 14. If the deviation between the two is within a certain value, for example, within 0.2 degrees for a certain period, the current neural network is determined to be appropriate, and the water quality prediction means 11 uses this network model continuously. Conversely, if the deviation is 0.2 degrees or more for a certain period, it is determined that the current neural network is not appropriate. At this time, the water quality predicting unit 11 causes the current network to execute re-learning based on the water quality and the chemical injection rate data in the database 14,
Update the network.
【００５８】このように、当該制御システムによれば、
処理水濁度の実績値と予測値の偏差が許容範囲内にある
ニューラルネットワークを維持させているので、常に正
確な処理水の濁度の予測が可能となる。 （第６実施形態）予測値と実績値が合わないときの対応
（その２） また、先の実施形態においては、濁質除去が優先される
が、原水のUV成分が高いところでは、濁度だけでなくUV
成分も安定した除去が求められる場合もある。そこで、
本発明に係る薬注制御システムは、処理水の濁度とUV-V
ISの両者をネットワーク更新の判断指標とすることもで
きる。As described above, according to the control system,
Since the neural network in which the deviation between the actual value and the predicted value of the treated water turbidity is within an allowable range is maintained, it is possible to always accurately predict the turbidity of the treated water. (Sixth embodiment) Correspondence when predicted value and actual value do not match (Part 2) In the above embodiment, turbidity removal is prioritized, but where raw water has a high UV component, turbidity is low. Not only UV
In some cases, stable removal of components is also required. Therefore,
The chemical dosing control system according to the present invention, the turbidity of treated water and UV-V
Both of the IS can be used as a judgment index for updating the network.
【００５９】当該制御システムは、処理水の濁度とUV-V
ISの、実績値と予測値との偏差が許容範囲内のときのみ
のニューラルネットワークモデルを採用している。具体
的には、比較手段１２は、データベース１４に蓄えられ
た処理水濁度の実績値と予測値を比較する。このとき、
濁度の偏差が一定値以内、例えば0.2度以内、であって
も、UV-VISの偏差が一定値、例えば0.05abs（50ｍｍセ
ル換算）、であれば、現行のニューラルネットワークは
適正でないと判断する。ここで、水質予測手段１１は、
データベース１４内の水質や薬品注入率データに基づ
き、現行のネットワークに再学習を実行させて、該ネッ
トワークを更新する。The control system controls the turbidity of the treated water and the UV-V
The neural network model is used only when the deviation between the actual value and the predicted value of IS is within an allowable range. Specifically, the comparing means 12 compares the actual value and the predicted value of the treated water turbidity stored in the database 14. At this time,
Even if the turbidity deviation is within a certain value, for example, within 0.2 degrees, if the deviation of UV-VIS is a certain value, for example, 0.05 abs (converted to 50 mm cell), it is determined that the current neural network is not appropriate. I do. Here, the water quality prediction means 11
Based on the water quality and chemical injection rate data in the database 14, the current network is re-learned to update the network.
【００６０】このように、当該制御システムによれば、
処理水の濁度とUV-VISの、実績値と予測値の偏差が許容
範囲内にあるニューラルネットワークを維持させている
ので、常に正確な処理水の濁度とUV-VISの予測が可能と
なる。As described above, according to the control system,
By maintaining a neural network where the deviation between the actual and predicted values of the turbidity of the treated water and UV-VIS is within the allowable range, it is possible to always accurately predict the turbidity of the treated water and UV-VIS. Become.
【００６１】[0061]
【発明の効果】以上の説明から明らかなように、本発明
は、以下の効果を奏する。As is apparent from the above description, the present invention has the following effects.
【００６２】本発明によれば、過去のデータに基づきシ
ミュレーションでプラントモデルの構築が可能となり、
水質予測、特に処理水の濁度やUV-VIS、が正確に予測す
るできるので、薬品注入率の決定に使用できる。また、
水質や予測結果を蓄積することで、ニューラルネットワ
ークの再学習が可能となる。さらに、ニューラルネット
ワークは自己学習可能であるので、常に最適な処理水の
水質、特に濁度やUV-VISの予測が可能となるばかりでな
く、変動しやすい原水の特性に対応した、自動運転制御
システムの構築が可能となる。そして、この最適な処理
水の水質予測に基づき、最適な薬品注入率の決定、特
に、凝集剤注入率、前苛性注入率及び前塩素注入率の決
定が可能となり、薬品の消費量を最小限に抑えることが
できる。特に、濁度やUVを指標とすることで、過剰な薬
品の注入を防ぐことができる。According to the present invention, a plant model can be constructed by simulation based on past data.
