JP4537140B2 - BOD estimation apparatus and method - Google Patents

Description

  The present invention relates to a water pollution measurement technique, and more particularly to a BOD measurement technique for obtaining a sewage BOD value (Biochemical Oxygen Demand).

  There are two major types of sewerage systems, a merging type and a diversion type, depending on the treatment method for domestic wastewater and rainwater. The combined type is a method for treating domestic wastewater and rainwater in a lump, and the diversion type is a method for treating domestic wastewater and rainwater separately. In the combined type, the underground sewage pipe can be shared with domestic wastewater and rainwater, but the sewage treatment facility has a heavy sewage treatment burden because it needs to treat not only domestic wastewater but also rainwater. On the other hand, in the diversion type, although it is necessary to construct a drainage pipe dedicated to rainwater, it is only necessary to sewage domestic wastewater at the sewage treatment facility, and the treatment burden can be reduced.

Of these, for the combined sewage treatment facility, the Sewerage Law Enforcement Order was revised (enforced from April 1, 2004) for the purpose of promoting the improvement of the combined sewage system and released from the sewage treatment facility to the rivers and oceans. Water quality standards for discharged water are being strengthened.
This specific content prohibits the discharge of sewage having a quality equal to or higher than a predetermined reference value, and a BOD value (concentration) is used as one of the reference values of water pollution for the discharged water ( (See Non-Patent Document 1, etc.). Therefore, when discharging sewage, it is necessary to confirm that the BOD value of the sewage satisfies the reference value.

  The BOD value used for the water quality standard for effluent water is one of the index items for water pollution established by the government. The temperature is limited to 20 ° C and 5 days a day. During this period, aerobic microorganisms decompose organic substances into the water. The concentration of the amount of oxygen consumed by aerobic microorganisms due to its growth and respiratory action is expressed in mg / l. This is a measure that incorporates the purification phenomenon that occurs naturally in rivers, etc., and has great significance, and is used not only as a quality standard for discharged water, but also as an environmental standard.

  Conventionally, when such a BOD value is measured, there is a standard dilution method as a standard measurement method for manual analysis. In this method, diluted or planted diluted water is added to a sample that has been pretreated (pH adjustment, residual chlorine replacement, supersaturated oxygen expelling), and the oxygen consumption for 5 days at 20 ° C. is 3.5 to 6 mg. Prepare several types of diluted test water with different dilution ratios so that the sample will contain 1 / l, and the dissolved oxygen amount before entering the thermostatic bath for this diluted test water and the dissolved oxygen after leaving it in the thermostatic bath for 5 days The amount of oxygen is analyzed, and the BOD value at 20 ° C. for 5 days is determined from the difference.

  There is also an automated version of such manual analysis, for example, a coulometric method for directly obtaining the BOD value without dilution. This is a method in which seed material and buffer solution are put into a sample and continuously stirred, carbon dioxide is absorbed, and the supplied oxygen is automatically measured to compensate for the pressure drop due to dissolved oxygen in the sample consumed by microbial activity. It is.

The applicant has not yet found prior art documents related to the present invention by the time of filing other than the prior art documents specified by the prior art document information described in this specification.
"Water quality inspection manual for the quality standards of sewage discharged from combined sewers", Ministry of Land, Infrastructure, Transport and Tourism, Sewerage Department, Urban and Regional Development Bureau, http://www.mlit.go.jp/crd/city/sewerage/info /seirei/040416_03.pdf

However, in such a conventional BOD measurement technique, since aerobic microorganisms are actually added to sewage and the oxygen consumption is measured, at least 5 days are required until the measurement result is obtained. There is a problem that it cannot be used as real-time operation data required for water quality management operation in a treatment facility.
For example, when the conventional BOD measurement technology is used, when discharging sewage, it takes five days to obtain the measurement result of the sewage BOD value and confirm whether it can be discharged. It was difficult to carry out the sewage treatment work without delay, and there was a problem that it was not possible to cope with any urgent discharge.

  The present invention has been made to solve such problems, and an object thereof is to provide a BOD estimation apparatus and method that can obtain a BOD value of sewage in an extremely short time.