Since water quality prediction, especially turbidity of treatment water and UV-VIS, can be accurately predicted, it can be used for determining the chemical injection rate. Also,
By accumulating the water quality and the prediction results, the neural network can be re-learned. In addition, since the neural network is capable of self-learning, it is possible to always predict the optimal quality of treated water, especially turbidity and UV-VIS, and also to control automatic operation that responds to the characteristics of raw water that tends to vary. A system can be constructed. Then, based on the prediction of the optimum quality of the treated water, it is possible to determine the optimum chemical injection rate, particularly the coagulant injection rate, the pre-caustic injection rate and the pre-chlorine injection rate, and minimize the consumption of chemicals. Can be suppressed. In particular, by using turbidity or UV as an index, injection of excessive chemicals can be prevented.
【図１】本発明に係る薬品注入制御システムの構成図。FIG. 1 is a configuration diagram of a medicine injection control system according to the present invention.
【図２】logsig（シグモイド関数）の特性図。FIG. 2 is a characteristic diagram of logsig (sigmoid function).
【図３】処理水の水質予測結果を示したもので、（ａ）
は処理水濁度の実測値と予測値の経時的変化を、（ｂ）
は処理水UV-VISの実測値と予測値の経時的変化を示した
特性図。FIG. 3 shows a result of predicting the quality of treated water.
Shows the change over time between the measured and predicted values of the treated water turbidity, (b)
FIG. 4 is a characteristic diagram showing a change over time of an actually measured value and a predicted value of the treated water UV-VIS.
【図４】本発明による凝集剤注入率と前苛性注入率の同
時決定の説明図。FIG. 4 is an explanatory diagram of simultaneous determination of a coagulant injection rate and a pre-caustic injection rate according to the present invention.
【図５】本発明による凝集剤注入率と前塩素注入率の同
時決定の説明図。FIG. 5 is an explanatory diagram of simultaneous determination of a coagulant injection rate and a pre-chlorine injection rate according to the present invention.
【図６】浄水設備の現状課題とその対策。[Fig. 6] Current problems of water purification equipment and their countermeasures.
１１…水質予測手段 １２…薬品注入率算出手段 １３…比較手段 １４…データベース 11 ... Water quality prediction means 12 ... Chemical injection rate calculation means 13 ... Comparison means 14 ... Database
───────────────────────────────────────────────────── フロントページの続き (72)発明者 秦野 薫 東京都品川区大崎２丁目１番17号 株式会 社明電舎内 Ｆターム(参考） 4G068 AA02 AB15 AC16 AF32 AF35 AF36 AF40 ────────────────────────────────────────────────── ─── Continuing on the front page (72) Inventor Kaoru Hatano 2-1-1-17 Osaki, Shinagawa-ku, Tokyo F-term in Meidensha Co., Ltd. 4G068 AA02 AB15 AC16 AF32 AF35 AF36 AF40
Claims (9)
ルネットワークに供給して、処理水の水質を予測した
後、この予測値を目標値と比較し、この比較結果に基づ
き、該薬品注入率を調整する薬品注入率制御方法であっ
て、該予測値が目標値以下である場合、該薬品注入率
を、該原水に対し適正な薬品注入率として採用し、該予
測値が目標値以上である場合、該薬品注入率を、演算に
よって補正した後に、再度、前記ニューラルネットワー
クに供給することを特徴とする薬品注入率制御方法。1. A method for predicting the quality of treated water by supplying the water quality of raw water and the injection rate of chemicals to a neural network, comparing the predicted value with a target value, and injecting the chemical based on the comparison result. A chemical injection rate control method for adjusting a rate, wherein when the predicted value is equal to or less than a target value, the chemical injection rate is adopted as an appropriate chemical injection rate for the raw water, and the predicted value is equal to or greater than the target value. Wherein the chemical injection rate is corrected by calculation and then supplied to the neural network again.
ルネットワークに供給して、処理水の水質を予測した
後、この予測値を目標値と比較し、この比較結果に基づ
き、該薬品注入率を調整する薬品注入率制御方法であっ
て、薬品が凝集剤とアルカリ剤である場合、予測値が目
標値以下となる凝集剤とアルカリ剤の注入率が最小とな
るように、該薬品の注入率を調整することを特徴とする
薬品注入率制御方法。2. The water quality of raw water and the injection rate of chemicals are supplied to a neural network to predict the quality of treated water, and the predicted value is compared with a target value. A chemical injection rate control method for adjusting the rate, when the chemical is a coagulant and an alkaline agent, so that the injection rate of the coagulant and the alkaline agent whose predicted value is less than or equal to the target value is minimized, A method for controlling a chemical injection rate, comprising adjusting an injection rate.
ルネットワークに供給して、処理水の水質を予測した
後、この予測値を目標値と比較し、この比較結果に基づ
き、該薬品注入率を調整する薬品注入率制御方法であっ
て、薬品が凝集剤と塩素剤である場合、予測値が目標値
以下となる凝集剤とアルカリ剤の注入率が最小となるよ
うに、該薬品の注入率を調整することを特徴とする薬品
注入率制御方法。3. The water quality of raw water and the injection rate of chemicals are supplied to a neural network to predict the quality of treated water, and the predicted value is compared with a target value. In a chemical injection rate control method for adjusting the rate, when the chemical is a coagulant and a chlorine agent, the injection value of the coagulant and the alkaline agent, the predicted value of which is equal to or less than the target value, is minimized, A method for controlling a chemical injection rate, comprising adjusting an injection rate.
て、この予測値と実績値との偏差が、一定時間、一定値
範囲以外である場合、前記ニューラルネットワークに再
学習させることを特徴とする請求項１記載の薬品注入率
制御方法。4. When the water quality index of the treated water is turbidity and the deviation between the predicted value and the actual value is out of a certain value range for a certain time, the neural network is made to re-learn. 2. The method according to claim 1, wherein the chemical injection rate is controlled.
ISであって、これらの予測値と実績値との偏差が一定値
範囲以外である場合、前記ニューラルネットワークに再
学習させることを特徴とする請求項１記載の薬品注入率
制御方法。5. The water quality index of the treated water is turbidity and UV-V
2. The chemical injection rate control method according to claim 1, wherein the IS is re-learned by the neural network when the deviation between the predicted value and the actual value is out of the fixed value range.
ットワークに供給して処理水の水質を予測する水質予測
手段と、前記水質の予測値と目標値とを比較する比較手
段と、前記比較手段における比較結果に基づき、演算に
よって該薬品注入率を補正する薬品注入率補正手段とを
備えたことを特徴とする薬品注入率制御装置。6. A water quality prediction means for predicting the quality of treated water by supplying the quality of raw water and a chemical injection rate to a neural network, a comparison means for comparing the predicted value of the water quality with a target value, and the comparison means And a chemical injection rate correcting means for correcting the chemical injection rate by calculation based on the comparison result in the above.
予測値が目標値以下となる薬品注入率が最小となるよう
に、該薬品注入率を演算によって補正することを特徴と
する請求項６記載の薬品注入率制御装置。7. The chemical injection rate correcting means corrects the chemical injection rate by calculation so that the chemical injection rate at which the predicted value of the quality of the treated water is equal to or less than the target value is minimized. Item 7. The chemical injection rate control device according to Item 6.
処理水の水質指標が濁度であって、この予測値と実績値
との偏差が、一定時間、一定値範囲以外である、と判断
した場合、ニューラルネットワークに再学習を実行する
ことを特徴とする請求項６記載の薬品注入率制御装置。8. The water quality predicting means, wherein the comparing means determines that the water quality index of the treated water is turbidity, and that the deviation between the predicted value and the actual value is out of a certain value range for a certain time. 7. The chemical injection rate control device according to claim 6, wherein when it is determined, re-learning is performed on the neural network.