In order to achieve such an object, a BOD estimation apparatus according to the present invention is a BOD estimation apparatus that estimates a BOD value (Biochemical Oxygen Demand) of sewage, and a COD value obtained from sewage. (Chemical Oxygen Demand: chemical oxygen demand), SS value (Suspended Solid: suspended matter amount), and model input data including water temperature, and model output data consisting of measured BOD measured from the sewage and estimation model consisting of the case base having a plurality of cases comprising a pair of input and output values representative of one or more history data among the history data created based on a plurality of history data, the estimation target Cases with input values similar to the input data including COD values, SS values, and water temperatures obtained from sewage are searched from the case base of the estimation model, Those comprising an estimation processor for calculating output BOD value of the sewage on the basis of the output value of cases.

In addition, the BOD estimation method according to the present invention is a BOD estimation method for estimating the BOD value (Biochemical Oxygen Demand) of sewage, and the COD value (Chemical Oxygen Demand: chemical oxygen) obtained from the sewage. (Required amount), SS value (Suspended Solid: suspended matter amount), and model input data including water temperature, and created based on a plurality of historical data consisting of model output data consisting of measured BOD values measured from the sewage COD obtained from the sewage to be estimated using an estimation model consisting of a case base having a plurality of cases consisting of pairs of input values and output values representing one or more historical data among the respective historical data A case having an input value similar to the input data including the SS value, SS value, and water temperature is searched from the case base of the estimation model, and based on the output value of the searched similar case. Those comprising an estimation process step of calculating output BOD value of the sewage.

According to the present invention, based on a plurality of history data consisting of pairs of model input data including COD values, SS values, and water temperatures obtained from sewage, and model output data consisting of BOD actual measurement values measured from the sewage. It is obtained from the sewage to be estimated using an estimation model consisting of a case base having a plurality of cases consisting of pairs of input values and output values that represent one or more historical data among the generated historical data. A case having an input value similar to the input data including the COD value, the SS value, and the water temperature is searched from the case base of the estimation model, and the BOD value of the sewage is estimated based on the output value of the searched similar case. . At this time, since the desired BOD can be estimated by a calculation process in a short time after the input data is obtained, as a result, the time required for acquiring the input data from the sewage is actually extremely short (about 1 hour at the time of application). With time, the sewage BOD value can be estimated. In addition, the time required for input data acquisition is expected to be shortened in the future, and the sewage BOD value can be estimated in a shorter time.

Therefore, compared with the case where an aerobic microorganism is actually added to sewage and the oxygen consumption is measured over 5 days to obtain a BOD value as in the conventional case, according to the present embodiment, in the sewage treatment facility, It can be used as real-time operation data required for water quality management operation.
As a result, when inflowing sewage is treated or discharged, it can be confirmed whether or not the sewage can be discharged based on the BOD value of the sewage in a very short time, and the sewage treatment work can be carried out without delay while managing the water quality. Even in case of emergency, it is possible to cope with the situation where it is necessary to release it.

Next, embodiments of the present invention will be described with reference to the drawings.
[BOD estimation device]
First, a BOD estimation apparatus according to an embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration of a BOD estimation apparatus according to an embodiment of the present invention.
The BOD estimation device 10 uses the results measured from various measuring devices 2 from the sewage 1 as input data 3, and based on an estimation model generated in advance, output data corresponding to the input data 3, that is, a BOD estimated value. 4 is an apparatus that estimates and outputs 4.

  In this embodiment, as the input data 3 used for estimating the BOD value, the COD value of sewage (Chemical Oxygen Demand: chemical oxygen demand [mg / l]), SS value (Suspended Solid: amount of suspended matter [mg / l] l]), water temperature [° C.], hydrogen ion concentration [pH], transparency [cm], total phosphorus [mg / l], total nitrogen [mg / l], etc. An input parameter (input variable) that can be measured in time is used, and a desired BOD value is estimated based on input data 3 that is a combination of these input parameters.

The COD value is the amount of oxygen consumed when an organic substance in water is chemically oxidized with an oxidant, and indicates the concentration of the amount of oxygen consumed by potassium permanganate (oxidant) It is. The higher the number, the more organic matter.
SS is an extremely small suspended substance mixed in water, such as plankton, dead organisms, debris, dung and their decomposition products. The numerical value indicates the concentration of the substance remaining on the filter paper when filtered through the filter paper. The higher the numerical value, the higher the turbidity, including organic substances.

The hydrogen ion concentration is an index representing the acidity (pH <7), alkalinity (pH> 7), and neutrality (pH = 7) of water. When the hydrogen ion concentration of water is far from neutrality, contamination of foreign matters is considered.
The degree of transparency indicates the degree of transparency of water, and is represented by the height (cm) of the water layer when the double cross (or No. 5 type) at the bottom of the transparency meter can be clearly read for the first time. In many cases, it has a good correlation with the SS value and BOD value in relation to the cleanness of the apparent water.

Total phosphorus is the total amount of phosphorus compounds in water expressed in terms of phosphorus concentration and is used as an indicator of eutrophication. The higher the value of total phosphorus, the more human waste, detergent, fertilizer, etc. are contained.
Total nitrogen represents the total amount of nitrogen of various forms of nitrogen compounds in water and is used as an indicator of eutrophication. Total nitrogen is used as an abnormal limit value of plankton together with total phosphorus.
In any case, a measurement result can be obtained in about one hour with these input parameters using the current measuring device.

  In FIG. 1, a BOD estimation apparatus 10 is composed of an information processing apparatus having a computer as a whole, and includes an input interface unit (hereinafter referred to as an input I / F unit) 11, an operation input unit 12, a storage unit 13, an estimation processing unit 14, A screen display unit 15 and an output interface unit (hereinafter referred to as an output I / F unit) 16 are provided. In the following, as an example of the estimation model for estimating the BOD value from the input data 3, a case base that retrieves a case close to the input data from a large number of cases and obtains a desired estimated value will be described as an example.

The input I / F unit 11 is a circuit unit that is connected to an external device such as the measurement device 2 via a communication line, receives various information such as input data 3 from the measurement device 2, and outputs the information to the estimation processing unit 14. is there.
The operation input unit 12 is an input device such as a keyboard or a mouse that detects an operator operation such as a BOD estimation process start instruction, an estimation result display instruction, or manual input of the input data 3 and outputs the detected operation to the estimation processing unit 14. is there.

  The storage unit 13 includes a hard disk, a memory, and the like, and is a storage device that stores various types of information and programs necessary for processing operations in the estimation processing unit 14. As information used for the estimation process, an estimation model 13A (black box estimation model) for estimating a desired BOD value based on the input data 3 is stored in the storage unit 13. Further, a program 13 </ b> P that is read and executed by the estimation processing unit 14 as a program is stored in the storage unit 13. The estimation model 13A and the program 13P are stored in advance in the storage unit 13 from another device or storage medium via the input I / F unit 11.

The estimation processing unit 14 is a processing unit that estimates and outputs the BOD estimated value 4 corresponding to the input data 3 input from the input I / F unit 11 or the operation input unit 12 using the estimation model 13A of the storage unit 13. . The estimation processing unit 14 includes a microprocessor such as a CPU and its peripheral circuits. By reading and executing the program 13P of the storage unit 13, the hardware and the program 13P cooperate with each other to perform various functional units. Realize.
Functional means realized by the estimation processing unit 14 include an input data processing means 14A, a similar case search means 14B, and an output calculation means 14C.

The input data processing unit 14A is a functional unit that performs predetermined preprocessing on the input data 3 input from the input I / F unit 11 or the operation input unit 12.
The similar case retrieval unit 14B is a functional unit that retrieves cases similar to the input data preprocessed by the input data processing unit 14A with reference to the estimation model 13A in the storage unit 13.
The output calculation unit 14C is a functional unit that calculates an output value corresponding to the input data, that is, the BOD estimated value 4, based on the output value of the case obtained by the similar case search unit 14B.

The screen display unit 15 includes a LCD, a CRT, and the like, and is a screen display device that displays various information such as an estimation result obtained by the estimation processing unit 14 on the screen based on an instruction from the estimation processing unit 14.
The output I / F unit 16 is a circuit unit that outputs various information such as an estimation result obtained by the estimation processing unit 14 to an external device such as a control device via a communication line based on an instruction from the estimation processing unit 14. It is.