処理水の水質指標が濁度及びUV-VISであって、これらの
予測値と実績値との偏差が一定値範囲以外である、と判
断した場合、ニューラルネットワークの再学習を実行す
ることを特徴とする請求項６または７記載の薬品注入率
制御装置。9. The water quality predicting means, wherein the comparing means is configured such that the water quality index of the treated water is turbidity and UV-VIS, and a deviation between the predicted value and the actual value is out of a certain value range. 8. The chemical injection rate control device according to claim 6, wherein when it is determined that the neural network is re-learned, the neural network is re-learned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2000320743A JP4341164B2 (en) | 2000-10-20 | 2000-10-20 | Chemical injection rate control method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2000320743A JP4341164B2 (en) | 2000-10-20 | 2000-10-20 | Chemical injection rate control method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2002126721A true JP2002126721A (en) | 2002-05-08 |
| JP4341164B2 JP4341164B2 (en) | 2009-10-07 |
Family
ID=18798974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2000320743A Expired - Fee Related JP4341164B2 (en) | 2000-10-20 | 2000-10-20 | Chemical injection rate control method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP4341164B2 (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004195304A (en) * | 2002-12-17 | 2004-07-15 | Toshiba Corp | Coagulant injection control method and apparatus |
| KR100808607B1 (en) | 2006-09-21 | 2008-02-28 | 조필호 | Method for automatic injection of coagulant in water purification plant and apparatus thereof |
| WO2013062003A1 (en) * | 2011-10-28 | 2013-05-02 | 株式会社明電舎 | Chemical injection control method and chemical injection controller |
| JP2014050773A (en) * | 2012-09-05 | 2014-03-20 | Metawater Co Ltd | Filtration assistant injection control method and filtration assistant injection control device |
| JP2017140595A (en) * | 2016-02-12 | 2017-08-17 | 株式会社東芝 | Management support system, management support method and management support program |
| KR101838172B1 (en) * | 2016-09-12 | 2018-03-13 | 두산중공업 주식회사 | Apparatus and method for determining chemical input |
| JP2018158284A (en) * | 2017-03-22 | 2018-10-11 | 水ｉｎｇ株式会社 | Method of creating database and water treatment or sludge treatment system |
| WO2020021687A1 (en) * | 2018-07-26 | 2020-01-30 | 三菱電機株式会社 | Water treatment plant |
| EP3719590A1 (en) | 2019-04-02 | 2020-10-07 | Yokogawa Electric Corporation | Plant operation support system and plant operation support method |
| JP2020168618A (en) * | 2019-04-04 | 2020-10-15 | 株式会社東芝 | Operation support device, operation support method, and computer program |
| WO2021065376A1 (en) * | 2019-09-30 | 2021-04-08 | 富士フイルム株式会社 | Search device, method for operating search device, operation program for search device, and flow reaction equipment |
| JP2021173208A (en) * | 2020-04-24 | 2021-11-01 | トヨタ自動車株式会社 | Vehicle control device, vehicle control method and vehicle control computer program |
| CN115417492A (en) * | 2022-08-30 | 2022-12-02 | 同济大学建筑设计研究院(集团)有限公司 | Advanced oxidation system based on underwater vision and control method |
| WO2024034509A1 (en) * | 2022-08-08 | 2024-02-15 | 栗田工業株式会社 | Method for operating waste liquid treatment equipment, method for predicting property of treated waste liquid, operation system, and prediction system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107055732A (en) * | 2017-05-17 | 2017-08-18 | 北京易沃特科技有限公司 | A kind of heavy metals minimizing technology and device |
-
2000
- 2000-10-20 JP JP2000320743A patent/JP4341164B2/en not_active Expired - Fee Related
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004195304A (en) * | 2002-12-17 | 2004-07-15 | Toshiba Corp | Coagulant injection control method and apparatus |
| KR100808607B1 (en) | 2006-09-21 | 2008-02-28 | 조필호 | Method for automatic injection of coagulant in water purification plant and apparatus thereof |
| WO2013062003A1 (en) * | 2011-10-28 | 2013-05-02 | 株式会社明電舎 | Chemical injection control method and chemical injection controller |
| JP2013094686A (en) * | 2011-10-28 | 2013-05-20 | Meidensha Corp | Chemical injection control method and chemical injection controller |
| CN103889900A (en) * | 2011-10-28 | 2014-06-25 | 旭化成化学株式会社 | Chemical injection control method and chemical injection controller |
| US9517954B2 (en) | 2011-10-28 | 2016-12-13 | Asahi Kasei Chemicals Corporation | Chemical injection control method and chemical injection controller |
| JP2014050773A (en) * | 2012-09-05 | 2014-03-20 | Metawater Co Ltd | Filtration assistant injection control method and filtration assistant injection control device |
| JP2017140595A (en) * | 2016-02-12 | 2017-08-17 | 株式会社東芝 | Management support system, management support method and management support program |
| US11549876B2 (en) | 2016-09-12 | 2023-01-10 | Doosan Enerbility Co., Ltd. | Apparatus and method for determining chemical input |
| KR101838172B1 (en) * | 2016-09-12 | 2018-03-13 | 두산중공업 주식회사 | Apparatus and method for determining chemical input |
| JP2018158284A (en) * | 2017-03-22 | 2018-10-11 | 水ｉｎｇ株式会社 | Method of creating database and water treatment or sludge treatment system |