[Estimated model]
Next, an estimation model used in the BOD estimation apparatus according to the present embodiment will be described with reference to FIG. 2 and FIG. FIG. 2 is a schematic diagram illustrating an estimation operation in the BOD estimation apparatus according to the present embodiment. FIG. 3 is an example of time-series data used for generating an estimation model.
In general, an estimation model is a model obtained by modeling a causal relationship or an inference process between a model input value indicating an estimation condition and a desired model output value. As shown in FIG. 2, the estimation model 13 </ b> A handled in the present embodiment has an output corresponding to input data 3 when an actual measurement value such as a COD value, an SS value, and a water temperature of sewage is given as input data 3. BOD estimated value 4 is output as data.

  In order to create such an estimation model 13A, time series data 5 indicating the characteristics of sewage is required. As shown in FIG. 3, the time series data 5 includes sewage COD value [mg / l], SS value [mg / l], water temperature [° C.], hydrogen ion concentration [pH], transparency [cm], etc. It consists of a plurality of history data 6 consisting of pairs of model input data 51 obtained in advance and model output data 52 having a desired BOD value [mg / l]. The model input data 51 and model output data 52 of the history data 6 are actually measured from sewage in the past.

As a configuration of the estimation model 13A, a black box estimation model in which the causal relationship and the inference process are not clarified by a mathematical formula is used instead of the mathematical model in which the causal relationship and the inference process are expressed by a mathematical formula using a physical law.
This black box estimation model includes a case base, a fuzzy inference base, and a model using a neural network. In particular, the case-based reasoning model is a well-known modeling technique that can be applied to general objects in which the continuity of the input / output relationship of the system is established based on the concept of topology (for example, JP-A-11-372898). (See publications).

[Case base]
Next, with reference to FIG. 4, the case base used in the BOD estimation apparatus according to the present embodiment will be described in detail. FIG. 4 is an explanatory diagram showing a case-based configuration used in the BOD estimation apparatus according to the present embodiment.
Case-based reasoning (CBR) is a black box modeling that relates input / output relationships according to a predetermined algorithm from learning data without qualitative meaning of input / output relationships. This is a technique for deriving a desired solution by directly using past cases similar to a given problem.

In the present embodiment, a case where TCBM (Topological Case-Based Modeling) is used among such case-based reasoning will be described as an example.
TCBM is a modeling technique that uses the framework of case-based reasoning on the premise that continuity is established in the input / output relationship in the inference target. As a feature, TCBM is based on the concept of continuous mapping in mathematical topology (topology). Based on this, the case base corresponding to the output resolution, that is, the output error allowable range, and the similarity indicating the relationship between the cases are defined.

As shown in FIG. 4A, when a plurality of sets of model input data x1, x2 and model output data y are obtained as history data obtained in the past from the target, these history data are shown in FIG. As shown in b), they are arranged in the input space.
Here, when the estimation error required for the case base, that is, the output error allowable width ε is given, as shown in FIG. 4C, the input space is divided into partial sections called meshes using the output error allowable width ε. By dividing and quantizing, it is possible to define an input neighborhood corresponding to the size of the output neighborhood, that is, a case.

  Accordingly, each history data is distributed to each mesh based on the model input data x1, x2. Then, a mesh to which one or more history data is distributed among the meshes is selected as an example, and an input / output value and an output value representing the history data in the mesh are calculated.

At this time, as shown in FIG. 4D, when a plurality of history data is distributed to the same mesh, an average value of the model output data y of each history data is used as an output value representing the case, The median value of the mesh is used as an input value representing the case, and each history data is integrated as one case.
As a result, for all cases, the error between the model output data of each history data distributed to the mesh of the case and the output value of the case satisfies the output error allowable range ε.

[Operation of this embodiment]
Next, the estimation operation of the BOD estimation apparatus according to the embodiment of the present invention will be described with reference to FIG. FIG. 5 is a flowchart showing an estimation process of the BOD estimation apparatus according to the embodiment of the present invention.
The estimation processing unit 14 of the BOD estimation apparatus 10 performs the estimation process of FIG. 5 when estimating the BOD value of arbitrary sewage.

First, new input data 3 consisting of a combination of various input parameters measured from the sewage 1 to be estimated by the measuring device 2 is fetched from the input I / F unit 11 and the operation input unit 12 (step 100), and the input data. A predetermined pre-process is performed by the processing means 14A (step 101).
As this preprocessing, for each input parameter, a process for removing measurement errors included in the input data by calculating a statistical value such as a moving average value using a plurality of input data values obtained in time series Various data processing processes such as a process of converting input data to data having a strong correlation with output data by shifting the input data on the time axis are performed as necessary.