| WO2020021687A1 (en) * | 2018-07-26 | 2020-01-30 | 三菱電機株式会社 | Water treatment plant |
| JPWO2020021687A1 (en) * | 2018-07-26 | 2020-08-06 | 三菱電機株式会社 | Water treatment plant |
| US11649183B2 (en) | 2018-07-26 | 2023-05-16 | Mitsubishi Electric Corporation | Water treatment plant |
| EP3719590A1 (en) | 2019-04-02 | 2020-10-07 | Yokogawa Electric Corporation | Plant operation support system and plant operation support method |
| US11763243B2 (en) | 2019-04-02 | 2023-09-19 | Yokogawa Electric Corporation | Plant operation support system and plant operation support method |
| JP2020168618A (en) * | 2019-04-04 | 2020-10-15 | 株式会社東芝 | Operation support device, operation support method, and computer program |
| JP7234013B2 (en) | 2019-04-04 | 2023-03-07 | 株式会社東芝 | Driving support device, driving support method and computer program |
| JP7254950B2 (en) | 2019-09-30 | 2023-04-10 | 富士フイルム株式会社 | Searching device, searching method, operating program for searching device, and flow reaction equipment |
| JPWO2021065376A1 (en) * | 2019-09-30 | 2021-04-08 | ||
| WO2021065376A1 (en) * | 2019-09-30 | 2021-04-08 | 富士フイルム株式会社 | Search device, method for operating search device, operation program for search device, and flow reaction equipment |
| JP7226388B2 (en) | 2020-04-24 | 2023-02-21 | トヨタ自動車株式会社 | VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD AND COMPUTER PROGRAM FOR VEHICLE CONTROL |
| JP2021173208A (en) * | 2020-04-24 | 2021-11-01 | トヨタ自動車株式会社 | Vehicle control device, vehicle control method and vehicle control computer program |
| WO2024034509A1 (en) * | 2022-08-08 | 2024-02-15 | 栗田工業株式会社 | Method for operating waste liquid treatment equipment, method for predicting property of treated waste liquid, operation system, and prediction system |
| CN115417492A (en) * | 2022-08-30 | 2022-12-02 | 同济大学建筑设计研究院(集团)有限公司 | Advanced oxidation system based on underwater vision and control method |
Also Published As
| Publication number | Publication date |
|---|---|
| JP4341164B2 (en) | 2009-10-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2002126721A (en) | Method and apparatus for controlling injection ratio of chemicals | |
| JP2000218263A (en) | Water quality controlling method and device therefor | |
| US9517954B2 (en) | Chemical injection control method and chemical injection controller | |
| JP2001079310A (en) | Water quality control method and device therefor | |
| JPH06304546A (en) | Operation controller for waterwork plant | |
| KR100331708B1 (en) | Method and apparatus for automatically calculating coagulant injection rate in portable water purification system | |
| KR101042243B1 (en) | chlorine automatic System | |
| JP2008149226A (en) | Wastewater treatment system | |
| JP4188200B2 (en) | Plant-wide optimum process controller | |
| CN110188945B (en) | Sewage prediction system and method in production | |
| Chen et al. | Fuzzy model identification and control system design for coagulation chemical dosing of potable water | |
| JP4649175B2 (en) | Sewage treatment plant control equipment | |
| JPH0938690A (en) | Method for controlling injection of flocculating agent in water treatment | |
| JP3321876B2 (en) | Ozone treatment apparatus, ozone treatment method, and water purification treatment method | |
| JP4982114B2 (en) | Water treatment control device | |
| JP7321014B2 (en) | Operation support equipment for water treatment plants | |
| Carrio et al. | Practical considerations for design of a step-feed biological nutrient removal system | |
| JP4248043B2 (en) | Biological phosphorus removal equipment | |
| KR20140125329A (en) | Optimized coagulant feeding devices based on the prediction of phosphorus concentrations | |
| JP3999869B2 (en) | Biological water treatment equipment | |
| KR101962566B1 (en) | Low Energy Anaerobic Ammonium Oxidation System using Sequence Batch Reactor and Proactive scheduling method for the system | |
| Spink et al. | Design and Operation of a 200‐mgd Direct‐Filtration Facility | |
| JPH06343979A (en) | Corrosion control device for water supply and distribution pipe | |
| JPH1157771A (en) | Biological water treatment and equipment therefor | |
| KR20050063263A (en) | A apparatus and method for controlling the value of concentration contact time(ct) automatically in the chlorine-disinfection process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20051209 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20081216 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20090216 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20090324 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20090525 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20090616 |
|
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20090629 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20120717 Year of fee payment: 3 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 4341164 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20130717 Year of fee payment: 4 |
|
| LAPS | Cancellation because of no payment of annual fees |