  Next, after the similarity is initialized to zero by the similar case search means 14B (step 102), the input data processing means 14A refers to the estimated model (case base) 13A stored in the storage unit 13 and A similar case similar to the preprocessed input data is searched (step 103). At this time, the similar case search unit 14B searches for similar cases based on the above-described TCBM similarity. FIG. 6 is an explanatory diagram showing case search processing based on similarity.

The degree of similarity is a scale indicating how much similarity each case has with a new prediction condition, that is, a mesh corresponding to input data, among the meshes provided in the input space of the case base.
FIG. 6 shows an example in which the mesh corresponding to the input data x1, x2 is a central mesh located at the center. If a case exists in the center mesh, the case and the input data are defined as “similarity = 0”. In addition, the example existing next to the center mesh is “similarity = 1”, and thereafter, the degree of similarity increases by 1 each time the mesh is separated from the center mesh.

  Therefore, when estimation is performed, the estimated value based on the case of similarity i has an accuracy within (i + 1) × output error allowable width ε. At this time, when the cases on both sides are successfully used for the input data to be estimated, it is expected that the output value has an accuracy better than (i + 1) × output error allowable width ε. In addition, when only one case is used for the value to be estimated, it is expected based on the continuity of the input / output relationship that the accuracy is about (i + 1) × output error tolerance ε. .

  In FIG. 5, the similar case search means 14B determines whether there is a similar case in the range indicated by the similarity (step 104). If there is no similar case (step 104: NO), the similarity is incremented by 1 and the search range is set. After expansion (step 105), the process returns to step 103 to search for similar cases.

If there are similar cases in the range indicated by the similarity (step 104: YES), the output calculation unit 14C calculates one output value representing these from the output values of all the obtained cases ( Step 106), a desired BOD estimated value 4 corresponding to the input data 3 is output (Step 107), and the series of estimation processes is terminated.
As a result, the estimated BOD value 4 calculated by the output calculation unit 14C is displayed on the screen display unit 15 or output from the output I / F unit 16 to the external device.

FIG. 7 is an explanatory diagram showing an estimation result of the BOD estimation apparatus 10 according to the present embodiment, in which the horizontal axis represents the actual BOD value measured by the conventional BOD measurement method, and the vertical axis represents the BOD according to the present embodiment. This is a BOD estimated value estimated by the estimating apparatus 10.
In this estimation, the BOD value of sewage flowing into an existing sewage treatment facility was estimated using the COD value, SS value, and water temperature as input parameters (input variables). Although there are some estimation errors in some cases, the correlation coefficient between them is as extremely high as 0.985505, and a good estimation result is obtained.

FIG. 8 is an explanatory diagram illustrating an example of the estimation operation of the BOD estimation apparatus 10 according to the present embodiment, in which the horizontal axis is the observation date, the vertical axis is the BOD actual measurement value measured by the conventional BOD measurement method, The vertical axis represents the BOD estimated value estimated by the BOD estimating apparatus 10 according to the present embodiment.
This estimation result is obtained by continuously estimating the BOD value of the sewage flowing into the sewage treatment facility over one week using the COD value, the SS value, and the water temperature as input parameters (input variables). Despite the fact that the BOD of the sewage is large and steeply changed, there is almost no error between the measured BOD value (shown by the broken line in the figure) and the estimated BOD value (shown by the solid line in the figure), However, very good estimation results are obtained.

  As described above, in the present embodiment, a plurality of pairs of model input data including the COD value, SS value, and water temperature obtained from sewage and model output data including BOD actual measurement values measured from the sewage are provided. A non-linear black box estimation model created based on historical data is used to estimate the COD value, SS value obtained as input data from the sewage to be estimated, and the BOD value of the sewage corresponding to the water temperature. It is a thing. At this time, since the desired BOD can be estimated by a calculation process in a short time after the input data is obtained, as a result, the time required for acquiring the input data from the sewage is actually extremely short (about 1 hour at the time of filing). With time, the sewage BOD value can be estimated. In addition, the time required for input data acquisition is expected to be shortened in the future, and the sewage BOD value can be estimated in a shorter time.

Therefore, compared to the case where an aerobic microorganism is actually added to sewage and the oxygen consumption is measured over 5 days to obtain BOD as in the prior art, according to this embodiment, the water quality in the sewage treatment facility is as follows. It can be used as real-time operation data required for management operation.
As a result, when inflowing sewage is treated or discharged, it can be confirmed whether or not the sewage can be discharged based on the BOD value of the sewage in a very short time, and the sewage treatment work can be carried out without delay while managing the water quality. Even in case of emergency, it is possible to cope with the situation where it is necessary to release it.

  Since only the COD value, SS value, and water temperature of sewage are used as input parameters (input variables), the estimation accuracy sufficient for practical use as shown in FIGS. It can be obtained by acquiring only three types of input data from the sewage. As a result, the work required for acquiring the input data can be greatly reduced, and the work load required for BOD estimation can be greatly reduced. When estimating the BOD value, the BOD value may be estimated by adding other input parameters such as hydrogen ion concentration, transparency, total phosphorus, total nitrogen, etc. Can do.

In the above description, the case where the BOD estimation apparatus 10 uses the estimation model 13A previously generated from the history data has been described as an example. However, the BOD estimation apparatus 10 generates the estimation model 13A and updates it. Also good.
In this case, the estimation processing unit 14 may be provided with model generation means for executing the above-described case base generation process of FIG. 4, for example, and the estimation model 13A may be generated based on the history data input from the outside. In addition, case update means is provided in the estimation processing unit 14 so that the output data of the corresponding case data is recalculated based on the history data consisting of pairs of the BOD actual measurement values actually measured from the sewage and the input data at that time. In this case, the output data may be recalculated in consideration of the time weight due to the forgetting count.

It is a block diagram which shows the structure of the BOD estimation apparatus concerning one embodiment of this invention. It is the schematic which shows the estimation operation | movement with the BOD estimation apparatus concerning this Embodiment. It is an example of the time series data used for the estimation model production | generation of the BOD estimation apparatus concerning this Embodiment. It is explanatory drawing which shows the example base structure used with the BOD estimation apparatus concerning this Embodiment. It is a flowchart which shows the estimation process of the BOD estimation apparatus concerning one embodiment of this invention. It is explanatory drawing which shows the case search process based on similarity. It is explanatory drawing which shows the estimation result of the BOD estimation apparatus concerning this Embodiment. It is explanatory drawing which shows the estimation operation example of the BOD estimation apparatus concerning this Embodiment.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Sewage, 2 ... Measuring equipment, 3 ... Input data, 4 ... Output data, 5 ... Time series data, 51 ... Model input data, 52 ... Model output data, 6 ... History data, 10 ... BOD estimation apparatus, 11 ... Input I / F unit, 12 ... operation input unit, 13 ... storage unit, 13A ... estimation model (case base), 13B ... program, 14 ... estimation processing unit, 14A ... input data processing unit, 14B ... similar case search unit, 14C: Output calculation means, 15: Screen display unit, 16: Output I / F unit.

Claims (2)

In the BOD estimation device for estimating the BOD value (Biochemical Oxygen Demand) of sewage,
Model consisting of COD values (Chemical Oxygen Demand: chemical oxygen demand), SS values (Suspended Solid), and water temperature obtained from sewage, and BOD measured values measured from the sewage Created based on a plurality of history data consisting of pairs with output data, comprising a case base having a plurality of cases consisting of pairs of input values and output values representing one or more history data of each history data An estimation model;
Cases having input values similar to the input data including the COD value, SS value, and water temperature obtained from the sewage to be estimated are searched from the case base of the estimation model, and the output values of the searched similar cases are obtained. And an estimation processing unit that calculates and outputs the BOD value of the sewage based on the BOD estimation device. In the BOD estimation method for estimating the BOD value (Biochemical Oxygen Demand) of sewage,
Model consisting of COD values (Chemical Oxygen Demand: chemical oxygen demand), SS values (Suspended Solid), and water temperature obtained from sewage, and BOD measured values measured from the sewage Estimate consisting of a case base having a plurality of cases consisting of pairs of input values and output values representing one or more history data among each history data created based on a plurality of history data consisting of pairs of output data Using the model, a case having an input value similar to the input data including the COD value, the SS value, and the water temperature obtained from the sewage to be estimated is searched from the case base of the estimation model, and the similarities searched. A BOD estimation method comprising an estimation process step of calculating and outputting a BOD value of the sewage based on an output value of the case .

Images